To see the other types of publications on this topic, follow the link: FORENSICS HANDWRITTEN DOCUMENT ANALYSIS.
Journal articles on the topic 'FORENSICS HANDWRITTEN DOCUMENT ANALYSIS'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 journal articles for your research on the topic 'FORENSICS HANDWRITTEN DOCUMENT ANALYSIS.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse journal articles on a wide variety of disciplines and organise your bibliography correctly.
1
Krasiuk, Ihor. "SIGNATURES AND SHORT HANDWRITTEN NOTES AS OBJECTS OF EXPERT ANALYSIS." Criminalistics and Forensics, no. 67 (August 9, 2022): 427–38. http://dx.doi.org/10.33994/kndise.2022.67.44.
Full textAbstract:
A detailed scientific analysis of the signature and short handwritten notes as objects of expert research has been carried out. The essence and understanding of the object of judicial handwriting examination are determined. The etymology of the terms “document”, “signature”, “short handwritten note” is investigated, the components of the object of forensic handwriting examination are established, on the basis of which the definition of the object of forensic handwriting examination is formulated as a collective concept that includes phenomena, processes and events of objective reality related to handwritten texts, as well as material carriers of information that reflect these phenomena, processes and events, which are sources of information about them and are provided for research by an expert (experts). It is concluded that “writing” and “handwriting” are close, but independent categories. They correlate with each other as a whole and part of a written functional system, are expressed in a manuscript on the basis of a written and written-motor functional-dynamic complex, have the properties of a wide and narrow profile, are complex and homogeneous objects of forensic handwriting examination. The characteristic features of the signature are determined: it is an identification mark of a certain person; performed by hand in the form of a graphic image; may consist of letters of the surname or be a conditional graphic design of the surname, initials, name; applied to a document in order to certify various facts and events. It is emphasized that the material carrier of information about the fact of the letter, its signs and other circumstances that are important in criminal proceedings, in our case, is a small handwritten product (signature and / or a short handwritten note) reflected in the corresponding document. It is proved that the signature and/or a short handwritten note are the components of the complex of objects of forensic handwriting examination. These include the material carrier itself, that is, the document in a forensic sense, as well as the phenomena, processes and events of objective reality associated with the criminal offense under investigation and reflected on the material media provided to the expert (experts) for research. Key words: small handwriting object, signature, short handwriting, object of ex- amination, forensic handwriting examination.
2
Mohammed, Twana Latif, and Ahmed Abdullah Ahmed. "Offline Writer Recognition for Kurdish Handwritten Text Document Based on Proposed Codebook." UHD Journal of Science and Technology 5, no. 1 (March 31, 2021): 21–27. http://dx.doi.org/10.21928/uhdjst.v5n2y2021.pp21-27.
Full textAbstract:
Handwritten text recognition has been an ongoing attractive task to research in the field of document analysis and recognition with applications in handwriting forensics, paleography, document examination, and handwriting recognition. In the present research, an automatic method of writer recognition is presented using digitized images of unconstrained texts. Despite the increasing efforts by prior literature on the different methods used for the same purpose, such methods performance, particularly their accuracy, has not been promising, leaving plenty of room for improvements. This method made use of codebook-based writer characterization, with each writing sample represented by a group of computed features from a primary and secondary codebook. The writings were then represented through the computation of the probability of codebook patterns occurrence, and the probability distribution was employed for each writer’s characterization. Writer identification process involved comparing two writings through the computation of the distances between their respective probability distribution. The study carried out experiments to determine the performance of the implemented method in light of rates of identification with the help of standard datasets, namely, KRDOH and IAM, the former being the most current and largest Kurdish handwritten datasets with 1076 writers, and the latter being a dataset containing 650 writers. The outcome of the experiments was promising with a rate of identification of 94.3%, with the proposed method outperforming the state-of-the-art methods by 2–3%.
3
Khan, Majid A., Nazeeruddin Mohammad, Ghassen Ben Brahim, Abul Bashar, and Ghazanfar Latif. "Writer verification of partially damaged handwritten Arabic documents based on individual character shapes." PeerJ Computer Science 8 (April 20, 2022): e955. http://dx.doi.org/10.7717/peerj-cs.955.
Full textAbstract:
Author verification of handwritten text is required in several application domains and has drawn a lot of attention within the research community due to its importance. Though, several approaches have been proposed for the text-independent writer verification of handwritten text, none of these have addressed the problem domain where author verification is sought based on partially-damaged handwritten documents (e.g., during forensic analysis). In this paper, we propose an approach for offline text-independent writer verification of handwritten Arabic text based on individual character shapes (within the Arabic alphabet). The proposed approach enables writer verification for partially damaged documents where certain handwritten characters can still be extracted from the damaged document. We also provide a mechanism to identify which Arabic characters are more effective during the writer verification process. We have collected a new dataset, Arabic Handwritten Alphabet, Words and Paragraphs Per User (AHAWP), for this purpose in a classroom setting with 82 different users. The dataset consists of 53,199 user-written isolated Arabic characters, 8,144 Arabic words, 10,780 characters extracted from these words. Convolutional neural network (CNN) based models are developed for verification of writers based on individual characters with an accuracy of 94% for isolated character shapes and 90% for extracted character shapes. Our proposed approach provided up to 95% writer verification accuracy for partially damaged documents.
4
Islam, Ammad Ul, Muhammad Jaleed Khan, Muhammad Asad, Haris Ahmad Khan, and Khurram Khurshid. "iVision HHID: Handwritten hyperspectral images dataset for benchmarking hyperspectral imaging-based document forensic analysis." Data in Brief 41 (April 2022): 107964. http://dx.doi.org/10.1016/j.dib.2022.107964.
Full text
5
Pichugin, S. A. "On the issue of new forensic methods for establishing the limitation period for the execution of document details." Courier of Kutafin Moscow State Law University (MSAL)), no. 2 (May 17, 2021): 140–46. http://dx.doi.org/10.17803/2311-5998.2021.78.2.140-146.
Full textAbstract:
The author critically examines the original forensic technique of “copying fragments of signature strokes (handwritten records) moistened with a system of solvents”. The provisions of this method contain the statement that the color of the coloring substance can be reliably determined when the studied document details were performed. The expert determines the categories of color shades visually (by eye). The comparative stage of the expert study is based on comparing the color of the dye used to make the document under study with the color scheme of the dye details of a similar method of execution, acting as comparison samples. As a result of the comparison of the colors of the dyes that were used to perform the studied details, and possibly the sample details, the expert has a personal opinion about the prescription of the studied document details. It is assumed that such a “technique” allows you to reliably establish the prescription of the details of the studied documents. The relevance of theoretical and practical analysis of the provisions of this “methodology” is associated with its active and unjustified use in solving expert problems in arbitration, civil and criminal proceedings.
