Dissertations / Theses on the topic 'Object invariants'
To see the other types of publications on this topic, follow the link: Object invariants.
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 dissertations / theses for your research on the topic 'Object invariants.'
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.
1
Self, T. Benjamin (Thomas Benjamin) 1977. "Expression and localization of object invariants." Thesis, Massachusetts Institute of Technology, 2000. http://hdl.handle.net/1721.1/86498.
Full textAbstract:
Thesis (S.B. and M.Eng.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2000.Includes bibliographical references (leaf 23).
by T. Benjamin Self.
S.B.and M.Eng.
2
Vinther, Sven. "Active 3D object recognition using geometric invariants." Thesis, University of Cambridge, 1994. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.362974.
Full text
3
Beis, Jeffrey S. "Indexing without invariants in model-based object recognition." Thesis, National Library of Canada = Bibliothèque nationale du Canada, 1997. http://www.collectionscanada.ca/obj/s4/f2/dsk3/ftp04/nq25014.pdf.
Full text
4
Zhu, Yonggen. "Feature extraction and 2D/3D object recognition using geometric invariants." Thesis, King's College London (University of London), 1996. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.362731.
Full text
5
Soysal, Medeni. "Joint Utilization Of Local Appearance Descriptors And Semi-local Geometry For Multi-view Object Recognition." Phd thesis, METU, 2012. http://etd.lib.metu.edu.tr/upload/12614313/index.pdf.
Full textAbstract:
Novel methods of object recognition that form a bridge between today&rsquos local feature frameworks and previous decade&rsquo
s strong but deserted geometric invariance field are presented in this dissertation. The rationale behind this effort is to complement the lowered discriminative capacity of local features, by the invariant geometric descriptions. Similar to our predecessors, we first start with constrained cases and then extend the applicability of our methods to more general scenarios. Local features approach, on which our methods are established, is reviewed in three parts
namely, detectors, descriptors and the methods of object recognition that employ them. Next, a novel planar object recognition framework that lifts the requirement for exact appearance-based local feature matching is presented. This method enables matching of groups of features by utilizing both appearance information and group geometric descriptions. An under investigated area, scene logo recognition, is selected for real life application of this method. Finally, we present a novel method for three-dimensional (3D) object recognition, which utilizes well-known local features in a more efficient way without any reliance on partial or global planarity. Geometrically consistent local features, which form the crucial basis for object recognition, are identified using affine 3D geometric invariants. The utilization of 3D geometric invariants replaces the classical 2D affine transform estimation /verification step, and provides the ability to directly verify 3D geometric consistency. The accuracy and robustness of the proposed method in highly cluttered scenes with no prior segmentation or post 3D reconstruction requirements, are presented during the experiments.
6
Wilhelm, Hedwig. "A Neural Network Model of Invariant Object Identification." Doctoral thesis, Universitätsbibliothek Leipzig, 2010. http://nbn-resolving.de/urn:nbn:de:bsz:15-qucosa-62050.
Full textAbstract:
Invariant object recognition is maybe the most basic and fundamental property of our visual system. It is the basis of many other cognitive tasks, like motor actions and social interactions. Hence, the theoretical understanding and modeling of invariant object recognition is one of the central problems in computational neuroscience.
Indeed, object recognition consists of two different tasks: classification and identification.
The focus of this thesis is on object identification under the basic geometrical
transformations shift, scaling, and rotation. The visual system can
perform shift, size, and rotation invariant object identification.
This thesis consists of two parts. In the first part, we present and investigate the VisNet model proposed by Rolls. The generalization problems of VisNet triggered our development of a new neural network model for invariant object identification. Starting point for an improved generalization behavior is the search for an operation that extracts images features that are invariant under shifts, rotations, and scalings. Extracting invariant features guarantees that an object seen once in a specific pose can be identified in any pose.
We present and investigate our model in the second part of this thesis.
7
Srestasathiern, Panu. "View Invariant Planar-Object Recognition." The Ohio State University, 2008. http://rave.ohiolink.edu/etdc/view?acc_num=osu1420564069.
Full text
8
Tonge, Ashwini Kishor. "Object Recognition Using Scale-Invariant Chordiogram." Thesis, University of North Texas, 2017. https://digital.library.unt.edu/ark:/67531/metadc984116/.
Full textAbstract:
This thesis describes an approach for object recognition using the chordiogram shape-based descriptor. Global shape representations are highly susceptible to clutter generated due to the background or other irrelevant objects in real-world images. To overcome the problem, we aim to extract precise object shape using superpixel segmentation, perceptual grouping, and connected components. The employed shape descriptor chordiogram is based on geometric relationships of chords generated from the pairs of boundary points of an object. The chordiogram descriptor applies holistic properties of the shape and also proven suitable for object detection and digit recognition mechanisms. Additionally, it is translation invariant and robust to shape deformations. In spite of such excellent properties, chordiogram is not scale-invariant. To this end, we propose scale invariant chordiogram descriptors and intend to achieve a similar performance before and after applying scale invariance. Our experiments show that we achieve similar performance with and without scale invariance for silhouettes and real world object images. We also show experiments at different scales to confirm that we obtain scale invariance for chordiogram.
9
Dahmen, Jörg. "Invariant image object recognition using Gaussian mixture densities." [S.l.] : [s.n.], 2001. http://deposit.ddb.de/cgi-bin/dokserv?idn=964586940.
