Dissertations / Theses on the topic 'Amélioration de la qualité visuelle des images'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 19 dissertations / theses for your research on the topic 'Amélioration de la qualité visuelle des images.'
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 dissertations / theses on a wide variety of disciplines and organise your bibliography correctly.
Ding, Yi. "Amélioration de la qualité visuelle et de la robustesse aux post-traitements des images comprimées par une approche de type "problème inverse"." Lyon, INSA, 1996. http://www.theses.fr/1996ISAL0086.
Full textLow bit-rate can only be attained by lossy compression techniques. Most of the lossy compression schemes proceed by blocks at the transformation or at the quantization stage. The usual decompression algorithm is a symmetric inverse processing of the compression scheme. This generates blocking artifacts and ringing noise. Furthermore, decompressed image can never support post-processing such as edge detection. In this work, we propose a decompression scheme based on the theory of inverse problems. The decompression restores the compressed image with some constraints based on information about both the original image and on the compression procedure: the image smoothness and the upper bound of the quantization error, respectively. We consider an extension of the regularized mean square approach for ill-posed problems proposed by Miller. This idea is first carried out for the JPEG algorithm. We proposed two schemes. In the first one the dequantization array is calculated in order to minimize the reconstruction error subjected to a mean regularity constraint on the whole image blacks. This scheme is in full compliance with the JPEG standard. In the second approach the original image is pre-filtered by an unsharp masking filter in order to enhance the image details before compression and post-filtered by a low-pass inverse filter after decompression to remove the blocks. The inverse filter is designed for an optimal restoration subjected to both a constraint on the image roughness and on the decompression error. This second technique is more efficient than the first one against blocking artifacts. It is also in full compliance with the JPEG standard but requires two additional processing components. The robustness of the decompressed image to edge detection was assessed for both proposed schemes. We also proposed an algorithm which adapts the block size to the correlation length of the image in JPEG and which optimizes the coefficients of the quantization array. This approach is very efficient for medical images. The regularized restoration method is also applied to the subband coding techniques that use vector quantization of the subband images. Two approaches are considered. In the first one the image is restored at each resolution level and in the second one a global restoration is applied. Experimental results prove that both methods significantly reduce blocking effects and preserve the edges of compressed images. In order to complete the research, we compare the performance of our proposal to a non-linear approach which is adapted to the attenuation of ringing noise
Bouraoui, Atidel. "Image quality assessment using an artificial neural network approach." Paris 13, 2012. http://scbd-sto.univ-paris13.fr/intranet/edgalilee_th_2012_lahoulou_ep_bouraoui.pdf.
Full textImage quality assessment presents a substantial interest for image services that target human observers. Indeed, Image quality can be measured in two different ways. The first, called “subjective quality assessment”, is the obvious approach given the subjective nature of the visual data quality. The second one is called “objective quality assessment” that automatically allow to produce values that score image quality. There exists a large array of objective image quality assessment measures for which a taxonomic scheme has been proposed in the beginning of this manuscript. In fact, the first objective of this thesis is to provide a complete and thorough statistical predictive performance assessment of a variety of full‐reference objective quality measures over number of subjectively rated image quality databases. The second is to define the image attributes that are the most relevant to its quality evaluation. Two feature selection methods have been used including the structural risk minimization and the neural network based approaches. This allowed us to develop two new objective reduced‐reference image quality metrics where the image quality assessment requires the use of only a few features of the reference and the test images. The third objective of this research work is to exploit the supervised machine learning techniques, especially the multilayer perceptron based model, for automatic image quality appreciation. The system learns from the subjective quality scores and builds a model capable to further provide an objective measure that continues to match with the human opinion to any other image. The main target was to optimize the predictive performance of the developed measures according to correlation, monotonicity and accuracy. The default cost function based on error was employed for the first developed measure (that we called ECF) and a customized cost function based on correlation was proposed to design the second metric (that we called CCF). The comparative investigation to eighteen other full‐reference image quality algorithms over three image quality databases shows that both ECF and CCF take into consideration the nonlinearities of the human visual system. The ECF is more accurate than the majority of the metrics under study, while the CCF outperforms all its counterparts in terms of correlation and hence monotonicity
Cherifi, Daikha. "Amélioration et évaluation de la qualité des images." Thesis, Paris 13, 2014. http://www.theses.fr/2014PA132053.