6
Hasan, Md Al Mehedi, Jungpil Shin, and Md Maniruzzaman. "Online Kanji Characters Based Writer Identification Using Sequential Forward Floating Selection and Support Vector Machine." Applied Sciences 12, no. 20 (October 12, 2022): 10249. http://dx.doi.org/10.3390/app122010249.
Full textAbstract:
Writer identification has become a hot research topic in the fields of pattern recognition, forensic document analysis, the criminal justice system, etc. The goal of this research is to propose an efficient approach for writer identification based on online handwritten Kanji characters. We collected 47,520 samples from 33 people who wrote 72 online handwritten-based Kanji characters 20 times. We extracted features from the handwriting data and proposed a support vector machine (SVM)-based classifier for writer identification. We also conducted experiments to see how the accuracy changes with feature selection and parameter tuning. Both text-dependent and text-independent writer identification were studied in this work. In the case of text-dependent writer identification, we obtained the accuracy of each Kanji character separately. We then studied the text-independent case by considering some of the top discriminative characters from the text-dependent case. Finally, another text-dependent experiment was performed by taking two, three, and four Kanji characters instead of using only one character. The experimental results illustrated that SVM provided the highest identification accuracy of 99.0% for the text-independent case and 99.6% for text-dependent writer identification. We hope that this study will be helpful for writer identification using online handwritten Kanji characters.
7
Hora, I. V., and I. I. Popovych. "Comprehensive study of objects of judicial and technical examination of documents in solving issues regarding the establishment of their making." Uzhhorod National University Herald. Series: Law, no. 63 (August 9, 2021): 288–92. http://dx.doi.org/10.24144/2307-3322.2021.63.50.
Full textAbstract:
The article is devoted to the analysis of the essence of integrated research during the judicial and technical expertise to establish the prostitution of documents. The attention is drawn to the fact that the forensic examination with the establishment of the preparation of documents is the most difficult among other species of this kind of examinations and to be complex. The authors consider the peculiarities of this type of expertise and emphasizes that such examinations have difficulty in carrying out the use of special equipment and physicochemical research methods. The paths of determining the preparation of the paperwork are emphasized: determining the specific time of manufacture of each of the details with a further comparison of the results obtained among themselves; establishing conformity between the time of signature and handwritten records; the printing time of printing and text printing time, establish a chronological sequence of details in the document.
It was concluded that the decision of the expert problem with establishing the prescription of the document requires the use of so-called "destructive methods". The main complexity of the examination of the process of making the preparation of the document is that when conducting any actions with a document (cutting, selection of ink samples), the document can be fully or partially destroyed. In this regard, expert institutions that take an obligation to carry out such examinations, pay attention to the ability to damage the document and in this connection declare a relevant request for permission to carry out such actions. Such permission should be in the document on the appointment of expertise or in the letter. Attention is drawn to the fact that not the provision of information about the time of receipt of the document may lead to the impossibility of determining the prescription of the document. After a long time and complex research process, the expert is forced to give a conclusion "is not possible."
8
Rabaev, Irina, Izadeen Alkoran, Odai Wattad, and Marina Litvak. "Automatic Gender and Age Classification from Offline Handwriting with Bilinear ResNet." Sensors 22, no. 24 (December 9, 2022): 9650. http://dx.doi.org/10.3390/s22249650.
Full textAbstract:
This work focuses on automatic gender and age prediction tasks from handwritten documents. This problem is of interest in a variety of fields, such as historical document analysis and forensic investigations. The challenge for automatic gender and age classification can be demonstrated by the relatively low performances of the existing methods. In addition, despite the success of CNN for gender classification, deep neural networks were never applied for age classification. The published works in this area mostly concentrate on English and Arabic languages. In addition to Arabic and English, this work also considers Hebrew, which was much less studied. Following the success of bilinear Convolutional Neural Network (B-CNN) for fine-grained classification, we propose a novel implementation of a B-CNN with ResNet blocks. To our knowledge, this is the first time the bilinear CNN is applied for writer demographics classification. In particular, this is the first attempt to apply a deep neural network for the age classification. We perform experiments on documents from three benchmark datasets written in three different languages and provide a thorough comparison with the results reported in the literature. B-ResNet was top-ranked in all tasks. In particular, B-ResNet outperformed other models on KHATT and QUWI datasets on gender classification.
9
B.M, Adeyemi, Olaoye O.J, Uchehara C.C, Akinola O.M, and Sunmola F.O. "Adoption of Off-Line Signature Verification and Forgery Detection System Using Additive Fuzzy and TS Modelling Technique in Financial Auditing and Forensics Investigation." International Journal of Computer Science and Mobile Computing 10, no. 6 (June 30, 2021): 38–59. http://dx.doi.org/10.47760/ijcsmc.2021.v10i06.004.
Full textAbstract:
This paper presents a robust signature verification and forgery detection system using Additive fuzzy and TS modeling technique. The features of various handwritten signatures are sampled with proper analysis and encapsulated to devise an effective verification system. Grid method was used to extract features angles for detection of forgeries and verification of genuine signatures. In financial Accounting, Auditing and Forensic Investigation, signature forgery could occur in various ways. This could be carried out on papers, sales documents such as invoices or inventory procurement requisition paper, title documents on landed property or other tangible assets. It is also perpetrated on payment authorization such as cheques, payment vouchers both in cash and on bills. During this exercise, the fraud perpetrators perfect their concentration on the surface paper, and trace the original signature from the mandate given earlier. It has been difficult to use accounting and auditing professions to track down financial fraud in Nigeria mostly with the problem of unearthing ingenious fraud. Exponential membership function was used to fuzzified the derived functions, and modified into structural parameters suitable to adapt to any possible variations that may result from handwriting styles and also to reflect any other factors due to scripting of a signature. The proposed system is tested on a large database of signatures obtained from 40 subjects.
10
Guarnera, Luca, Giovanni Maria Farinella, Antonino Furnari, Angelo Salici, Claudio Ciampini, Vito Matranga, and Sebastiano Battiato. "Forensic analysis of handwritten documents with GRAPHJ." Journal of Electronic Imaging 27, no. 05 (July 27, 2018): 1. http://dx.doi.org/10.1117/1.jei.27.5.051230.
Full text
11
Guarnera, Luca, Giovanni Maria Farinella, Antonino Furnari, Angelo Salici, Claudio Ciampini, Vito Matranga, and Sebastianol Battiato. "Forensic analysis of handwritten documents with GRAPHJ (Erratum)." Journal of Electronic Imaging 27, no. 05 (October 27, 2018): 1. http://dx.doi.org/10.1117/1.jei.27.5.059801.
Full text
12
Kerniakevych-Tanasiichuk, Yuliia V., Viktor S. Sezonov, Iryna M. Nychytailo, Maryna A. Savchuk, and Iryna V. Tsareva. "Problems of forensic identification of handwriting in forensic examination." Journal of the National Academy of Legal Sciences of Ukraine 28, no. 1 (March 24, 2021): 195–204. http://dx.doi.org/10.37635/jnalsu.28(1).2021.195-204.
Full textAbstract:
The handwritten signature as a characteristic of authentication has been legally and publicly recognised for centuries and has been used in the forensic field for many decades to identify an author. Approaches to biometric user authentication developed in recent years are also based in part on handwriting characteristics, such as automatic signature verification. This article systematically identifies handwriting features published in forensics and analyses which of these properties can be adapted as biometrics to verify the user. A user verification procedure based on a set of 14 forensic characteristics is presented, which is integrated into the biometric verification procedure. The results of the verification of these forensic features are compared in detailed tests with the features of non-forensic data, and it is shown that significant improvements in false detection rates can be achieved by including forensics. For hundreds of years, handwritten signatures have been legally and socially recognised as authentication. The reason for this is the uniqueness of human handwriting. Although a forger with some practice may visually imitate another person’s text or signature, the typical traces resulting from the (studied) behaviour of a victim of forgery are difficult to copy. To check the record, the pressure force of all overlay points with a pen at the beginning or inside the word, written letters on the weight are used. In addition, the way a writer unconsciously or even consciously connects words, letters, or parts of letters to each other is a specific trait for that person. In a forensic examination, experts examine these and other features to prove or disprove the authenticity of signatures or documents. In the field of forensic science, there are many procedures offered based on physical handwriting samples to determine a writer
13
Zhizhina, M. V. "Forensic Handwriting Investigation Using Digital Photographic Copies of Documents." Theory and Practice of Forensic Science 15, no. 2 (July 28, 2020): 70–80. http://dx.doi.org/10.30764/1819-2785-2020-2-70-80.
Full textAbstract:
The study is a part of the research of the Russian Federal Centre of Forensic Science of the Ministry of Justice of the Russian Federation. It is the initial stage in the development of methodological recommendations for conducting forensic handwriting examinations of images of handwritten objects in digital photocopies of documents. The author has analyzed the current procedural legislation and judicial practice on the use of digital photocopies of documents in proof, as well as the modern expert practice of handwriting studies concerning the images of handwriting realizations presented in such copies. The analysis has shown that these forensic handwriting studies are being quite actively conducted in both judicial and extrajudicial examinations; however, they acquire the procedural status of evidence in the case. Though, the object remains outside the scope of expert methodological support and a comprehensive systematic review in the theoretical aspect. The author considers this practice unacceptable.The article reviews a complex of issues related to determining the properties and attributes of images – handwriting objects presented in photocopies of documents, their qualitative characteristics, and other factors essential for conducting forensic handwriting examinations and formulating relevant conclusions.
14
Shapiro, Vladimir, Georgi Gluhchev, and Vassil Sgurev. "Handwritten document image segmentation and analysis." Pattern Recognition Letters 14, no. 1 (January 1993): 71–78. http://dx.doi.org/10.1016/0167-8655(93)90134-y.
Full text
15
Bensefia, Ameur, Thierry Paquet, and Laurent Heutte. "Handwritten Document Analysis for Automatic Writer Recognition." ELCVIA Electronic Letters on Computer Vision and Image Analysis 5, no. 2 (October 1, 2005): 72. http://dx.doi.org/10.5565/rev/elcvia.97.
Full text
16
Chen, Zurui. "Classification of Pictures Using Different Algorithms." Highlights in Science, Engineering and Technology 9 (September 30, 2022): 99–103. http://dx.doi.org/10.54097/hset.v9i.1725.
Full textAbstract:
This study can be seen as an attempt of handwritten text recognition and analysis, because the dataset can be extended to a dataset including alphabets with or without the colour, and when the model can successfully learn the patterns, it can be applied to real-life applications such as scanning a handwritten document and save its text into a digital document.
17
Antwi, Paul. "Device Information for Forensic Analysis." Advances in Multidisciplinary and scientific Research Journal Publication 1, no. 1 (July 26, 2022): 373–78. http://dx.doi.org/10.22624/aims/crp-bk3-p59.
Full textAbstract:
This document provides an overview of information for forensic analysis related to device name, serial number and model of devices used to connect to social networking platforms. The increasing use of social networking applications on smartphones makes these devices a gold mine for forensic researchers. Potential evidence can be captured on these devices and recovered with the right tools and research methods. The increasing proliferation of network devices in homes and buildings increases the possibilities of finding digital traces relevant to an investigation, physical or virtual: cyber-attacks, identity theft, etc. connected to the network can also find useful traces on the devices themselves found or stored in an associated cloud account that can be identified by device ID, model, and serial number. Keywords: Digital Forensics; Device Information, Evidence, Storage, Cyber forensics framework. BOOK Chapter ǀ Research Nexus in IT, Law, Cyber Security & Forensics. Open Access. Distributed Free Citation: Paul Antwi (2022): Device Information for Forensic Analysis Book Chapter Series on Research Nexus in IT, Law, Cyber Security & Forensics. Pp 373-378 www.isteams.net/ITlawbookchapter2022. dx.doi.org/10.22624/AIMS/CRP-BK3-P59
18
WANG, DACHENG, and SARGUR N. SRIHARI. "ANALYSIS OF FORM IMAGES." International Journal of Pattern Recognition and Artificial Intelligence 08, no. 05 (October 1994): 1031–52. http://dx.doi.org/10.1142/s0218001494000528.
Full textAbstract:
Automatic analysis of images of forms is a problem of both practical and theoretical interest; due to its importance in office automation, and due to the conceptual challenges posed for document image analysis, respectively. We describe an approach to the extraction of text, both typed and handwritten, from scanned and digitized images of filled-out forms. In decomposing a filled-out form into three basic components of boxes, line segments and the remainder (handwritten and typed characters, words, and logos), the method does not use a priori knowledge of form structure. The input binary image is first segmented into small and large connected components. Complex boxes are decomposed into elementary regions using an approach based on key-point analysis. Handwritten and machine-printed text that touches or overlaps guide lines and boxes are separated by removing lines. Characters broken by line removal are rejoined using a character patching method. Experimental results with filled-out forms, from several different domains (insurance, banking, tax, retail and postal) are given.
19
Ruiz-Parrado, Victoria, Ruben Heradio, Ernesto Aranda-Escolastico, Ángel Sánchez, and José F. Vélez. "A bibliometric analysis of off-line handwritten document analysis literature (1990–2020)." Pattern Recognition 125 (May 2022): 108513. http://dx.doi.org/10.1016/j.patcog.2021.108513.
Full text
20
Calafato, Trevor. "Document examinations in Malta." Nowa Kodyfikacja Prawa Karnego 49 (April 18, 2019): 39–49. http://dx.doi.org/10.19195/2084-5065.49.4.
Full textAbstract:
The forensics of documents in Malta is constantly increasing in demand. This need is a reaction to the control of human trafficking and the international threat of terrorism, amongst other crimes in Malta and Europe. Besides the constant updates in the Criminal Code, document fraud analysts are increasingly in demand to ensure a more thorough and scientific analysis of forgeries of documents, stamps, seals and private writings.