Full textThe aim of this thesis is to propose new methods for image enhancement based on oriented and multi-scale transforms using some perceptual criteria. The first part of the thesis is devoted to the development of a simple and efficient contrast enhancement method inspired from the human visual system. This method is evaluated on a set of natural color and monochrome images. The obtained results are evaluated subjectively and by using objective measures based on energy spectrum analysis and perceptual criteria. The enhancement technique is also extended to some medical images, such as mammography and endoscopy images. A special contrast enhancement method adapted to mammography is then proposed. It is based on a segmentation process using a priori information on the mammography images. The last part of the thesis is devoted to image enhancement evaluation. A critical literature survey of image enhancement evaluation methods is provided. The evaluation method proposed in this thesis is based on the radial and angular analysis of the Fourier powerspectrum. Another perceptual approach is proposed to evaluate the output. This method is based on the analysis of the visibility map computed by using a pyramidal contrast. The evaluation is performed on some samples taken from two databases. Both subjective and objective evaluations demonstrate the efficiency of the proposed image enhancement methods
Le, Callet Patrick. "Critères objectifs avec référence de qualité visuelle des images couleur." Nantes, 2001. http://www.theses.fr/2001NANT2084.
Full textObjective metrics for image quality assessment are very useful in order to optimise performance of image processing systems for acquiring, viewing, archiving or transmitting visual data. An objective metric should provide quality measures in strong correspondence with human judgement. So, it is necessary to incorporate models of most of human visual system properties in the design of such metric. The main global of this thesis is to establish and apply these models in order to assess colour image quality. This assessment is done with the full reference image but without any a priori knowledge on the distortion nature introduced in the distorted image
Nguyen, Tien Nam. "Segmentation, Recognition and Indexing of Cham characters in Cham documents." Electronic Thesis or Diss., La Rochelle, 2023. http://www.theses.fr/2023LAROS016.
Full textSince the demise of Champa kingdoms during the 19th century, the Cham language that originated and developed from the 2nd century, is no longer really used among the descendants of the Champa. The lack of transmission of knowledge and documents of the Cham culture makes the study of this language difficult for epigraphists and historians. Therefore, the ANR CHAMDOC project aims to preserve and provide tools for studying the Cham language. In this thesis, we focused on the analysis of two types of Cham documents namely: inscriptions, which were engraved on stone steles, from 6th to 15th century; manuscripts dating from the 18th century. Some work on the digitization of inscriptions has started but no study has really been carried out. The collection of manuscripts, for its part, has never been exploited. These two collections offer many challenges for the scientific community. During this work, we propose a complete pipeline for the automatic processing of these documents. This is based on different DIA techniques. The challenges encountered come from the characteristics of the documents themselves, but also from the linguistic specificities of Cham. An analysis of these characteristics has been carried out in order to propose solutions adapted to inscriptions and manuscripts
Ninassi, Alexandre. "De la perception locale des distorsions de codage à l'appréciation globale de la qualité visuelle des images et vidéos : apport de l'attention visuelle dans le jugement de qualité." Nantes, 2009. http://www.theses.fr/2009NANT2012.
Full textThis study deals with the local evaluation of perceptual distortions, the overall visual quality assessment and the influence of visual attention in viusal quality assessment. To locally evaluate distortions in images, we have simplified an existing human visual system model using wavelet transform and we have proposed an improved visual masking model that takes into account both semi-local masking and contrast masking. From these models, we have designed and tested several image quality metrics. Regarding videos, we have developed a new method to locally evaluate the spatio-temporal distortions. This method is based on a short-term temporal pooling of spatial distortions which simulates the evaluation of distortions through some selection mechanisms of visual attention. A video quality metric based on this method has been designed and validated. It is based on a longterm temporal pooling incorporating perceptual saturation and asymmetric behavior. In order to study visual attention in subjective and objective visual quality assessment, eye-tracking experiments on images and videos have been conducted both in free task and quality task. From collected data we have studied the visual attention deployed in the different configurations. The results have confirmed, among others, the influence of the quality task on deployment of visual attention. The impact of visual attention in the construction of the quality judgment has also been studied using the real saliency information. Results show that, both with images and videos, a simple linear weighting of distortions by the visual attention does not clearly improve performances of objective quality metrics
El, Khalifa Moulay Ahmed. "Amélioration de la qualité des images en tomographie microonde : contribution à une imagerie quantitative." Paris 11, 1989. http://www.theses.fr/1989PA112203.