21
Ahmed, Ahmed Abdullah. "Kurdish Handwritten Classification Based on Human Personality Analysis." Academic Journal of Nawroz University 10, no. 1 (March 8, 2021): 174. http://dx.doi.org/10.25007/ajnu.v10n1a862.
Full textAbstract:
This study proposes a holistic technique of classifying Kurdish handwritten text documents, involving several stages. The first stage entails the sectioning of Kurdish handwritten document images into lines, words, and characters and the second stage entails the obtaining of structural and statistical features from the sectioned parts that are often utilized in human personality analysis for the examination of feature behavior and effectiveness. This is done by combining the entire potential outcomes to determine the significant features set. The third stage entails the use of F-Measure to evaluate the extracted features performance and their combination in various relationship methods, individually and in groups. The last stage entails the actual experiment using the standard KRDOH dataset of the Kurdish handwritten text, containing 1076 volunteers’ samples of different ages, genders, and education levels in a cumulative 4304 manuscripts consisting of 4 contributed pages by each writer. Based on the results obtained from multiple runs of an individual clustering method of each distance measure, a good set of features generally deliver significantly enhanced clustering of handwritten structures.
22
Sharma, Priya, Mohinder Singh, and Om Prakash Jasuja. "Forensic examination of electronic signatures: A comparative study." Nowa Kodyfikacja Prawa Karnego 59 (November 9, 2021): 149–84. http://dx.doi.org/10.19195/2084-5065.59.11.
Full textAbstract:
The writing of names or signatures has great importance due to its use in authentication, validation, and authorization of documents. Moreover, handwritten signatures present an aura of personality and make an impression on many people. But now, with the emergence of new technologies, a variety of electronic writing media such as digital tablets and pens are being used to produce writings and signatures; and the conventional way to produce the writing using pen and paper is waning. With the changing ways of writing and signature production, the means of producing forged writing or signature are also bound to change. This has brought new challenges for handwriting examiners. In the present study, a comparative analysis of electronically captured signatures with pen-paper signatures has been performed to study the effect of changes in writing media. Signature samples were taken from the same subjects on paper and electronic pads. The similarities and differences with respect to class and line quality features between both signatures were analysed. It was observed that despite differences between the signatures produced by the same author, it is still possible to establish the authorship of signatures in the case of electronic signatures.
23
Kutskir, H. "CURRENT METHODS OF SIGNATURES’ TECHNICAL FORGING WITH THE USE OF TECHNICAL MEANS." Theory and Practice of Forensic Science and Criminalistics 21, no. 1 (December 15, 2020): 309–17. http://dx.doi.org/10.32353/khrife.1.2020_20.
Full textAbstract:
Taking into account a significant scientific and technological progress, use of modern monochrome or multicolor photocopiers in the office administration, and the increase in this regard in the number of signatures received for examination by forensic expert units, relevance for continuing to study signatures as one of the essential requisites of many types of documents and methods of their technical forgery becomes obvious.
The purpose of the article is to highlight certain issues of current methods of signatures technical forgery.
Research methods: general (formal-logical methods of cognition: analysis, synthesis, generalization, analogy), general scientific (observation, measurement, description, comparison), special (visual, microscopic, photographic).
Since the fact of handwritten signature execution possesses legal value, it often becomes the object of forgery. For this purpose, a variety of techniques is used. Criminals often resort to the so-called technical forgery of signatures on documents (performing signatures on behalf of another person using various techniques and technical means which helps to achieve the greatest similarity with the original) along with the usual graphic forgery. The essence of signatures technical forgery usually lies in mechanical copying, instead of imitating features of writing-motor skills and the signature-original. By such a signature, you can not measure the level of writing-motor skills of the performer.
Each of the methods of signature technical forgery leaves in the signature the signs inherent only to this method. Studying such methods and their features collectively will allow to diagnose the fact of handwritten or technical execution of a signature with a sufficiently high degree of probability.
24
Kallimani, Jagadish, Chandrika Prasad, D. Keerthana, Manoj J. Shet, Prasada Hegde, and S. H. Ajeya. "Performance Analysis of Open Source Optical Character Recognition." Journal of Computational and Theoretical Nanoscience 17, no. 9 (July 1, 2020): 4267–75. http://dx.doi.org/10.1166/jctn.2020.9060.
Full textAbstract:
Optical character recognition is the process of conversion of images of text into machine-encoded text electronically or mechanically. The text on image can be handwritten, typed or printed. Some of the examples of image source can be a picture of a document, a scanned document or a text which is superimposed on an image. Most optical character recognition system does not give a 100% accurate result. This project aims at analyzing the error rate of a few open source optical character recognition systems (Boxoft OCR, ABBY, Tesseract, Free Online OCR etc.) on a set of diverse documents and makes a comparative study of the same. By this, we can study which OCR is the best suited for a document.
25
Vishwanath, Neerugatti Varipally. "A COMPARATIVE ANALYSIS OF LINE AND WORD SEGMENTATION FOR HANDWRITTEN DOCUMENT IMAGE." International Journal of Advanced Research in Computer Science 9, no. 1 (February 20, 2018): 514–19. http://dx.doi.org/10.26483/ijarcs.v9i1.5428.
Full text
26
Quiniou, Solen, Mohamed Cheriet, and Eric Anquetil. "Error handling approach using characterization and correction steps for handwritten document analysis." International Journal on Document Analysis and Recognition (IJDAR) 15, no. 2 (April 7, 2011): 125–41. http://dx.doi.org/10.1007/s10032-011-0156-6.
Full text
27
Mukherjee, Jayati, Swapan K. Parui, and Utpal Roy. "An Unsupervised and Robust Line and Word Segmentation Method for Handwritten and Degraded Printed Document." ACM Transactions on Asian and Low-Resource Language Information Processing 21, no. 2 (March 31, 2022): 1–31. http://dx.doi.org/10.1145/3474118.
Full textAbstract:
Segmentation of text lines and words in an unconstrained handwritten or a machine-printed degraded document is a challenging document analysis problem due to the heterogeneity in the document structure. Often there is un-even skew between the lines and also broken words in a document. In this article, the contribution lies in segmentation of a document page image into lines and words. We have proposed an unsupervised, robust, and simple statistical method to segment a document image that is either handwritten or machine-printed (degraded or otherwise). In our proposed method, the segmentation is treated as a two-class classification problem. The classification is done by considering the distribution of gap size (between lines and between words) in a binary page image. Our method is very simple and easy to implement. Other than the binarization of the input image, no pre-processing is necessary. There is no need of high computational resources. The proposed method is unsupervised in the sense that no annotated document page images are necessary. Thus, the issue of a training database does not arise. In fact, given a document page image, the parameters that are needed for segmentation of text lines and words are learned in an unsupervised manner. We have applied our proposed method on several popular publicly available handwritten and machine-printed datasets (ISIDDI, IAM-Hist, IAM, PBOK) of different Indian and other languages containing different fonts. Several experimental results are presented to show the effectiveness and robustness of our method. We have experimented on ICDAR-2013 handwriting segmentation contest dataset and our method outperforms the winning method. In addition to this, we have suggested a quantitative measure to compute the level of degradation of a document page image.
28
Hiba, Khelil, Benyettou Abdelkader, and Afef Kacem. "The Incremental Artificial Immune System for Arabic Handwritten Recognition." Journal of Information Technology Research 12, no. 4 (October 2019): 88–106. http://dx.doi.org/10.4018/jitr.2019100105.
Full textAbstract:
The historical document is a treasure. The frequent use of these documents requires having a numeric copy. The use of these numeric documents requires developing techniques to facilitate their use. The search by content, the word spotting, and handwriting recognition became important points of research in document analysis. For this purpose, in this article is covered the recognition of the Arabic manuscript names extracted from the register of names of the Tunisian national archive. In the study, the authors have used several techniques for extracting knowledge, coding, and name recognition. The authors have also optimized the clonclas algorithm using the incremental principle from the i2gng algorithm. The results encourage continuing exploration.
29
Singh, Pawan Kumar, Supratim Das, Ram Sarkar, and Mita Nasipuri. "Feature Selection Using Harmony Search for Script Identification from Handwritten Document Images." Journal of Intelligent Systems 27, no. 3 (July 26, 2018): 465–88. http://dx.doi.org/10.1515/jisys-2016-0070.
Full textAbstract:
Abstract The feature selection process can be considered a problem of global combinatorial optimization in machine learning, which reduces the irrelevant, noisy, and non-contributing features, resulting in acceptable classification accuracy. Harmony search algorithm (HSA) is an evolutionary algorithm that is applied to various optimization problems such as scheduling, text summarization, water distribution networks, vehicle routing, etc. This paper presents a hybrid approach based on support vector machine and HSA for wrapper feature subset selection. This approach is used to select an optimized set of features from an initial set of features obtained by applying Modified log-Gabor filters on prepartitioned rectangular blocks of handwritten document images written in either of 12 official Indic scripts. The assessment justifies the need of feature selection for handwritten script identification where local and global features are computed without knowing the exact importance of features. The proposed approach is also compared with four well-known evolutionary algorithms, namely genetic algorithm, particle swarm optimization, tabu search, ant colony optimization, and two statistical feature dimensionality reduction techniques, namely greedy attribute search and principal component analysis. The acquired results show that the optimal set of features selected using HSA gives better accuracy in handwritten script recognition.
30
Dinges, Laslo, Ayoub Al-Hamadi, Moftah Elzobi, Sherif El-etriby, and Ahmed Ghoneim. "ASM Based Synthesis of Handwritten Arabic Text Pages." Scientific World Journal 2015 (2015): 1–18. http://dx.doi.org/10.1155/2015/323575.
Full textAbstract:
Document analysis tasks, as text recognition, word spotting, or segmentation, are highly dependent on comprehensive and suitable databases for training and validation. However their generation is expensive in sense of labor and time. As a matter of fact, there is a lack of such databases, which complicates research and development. This is especially true for the case of Arabic handwriting recognition, that involves different preprocessing, segmentation, and recognition methods, which have individual demands on samples and ground truth. To bypass this problem, we present an efficient system that automatically turns Arabic Unicode text into synthetic images of handwritten documents and detailed ground truth. Active Shape Models (ASMs) based on 28046 online samples were used for character synthesis and statistical properties were extracted from the IESK-arDB database to simulate baselines and word slant or skew. In the synthesis step ASM based representations are composed to words and text pages, smoothed by B-Spline interpolation and rendered considering writing speed and pen characteristics. Finally, we use the synthetic data to validate a segmentation method. An experimental comparison with the IESK-arDB database encourages to train and test document analysis related methods on synthetic samples, whenever no sufficient natural ground truthed data is available.
31
Arlazarov, V. V., E. I. Andreeva, K. B. Bulatov, D. P. Nikolaev, O. O. Petrova, B. I. Savelev, and O. A. Slavin. "Document image analysis and recognition: a survey." Computer Optics 46, no. 4 (August 2022): 567–89. http://dx.doi.org/10.18287/2412-6179-co-1020.
Full textAbstract:
This paper analyzes the problems of document image recognition and the existing solutions. Document recognition algorithms have been studied for quite a long time, but despite this, currently, the topic is relevant and research continues, as evidenced by a large number of associated publications and reviews. However, most of these works and reviews are devoted to individual recognition tasks. In this review, the entire set of methods, approaches, and algorithms necessary for document recognition is considered. A preliminary systematization allowed us to distinguish groups of methods for extracting information from documents of different types: single-page and multi-page, with text and handwritten contents, with a fixed template and flexible structure, and digitalized via different ways: scanning, photographing, video recording. Here, we consider methods of document recognition and analysis applied to a wide range of tasks: identification and verification of identity, due diligence, machine learning algorithms, questionnaires, and audits. The groups of methods necessary for the recognition of a single page image are examined: the classical computer vision algorithms, i.e., keypoints, local feature descriptors, Fast Hough Transforms, image binarization, and modern neural network models for document boundary detection, document classification, document structure analysis, i.e., text blocks and tables localization, extraction and recognition of the details, post-processing of recognition results. The review provides a description of publicly available experimental data packages for training and testing recognition algorithms. Methods for optimizing the performance of document image analysis and recognition methods are described.
32
Bulatov, K. B., P. V. Bezmaternykh, D. P. Nikolaev, and V. V. Arlazarov. "Towards a unified framework for identity documents analysis and recognition." Computer Optics 46, no. 3 (June 2022): 436–54. http://dx.doi.org/10.18287/2412-6179-co-1024.
Full textAbstract:
Identity documents recognition is far beyond classical optical character recognition problems. Automated ID document recognition systems are tasked not only with the extraction of editable and transferable data but with performing identity validation and preventing fraud, with an increasingly high cost of error. A significant amount of research is directed to the creation of ID analysis systems with a specific focus for a subset of document types, or a particular mode of image acquisition, however, one of the challenges of the modern world is an increasing demand for identity document recognition from a wide variety of image sources, such as scans, photos, or video frames, as well as in a variety of virtually uncontrolled capturing conditions. In this paper, we describe the scope and context of identity document analysis and recognition problem and its challenges; analyze the existing works on implementing ID document recognition systems; and set a task to construct a unified framework for identity document recognition, which would be applicable for different types of image sources and capturing conditions, as well as scalable enough to support large number of identity document types. The aim of the presented framework is to serve as a basis for developing new methods and algorithms for ID document recognition, as well as for far more heavy challenges of identity document forensics, fully automated personal authentication and fraud prevention.
33
AMMAR, MAAN. "PROGRESS IN VERIFICATION OF SKILLFULLY SIMULATED HANDWRITTEN SIGNATURES." International Journal of Pattern Recognition and Artificial Intelligence 05, no. 01n02 (June 1991): 337–51. http://dx.doi.org/10.1142/s0218001491000193.