Full textBelgued, Youssef. "Amélioration de la qualité géométrique des images spatiales radar : méthodes de localisation et restitution du relief par radargrammétrie." Toulouse, INPT, 2000. http://www.theses.fr/2000INPT019H.
Full textAtif, Jamal. "Recalage non-rigide multimodal des images radiologiques par information mutuelle quadratique normalisée." Paris 11, 2004. http://www.theses.fr/2004PA112337.
Full textExposito, Jonathan. "Amélioration de la qualité des images obtenues par optique adaptative et application à l'étude des noyaux actifs de galaxie." Phd thesis, Université Paris-Diderot - Paris VII, 2013. http://tel.archives-ouvertes.fr/tel-01005770.
Full textExposito, Cano Jonathan. "Amélioration de la qualité des images obtenues par optique adaptative et application à l'étude des noyaux actifs de galaxie." Paris 7, 2013. http://www.theses.fr/2013PA077211.
Full textTo get the best quality of the images from an optical system in terms of contrast , it is used to deconvolve the image from the point spread function (PSF). For this method to be effective, it is necessary that the optical transfer function of the system telescope + residual atmosphere is well characterized. Myopic deconvolution is sometimes used to overcome this problem. This method is used to estimate both the object and the PSF from an average PSF obtained during the observation of the standard source, a power spectral density of the PSF and of the image. However, like any inversion algorithm, the myopic deconvolution needs initial conditions close enough to the final solution to converge to the correct solution. The results can be random if the uncertainty on PSF is too large. The reconstruction of FEP is then a solution. The analysis at each time adaptive optics loop state of turbulence and analyzer measurements and controls are recorded. 11 is then possible to use a method to reconstruct the optical transfer function (OTF or PSF) of the residual atmosphere during the observation using data from real-time telemetry provided by the AO loop. The reconstruction is done in post-processing and does not require extra time, which maximizes the time available for scientific source and therefore has a certain interest in the observations. I developed during this thesis a new tool for the reconstruction of PSF based on a maximum likelihood approach. At the same time, I studied the regions near the active nucleus of the galaxy NGC 1068 using NACO, an imaging spectrometer equipped with adaptive optics on the VLT
Bertolino, Pascal. "Algorithmes pour la segmentation et l'amélioration de la qualité des images et des vidéos." Habilitation à diriger des recherches, Université de Grenoble, 2012. http://tel.archives-ouvertes.fr/tel-00798440.
Full textNinassi, Alexandre. "DE LA PERCEPTION LOCALE DES DISTORSIONS DE CODAGE A L'APPRECIATION GLOBALE DE LA QUALITE VISUELLE DES IMAGES ET VIDEOS. APPORT DE L'ATTENTION VISUELLE DANS LE JUGEMENT DE QUALITE." Phd thesis, Université de Nantes, 2009. http://tel.archives-ouvertes.fr/tel-00426909.
Full textNauge, Michaël. "Exploitation des statistiques structurelles d'une image pour la prédiction de la saillance visuelle et de la qualité perçue." Thesis, Poitiers, 2012. http://www.theses.fr/2012POIT2300/document.