Full textAbstract:
This paper compares the performances of parametric and reference pattern based features (RPBFs) in the verification of skillfully simulated handwritten signatures. The comparison shows that RPBFs significantly improve results and give about 90% correct verification using only shape features. The performance of the used shape features is independent of the signature shape, language and position in the document. The careful analysis of the experimental results of using RPBFs in verification has led to the conclusion that two-dimensional RPBFs will give much better performance.
34
Gaydamakina, D., O. Drobysheva, L. Grinenko, and O. Matsiuk. "THE EXAMINATION OF SHORT HANDWRITTEN RECORDS EXECUTED BY PERSONS OF THE ELDERLY AND SENILE AGE." Theory and Practice of Forensic Science and Criminalistics 21, no. 1 (December 15, 2020): 291–308. http://dx.doi.org/10.32353/khrife.1.2020_19.
Full textAbstract:
Nowadays, the objects of forensic handwriting analysis are often become short handwritten records of elderly people and senile. The study of such records is one of the most difficult when conducting handwriting examination. This is due to the nature of this object, which is often subjected to changes due to insufficient written practice, influence of age-related changes in the body or conditions common for the elderly people and senile, frequent execution of short handwritten records in unusual conditions, and sometimes with the help of other people, limitations in the studied graphic material. The article attempts to substantiate and systematize theoretical knowledge on the study of short handwritten records executed by elderly and senile people through analyzing the literature and forensic practice on the study of this type of objects, establishing individual patterns of handwriting, explaining the nature of diagnostic signs occurrence, determining the structure of the process for solving the mentioned tasks. Cases from practice and related problematic aspects of solving identification and diagnostic tasks are considered. The main characteristics of impaired ability (sensory, amnestic and motor aphasia) to write are given. Literature sources are analyzed, which consider the physiological mechanisms of the formation of writing skills and the features of their changes due to various conditions in elderly and senile people. Handwriting can undergo changes owing to aging of the body. Disorder of hand-eye coordination, conditions of the musculoskeletal system, nervous system, circulatory disorders, inherent for elderly and senile people, affect the stability of handwriting features. Testaments, contracts of sale and donation, bank documents are often signed by people of elderly and senile age shortly before death resulting from a serious long illness after experiencing such conditions as stroke or myocardial infarction. It is the aging of the body that is accompanied by deterioration in the state of health, impaired vision, muscle weakness, depletion of the nervous system, decreased mobility of the musculoskeletal system and impaired blood circulation. Features of writing motor skill functioning in the elderly and senile people lead to a slowdown in the tempo of movement, decrease in their amplitude and speed, decrease in the plasticity of movements. The correct ratio of such signs as proficiency and coordination of movements is of great importance. In addition, short handwritten records executed by the elderly and senile people contain a limited amount of graphic material. At the moment of executing a short recording, even under normal conditions, the performer needs a certain adaptation to a situation, which can not be performed while rare or occasional execution of a single short record. Therefore, the stability of a skill while executing short recording has an increased spread, and selective variability has low thresholds.
35
Singh, Pawan Kumar, Ram Sarkar, Ajith Abraham, and Mita Nasipuri. "A Case Study on Handwritten Indic Script Classification: Benchmarking of the Results at Page, Block, Text-line, and Word Levels." ACM Transactions on Asian and Low-Resource Language Information Processing 21, no. 2 (March 31, 2022): 1–36. http://dx.doi.org/10.1145/3476102.
Full textAbstract:
Handwritten script classification is still considered as a challenging research problem in the domain of document image analysis. Although some research attempts have been made by the researchers for solving the challenging issues, a comprehensive solution is yet to be achieved. The case study, undertaken here, analyzes the performances of various state-of-the art handwritten script classification methods for Indian scripts where features, needed for the script classification task, are extracted from the script images at four different granularity levels, i.e., page, block, text line, or word. The results of handwritten script classification at each level have been obtained and compared using eight different feature sets and six different state-of-the-art classifiers. Based on the classification results, an ideal level for performing the handwritten script classification task is suggested among these four classification levels. The results have also been improved by using two feature dimensionality reduction methods. All these experiments are done on two different handwritten Indic script databases, of which one is an in-house developed dataset and the other one is a freely available dataset. Finally, some future research directions that may be undertaken by the researchers as an application of the handwritten Indic script classification problem are also highlighted. The work presented here provides a basic foundation for the construction of a comprehensive handwritten script classification method for official Indian scripts.
36
Barratt, Natalie M. "The Case for Forensic Botany." American Biology Teacher 73, no. 7 (September 1, 2011): 414–17. http://dx.doi.org/10.1525/abt.2011.73.7.8.
Full textAbstract:
Would you rather solve a forensics puzzle or take a lab practical? An alternative to the traditional lab practical can be used to assess students' skills and knowledge in plant cell biology and anatomy. This forensics project challenges students to analyze evidence from crime scenarios. The instructor supplies the scenarios, evidence collected at the crime scene, and type specimens. The students prepare the evidence and type specimens for analysis by light and polarized light microscopy and then document and report their findings. Students enjoy this project and are able to demonstrate their skills as well as their knowledge.
37
ALAEI, ALIREZA, UMAPADA PAL, and P. NAGABHUSHAN. "DATASET AND GROUND TRUTH FOR HANDWRITTEN TEXT IN FOUR DIFFERENT SCRIPTS." International Journal of Pattern Recognition and Artificial Intelligence 26, no. 04 (June 2012): 1253001. http://dx.doi.org/10.1142/s0218001412530011.
Full textAbstract:
In document image analysis (DIA) especially in handwritten document recognition, standard databases play significant roles for evaluating performances of algorithms and comparing results obtained by different groups of researchers. The field of DIA regard to Indo-Persian documents is still at its infancy compared to Latin script-based documents; as such standard datasets are not still available in literature. This paper is an effort towards alleviating this gap. In this paper, an unconstrained handwritten dataset containing documents of Persian, Bangla, Oriya and Kannada (PBOK) is introduced. The PBOK contains 707 text-pages written in four different languages (Persian, Bangla, Oriya and Kannada) by 436 individuals. Total number of text-lines, words/subwords and characters are 12,565, 104,541 and 423,980, respectively. In most documents of PBOK dataset contain either an overlapping or a touching text-lines. The average number of text-lines in text-pages of the PBOK dataset is 18. Two types of ground truths, based on pixels information and content information, are generated for the dataset. Because of such ground truths, the PBOK dataset can be utilized in many areas of document image processing e.g. text-line segmentation, word segmentation and word recognition. To provide an insight for other researches, recent text-line segmentation results on this dataset are also reported.
38
Refaey, Mohammed A. A. "Background Ruled-Lines Detection and Removal in Full-Colored Handwritten Image Documents." International Journal of Image and Graphics 15, no. 02 (April 2015): 1540006. http://dx.doi.org/10.1142/s0219467815400069.
Full textAbstract:
Automation becomes the standard in nearly all aspects of life. Some of these aspects are text analysis, translating and retrieval. This requires machine typed format as a preprocessing step. Converting the handwritten text into machine printed counterpart requires Optical Character Recognition (OCR) system, which requires clean text as input. One of the problems facing the process of getting clean handwritten text is the ruled background lines which are intersecting and mixed with the text. In this work, we present fast algorithms for detection and removal of these ruled lines. The detection stage use only the centralized and squared part of the image document instead of wasting time if the whole image document is used, and use Hough transform for getting the ruled lines location and direction. The removal algorithm uses the color histogram segmentation for separating the text from the ruled lines. The Hue of the color is used to represent colors instead of using all color components. Then the segmented image document is morphologically enhanced and converted to binary image that is suitable for OCR. The results show the benefits of the proposed algorithms with F1-measures 91.43% and 88.52% for detection and removal respectively.
39
Rogers, Chris. "La traducción en xinka de la Proclama a los Habitantes de Ultramar de 1812." Tlalocan 25 (September 7, 2020): 215–86. http://dx.doi.org/10.19130/iifl.tlalocan.2020.0007.
Full textAbstract:
The purpose of this paper is to present a morphological and philological analysis of the zeeje manuscript, a handwritten document in Xinkan, an indigenous language family of Guatemala. This manuscript is a translation of an 1812 Spanish proclamation designed to bolster support for the Spanish Empire during the Napoleonic conflict and is one of five translations into indigenous languages of the Americas. However, among these known translations, the Xinkan document remains unanalyzed and poorly understood. This analysis suggests that the zeeje manuscript is a reflection of the complex geographic and social landscape of the Xinkan territory in the colonial era.
40
Du, Jiang, Bin Lang Chen, and Zeng Qin. "The Application of Compound Document Storage Technology in Forensic Analysis System." Applied Mechanics and Materials 610 (August 2014): 756–59. http://dx.doi.org/10.4028/www.scientific.net/amm.610.756.
Full textAbstract:
Due to the special nature of electronic data, we need to create a complete copy of the raw disks before computer forensics. There is two ways to create a copy. One is copy from Disk to disk, another is disk mirroring. The former capacity of the copy disk has fixed while image file of the latter is highly compressed already. Neither any of them can add the forensic analysis evidence; it will be handed over to the court as a whole set of evidence. This will affect the completeness and admissibility of the evidence. In this thesis, we will take the disk mirroring and storage technology into consideration by using the Compound Document storage technology, by this way we can add the evidence into the evidence copy which makes an “evidence gathered” effect. At the same time, it can highly compressed the original evidence, save the capacity and ensure the safety of the data.
41
Bal, Abhishek, and Rajib Saha. "An Improved Method for Handwritten Document Analysis Using Segmentation, Baseline Recognition and Writing Pressure Detection." Procedia Computer Science 93 (2016): 403–15. http://dx.doi.org/10.1016/j.procs.2016.07.227.
Full text
42
Firdonsyah, Arizona, and Danur Wijayanto. "Analisis Forensik Rekayasa Dokumen Digital dengan Metode NIST." INFORMAL: Informatics Journal 7, no. 2 (August 31, 2022): 121. http://dx.doi.org/10.19184/isj.v7i2.31198.
Full textAbstract:
Digital Forensics is one of the technological fields contained many sub-fields that can assist technically in collecting digital evidence to be presented in a trial in accordance with applicable law. The example of digital forensics sub-field is Image Forensics, which aims to digitally collect and look for evidentiary facts in determining the authenticity of an image or document that contained images. Various criminal and pornographic cases involving image files are still happening nowadays, therefore forensics on images as evidence is an important key to assist the court in making decisions. This research examines the authenticity of documents in the form of digital letters using National Institute of Standard and Technology (NIST) method by applying the forensic ELA (Error Level Analysis). Several previous researches have proven that the forensic ELA is able to detect modifications that have been made to images. Differences with previous researches and this research are the authors also checked the metadata of the images before performing the ELA examination using Fotoforensics. The results of the analysis shows a high level of consistency in the images and writings due to the accumulation of white dots in several places such as in headers, logos, header’s writings, text contents, footnotes, and signatures.
43
Perdanasari, Lukie, Riyanto Sigit, and Achmad Basuki. "Analysis on Handwritten Document Text to Identify Human Personality Characteristics by Using Preprocessing and Feature Extraction." EMITTER International Journal of Engineering Technology 6, no. 2 (December 29, 2018): 254–74. http://dx.doi.org/10.24003/emitter.v6i2.289.
Full textAbstract:
It is important that a company uses the right means to recruit employees with certain personal characteristics as needed. Nowadays, the techniques to respond to psychological tests on people’s characteristics have been widely understood by most job applicants, so that it is difficult to know their true personality. Graphology is a way to identify a person’s characteristics by analyzing the handwriting from the document text made by the applicant. The two types of text document of each applicant are obtained from people of different ages and different writing times. The methods of graphology used in this research for identifying the handwriting are preprocessing and feature extraction. The preprocessing method uses projection integrals, shear transformations, and template matching. While the feature extraction process applies 10 features, they are, margins, line spacing, space between words, size of writing, style, zone, direction of writing, slope of writing, width of writing and shape of the letter. The result of the experiment from five writers shows the accuracy of writing identification equals to 82%, while personality identification equals to 67,4%.
44
Xiao, Mei Hua, Jie Tan, and Li Ke Zhuang. "The Research and Implementation of an Electronic Seal System Based on CAPICOM." Advanced Materials Research 734-737 (August 2013): 3228–33. http://dx.doi.org/10.4028/www.scientific.net/amr.734-737.3228.
Full textAbstract:
In order to guarantee the secure transmission and efficient authentication of electronic official document paper, this paper puts forward the design plan of the electronic seal system with the technologies of CAPICOM, SHA-1 and USBKey. The design plan implements document protection function with major forms of electronic signature, handwritten signature and keyboard notation. Examination result and analysis proves that the system can ensure the security of the seal and guaranteed the integrality, authentication and non-repudiation of the documents. The system has broad application potential in electronic commerce, electronic government and other electronic official field.
45
Meyer, Erin, R. Shawn Underwood, and Vijayalakshmi Padmanabhan. "Patient Misidentification in Papanicolaou Tests: A Systems-Based Approach to Reducing Errors." Archives of Pathology & Laboratory Medicine 133, no. 8 (August 1, 2009): 1297–300. http://dx.doi.org/10.5858/133.8.1297.