Full textIn the field of computer vision, the use of interest points (IP) is very frequent for objects tracking and recognition. Several studies have demonstrated the usefulness of these techniques, combining robustness and complexity that can be compatible with the real time. This thesis proposes to explore and exploit these image statistical descriptors under a different angle. Thus, we conducted a study on the relationship between IP and human visual saliency. In this study, we developed a method for predicting saliency maps relying on the efficiency of the descriptors. We also used the descriptive power of the PI to develop new metrics for image quality. With encouraging results in terms of prediction of perceived quality and the reduced amount of used information, we were able to integrate our metric "QIP" in an image transmission framework over a MIMO wireless network. The inclusion of this metric can improve the quality of experience by ensuring the best visual quality despite the errors introduced by the wireless transmission. We have extended this study by deeply analyzing structural statistics of the image and migration attributes to provide a generic model for predicting impairments. Finally, we conducted various psychovisual experiments to validate the proposed approaches or to contribute to JPEG standard committee. This led to develop a web application dedicated to the benchmark of image quality metrics
Sendjasni, Abderrezzaq. "Objective and subjective quality assessment of 360-degree images." Electronic Thesis or Diss., Poitiers, 2023. http://www.theses.fr/2023POIT2251.
Full text360-degree images, a.k.a. omnidirectional images, are in the center of immersive media. With the increase in demands of the latter, mainly thanks to the offered interactive and immersive experience, it is paramount to provide good quality of experience (QoE). This QoE is significantly impacted by the quality of the content. Like any type of visual signal, 360-degree images go through a sequence of processes including encoding, transmission, decoding, and rendering. Each of these processes has the potential to introduce distortions to the content. To improve the QoE, image quality assessment (IQA) is one of the strategies to be followed. This thesis addresses the quality evaluation of 360-degree images from the objective and subjective perspectives. By focusing on the influence of Head Mounted Displays (HMDs) on the perceived quality of 360-degree images, a psycho-visual study is designed and carried out using four different devices. For this purpose, a 360-degree image datasets is created and a panel of observers is involved. The impact of HMDs on the quality ratings is identified and highlighted as an important factor to consider when con- ducting subjective experiments for 360-degree images. From the objective perspective, we first comprehensively benchmarked several convolutional neural network (CNN) models under various configurations. Then, the processing chain of CNN-based 360-IQA is improved at different scales, from input sampling and representation to aggregating quality scores. Based on the observations of the above studies as well as the benchmark, two 360-IQA models based on CNNs are proposed to accurately predict the quality of 360-degree images. The obtained observations and conclusions from the various contributions shall bring insights for assessing the quality of 360-degree images
360-graders bilder, også kjent som rundstrålende bilder, er i sentrum av oppslukende medier. Med økningen i forventninger til sistnevnte, hovedsakelig takket være den aktiverte interaktive og oppslukende opplevelse, er det avgjørende å gi god kvaliteten på opplevelsen (QoE).Denne QoE er betydelig påvirket av kvaliteten på innholdet. Som alle typer visuelle signaler går 360-graders bilder gjennom en sekvens av prosesser, inkludert koding, overføring, dekoding og gjengivelse. Hver av disse prosessene har potensial til å introdusere forvrengninger til innholdet.For å forbedre QoE er vurdering av bildekvalitet (IQA) en av strategiene å følge. Denne oppgaven tar for seg kvalitetsevaluering av 360-graders bilder fra objektive og subjektive perspektiver. Ved å fokusere på påvirkningen av Head Mounted Displays (HMD-er) på den oppfattede kvaliteten til 360-graders bilder, er en psyko-visuell studie designet og utført ved hjelp av fire forskjellige enheter. For dette formålet opprettes et 360-graders bildedatasett og et panel av observatører er involvert. Virkningen av HMD-er på valitetsvurderingene identifiseres og fremheves som en viktig faktor når du utfører subjektive eksperimenter for 360-graders bilder.Fra det objektive perspektivet benchmarket vi først flere konvolusjonelle nevrale nettverk (CNN) under forskjellige konfigurasjoner. Deretter forbedres prosesseringskjeden til CNN-baserte 360-IQA i forskjellige skalaer, fra input-sampling og representasjon til aggregering av kvalitetspoeng. Basert på observasjonene av de ovenfornevnte studiene så vel som benchmark, foreslås to 360-IQA-modeller basert på CNN-er for å nøyaktig forutsi kvaliteten på 360-graders bilder.De innhentede observasjonene og konklusjonene fra de ulike bidragene skal gi innsikt for å vurdere kvaliteten på 360-graders bilder
Roggeman, Hélène. "Amélioration de performance de la navigation basée vision pour la robotique autonome : une approche par couplage vision/commande." Thesis, Université Paris-Saclay (ComUE), 2017. http://www.theses.fr/2017SACLS497/document.