Full textAbstract:
Abstract Context.—Patient safety is of prime concern in every laboratory. Double labeling of glass slides is performed in many cytology laboratories where handwritten patient information on the frosted portion of the glass is overlaid with paper labels (sometimes containing bar codes). The cytotechnologists match this information by turning slides over. We use SurePath liquid-based cytology for Papanicolaou tests in our laboratory and noticed patient misidentification because of slide labeling errors, a problem that has not been addressed in the literature. Objective.—To reduce slide labeling errors without increasing costs, using a systems-based approach. Design.—All errors from mislabeled slides during November 2006 were documented, and an informal root-cause analysis was performed. Slides were labeled on opposite ends and monitored for errors. Results.—Labeling on different ends of the glass slide reduced our error rate from 0.59% to 0%, made visual matching easy, and did not alter costs. Conclusions.—The practice of overlaying handwritten information with printed labels for liquid-based Papanicolaou tests should be strongly discouraged and replaced with placing patient information in separate portions of the glass slide so that crucial patient identification is not hidden and visual matching is easy.
46
Malakar, Samir, Manosij Ghosh, Ram Sarkar, and Mita Nasipuri. "Development of a Two-Stage Segmentation-Based Word Searching Method for Handwritten Document Images." Journal of Intelligent Systems 29, no. 1 (July 4, 2018): 719–35. http://dx.doi.org/10.1515/jisys-2017-0384.
Full textAbstract:
Abstract Word searching or keyword spotting is an important research problem in the domain of document image processing. The solution to the said problem for handwritten documents is more challenging than for printed ones. In this work, a two-stage word searching schema is introduced. In the first stage, all the irrelevant words with respect to a search word are filtered out from the document page image. This is carried out using a zonal feature vector, called pre-selection feature vector, along with a rule-based binary classification method. In the next step, a holistic word recognition paradigm is used to confirm a pre-selected word as search word. To accomplish this, a modified histogram of oriented gradients-based feature descriptor is combined with a topological feature vector. This method is experimented on a QUWI English database, which is freely available through the International Conference on Document Analysis and Recognition 2015 competition entitled “Writer Identification and Gender Classification.” This technique not only provides good retrieval performance in terms of recall, precision, and F-measure scores, but it also outperforms some state-of-the-art methods.
47
Vinod, H. C., and S. K. Niranjan. "Camera Captured Document De-Warping and De-Skewing." Journal of Computational and Theoretical Nanoscience 17, no. 9 (July 1, 2020): 4398–403. http://dx.doi.org/10.1166/jctn.2020.9085.
Full textAbstract:
De-warping is the elementary step in the analysis of document images which are camera based. Processing of warped image is a challenging task. Therefore, to make the document images OCR understandable de-warping has become a major task. In this paper, we have presented an effective pre-processing, de-warping and de-skewing techniques for camera captured document image processing. In pre-processing, we have divided input color document image into R, G and B-band, further convert R, G, B-band to C, M and Y-color space respectively, convert the average CMY grey scale image to binary by determining threshold value automatically. In de-warping and de-skewing, we have presented an effective techniques to remove geometrical and perspective distortion in camera captured document by combination of centroid and mid-point of bounding box height, bounding box is plotted on text blocks using connected component analysis technique. The introduced work is robust in correcting geometric distortion and skew correction for standard printed data set and also for Kannada handwritten documents.
48
Xu, Hedong, Jing Zheng, Ziwei Zhuang, and Suohai Fan. "A Solution to Reconstruct Cross-Cut Shredded Text Documents Based on Character Recognition and Genetic Algorithm." Abstract and Applied Analysis 2014 (2014): 1–11. http://dx.doi.org/10.1155/2014/829602.
Full textAbstract:
The reconstruction of destroyed paper documents is of more interest during the last years. This topic is relevant to the fields of forensics, investigative sciences, and archeology. Previous research and analysis on the reconstruction of cross-cut shredded text document (RCCSTD) are mainly based on the likelihood and the traditional heuristic algorithm. In this paper, a feature-matching algorithm based on the character recognition via establishing the database of the letters is presented, reconstructing the shredded document by row clustering, intrarow splicing, and interrow splicing. Row clustering is executed through the clustering algorithm according to the clustering vectors of the fragments. Intrarow splicing regarded as the travelling salesman problem is solved by the improved genetic algorithm. Finally, the document is reconstructed by the interrow splicing according to the line spacing and the proximity of the fragments. Computational experiments suggest that the presented algorithm is of high precision and efficiency, and that the algorithm may be useful for the different size of cross-cut shredded text document.
49
Obaidullah, Sk Md, Chayan Halder, Nibaran Das, and Kaushik Roy. "Bangla and Oriya Script Lines Identification from Handwritten Document Images in Tri-script Scenario." International Journal of Service Science, Management, Engineering, and Technology 7, no. 1 (January 2016): 43–60. http://dx.doi.org/10.4018/ijssmet.2016010103.
Full textAbstract:
In this paper, two popular eastern Indian scripts namely Bangla and Oriya are considered for Line-level script identification considering two Tri-script groups where Devnagari and Roman are kept common in each group. A 27 dimensional feature vector has been constructed using FD (Fractal Dimension) and IMT (Interpolated Morphological Transform). 600 Line-level handwritten document images of each Tri-script groups have been considered for experimentation. Promising results has been found using multiple classifiers where MLP (Multi-Layer Perceptron) Neural Network and LMT (Logistic Model Tree) perform best for BDR (Bangla-Devnagari-Roman) combinations with 97% accuracy and LMT outperforms over others for ODR (Oriya-Devnagari-Roman) combinations with 97.7% accuracy. Bi-script performance analysis has also been made where combinations BR (Bangla-Roman) and BD (Bangla-Devnagari) results with accuracy of 98% and 97.5% respectively for the first group. Whereas for the second group OD (Oriya-Devnagari) and OR (Oriya-Roman) shows an accuracy of 98.25% and 98% respectively.
50
Sharmila D , A. V. Pra.bu, N. Selvaganesh,. "AUTHORSHIP VERIFICATION USING MODIFIED PARTICLE SWARM OPTIMIZATION ALGORITHM." Psychology and Education Journal 58, no. 1 (January 15, 2021): 4262–66. http://dx.doi.org/10.17762/pae.v58i1.1492.
Full textAbstract:
Digital forensics is the study of recovery and investigation of the materials found in digital devices, mainly in computers. Forensic authorship analysis is a branch of digital forensics. It includes tasks such as authorship attribution, authorship verification, and author profiling. In Authorship verification, with a given a set of sample documents D written by an author A and an unknown document d, the task is to find whether document d is written by A or not. Authorship verification has been previously done using genetic algorithms, SVM classifiers, etc. The existing system creates an ensemble model by combining the features based on the similarity scores, and the parameter optimization was done using a grid search. The accuracy of verification using the grid search method is 62.14%. The time complexity is high as the system tries all possible combinations of the features during the ensemble model's construction. In the proposed work, Modified Particle Swarm Optimization (MPSO) is used to construct the classification model in the training phase, instead of the ensemble model. In addition to the combination of linguistic and character features, Average Sentence Length is used to improve the verification task accuracy. The accuracy of verification has been improved to 63.38%.