Full textThe aim of this thesis is to perform various autonomous navigation missions in indoor and cluttered environments with mobile robots. The environment perception is ensured by an embedded stereo-rig and a visual odometry algorithm which computes the localization of the robot. However, when the quality of the scene perceived by the cameras is poor, the visual localization cannot be computed with a high precision. Two solutions are proposed to tackle this problem. The first one is the data fusion from multiple sensors to perform a robust computation of the localization. The second solution is the prediction of the future scene quality in order to adapt the robot's trajectory to ensure that the localization remains accurate. In the two cases, the control loop is based on model predictive control, which offers the possibility to consider simultaneously the different objectives of the mission : waypoint navigation, exploration, obstacle avoidance. A second issue studied is waypoint navigation with avoidance of mobile obstacles using only the visual information. The mobile obstacles are detected in the images and their position and velocity are estimated in order to predict their future trajectory and consider it in the control strategy. Numerous experiments were carried out and demonstrated the effectiveness of the proposed solutions
Kang, Chen. "Image Aesthetic Quality Assessment Based on Deep Neural Networks." Thesis, université Paris-Saclay, 2020. http://www.theses.fr/2020UPASG004.
Full textWith the development of capture devices and the Internet, people access to an increasing amount of images. Assessing visual aesthetics has important applications in several domains, from image retrieval and recommendation to enhancement. Image aesthetic quality assessment aims at determining how beautiful an image looks to human observers. Many problems in this field are not studied well, including the subjectivity of aesthetic quality assessment, explanation of aesthetics and the human-annotated data collection. Conventional image aesthetic quality prediction aims at predicting the average score or aesthetic class of a picture. However, the aesthetic prediction is intrinsically subjective, and images with similar mean aesthetic scores/class might display very different levels of consensus by human raters. Recent work has dealt with aesthetic subjectivity by predicting the distribution of human scores, but predicting the distribution is not directly interpretable in terms of subjectivity, and might be sub-optimal compared to directly estimating subjectivity descriptors computed from ground-truth scores. Furthermore, labels in existing datasets are often noisy, incomplete or they do not allow more sophisticated tasks such as understanding why an image looks beautiful or not to a human observer. In this thesis, we first propose several measures of subjectivity, ranging from simple statistical measures such as the standard deviation of the scores, to newly proposed descriptors inspired by information theory. We evaluate the prediction performance of these measures when they are computed from predicted score distributions and when they are directly learned from ground-truth data. We find that the latter strategy provides in general better results. We also use the subjectivity to improve predicting aesthetic scores, showing that information theory inspired subjectivity measures perform better than statistical measures. Then, we propose an Explainable Visual Aesthetics (EVA) dataset, which contains 4070 images with at least 30 votes per image. EVA has been crowd-sourced using a more disciplined approach inspired by quality assessment best practices. It also offers additional features, such as the degree of difficulty in assessing the aesthetic score, rating for 4 complementary aesthetic attributes, as well as the relative importance of each attribute to form aesthetic opinions. The publicly available dataset is expected to contribute to future research on understanding and predicting visual quality aesthetics. Additionally, we studied the explainability of image aesthetic quality assessment. A statistical analysis on EVA demonstrates that the collected attributes and relative importance can be linearly combined to explain effectively the overall aesthetic mean opinion scores. We found subjectivity has a limited correlation to average personal difficulty in aesthetic assessment, and the subject's region, photographic level and age affect the user's aesthetic assessment significantly
Ben, Younes Ridha. "Contribution à l'amélioration qualitative et quantitative des images de médecine nucléaire en tomographie d'émission à simple photon." Besançon, 1989. http://www.theses.fr/1989BESA2008.
Full textAdam, Pierre. "Améliorations d'artefacts sur panneaux LCD." Phd thesis, 2008. http://tel.archives-ouvertes.fr/tel-00396368.
Full text