Full text
10
Booth, Michael C. A. "Temporal lobe mechanisms for view-invariant object recognition." Thesis, University of Oxford, 1998. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.299094.
Full text
11
Hsu, Tao-i. "Affine invariant object recognition by voting match techniques." Thesis, Monterey, California. Naval Postgraduate School, 1988. http://hdl.handle.net/10945/22865.
Full textAbstract:
Approved for public release; distribution is unlimitedThis thesis begins with a general survey of different model based systems for object recognition. The advantage and disadvantage of those systems are discussed. A system is then selected for study because of its effective Affine invariant matching [Ref. 1] characteristic. This system involves two separate phases, the modeling and the recognition. One is done off-line and the other is done on-line. A Hashing technique is implemented to achieve fast accessing and voting. Different test data sets are used in experiments to illustrate the recognition capabilities of this system. This demonstrates the capabilities of partial match, recognizing objects under similarity transformation applied to the models, and the results of noise perturbation. The testing results are discussed, and related experiences and recommendations are presented.
http://archive.org/details/affineinvarianto00hsut
Captain, Taiwan Republic of China Army
12
Kao, Chang-Lung. "Affine invariant matching of noisy objects." Thesis, Monterey, California. Naval Postgraduate School, 1989. http://hdl.handle.net/10945/26852.
Full text
13
Reiss, T. H. "Recognizing objects using invariant image features." Thesis, University of Cambridge, 1992. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.260553.
Full text
14
Allan, Moray. "Sprite learning and object category recognition using invariant features." Thesis, University of Edinburgh, 2007. http://hdl.handle.net/1842/2430.
Full textAbstract:
This thesis explores the use of invariant features for learning sprites from image sequences, and for recognising object categories in images. A popular framework for the interpretation of image sequences is the layers or sprite model of e.g. Wang and Adelson (1994), Irani et al. (1994). Jojic and Frey (2001) provide a generative probabilistic model framework for this task, but their algorithm is slow as it needs to search over discretised transformations (e.g. translations, or affines) for each layer. We show that by using invariant features (e.g. Lowe’s SIFT features) and clustering their motions we can reduce or eliminate the search and thus learn the sprites much faster. The algorithm is demonstrated on example image sequences. We introduce the Generative Template of Features (GTF), a parts-based model for visual object category detection. The GTF consists of a number of parts, and for each part there is a corresponding spatial location distribution and a distribution over ‘visual words’ (clusters of invariant features). We evaluate the performance of the GTF model for object localisation as compared to other techniques, and show that such a relatively simple model can give state-of- the-art performance. We also discuss the connection of the GTF to Hough-transform-like methods for object localisation.
15
Bone, Peter. "Fully invariant object recognition and tracking from cluttered scenes." Thesis, University of Sussex, 2007. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.444109.
Full text
16
Sim, Hak Chuah. "Invariant object matching with a modified dynamic link network." Thesis, University of Southampton, 1999. https://eprints.soton.ac.uk/256269/.
Full text
17
Robinson, Leigh. "Invariant object recognition : biologically plausible and machine learning approaches." Thesis, University of Warwick, 2015. http://wrap.warwick.ac.uk/83167/.
Full textAbstract:
Understanding the processes that facilitate object recognition is a task that draws on a wide range of fields, integrating knowledge from neuroscience, psychology, computer science and mathematics. The substantial work done in these fields has lead to two major outcomes: Firstly, a rich interplay between computational models and biological experiments that seek to explain the biological processes that underpin object recognition. Secondly, engineered vision systems that on many tasks are approaching the performance of humans. This work first highlights the importance of ensuring models which are aiming for biological relevance actually produce biologically plausible representations that are consistent with what has been measured within the primate visual cortex. To accomplish this two leading biologically plausible models, HMAX and VisNet are compared on a set of visual processing tasks. The work then changes approach, focusing on models that do not explicitly seek to model any biological process, but rather solve a particular vision task with the goal being increased performance. This section explores the recently discovered problem convolution networks being susceptible to adversarial exemplars. An extension of previous work is shown that allows state-of-the-art networks to be fooled to classify any image as any label while leaving that original image visually unchanged. Secondly an efficient implementation of applying dropout in a batchwise fashion is introduced that approximately halves the computational cost, allowing models twice as large to be trained. Finally an extension to Deep Belief Networks is proposed that constrains the connectivity of the a given layer to that of a topologically local region of the previous one.
18
Romero, i. Sànchez David. "Numerical computation of invariant objects with wavelets." Doctoral thesis, Universitat Autònoma de Barcelona, 2015. http://hdl.handle.net/10803/395169.
Full text
19
Zhang, Hui. "The investigation of correlator systems utilizing object and frequency space filters." Thesis, Abertay University, 2000. https://rke.abertay.ac.uk/en/studentTheses/5afbbda6-0d84-471b-bfcd-f3717c905233.
Full textAbstract:
The aim of this research is to develop real-time object recognition systems which are robust and have good discrimination. An important aspect of this work is the development of a rotationally invariant optical correlator. Optical correlation systems are investigated for the purpose of high speed, high discriminant and distortion invariant pattern recognition. A photorefractive joint transform correlator (JTC) using Bismuth Silicon Oxide (BSO) as a non-linear recording medium and a liquid crystal television as a spatial light modulator is implemented. The underlying physics is considered, some specific techniques to improve the operation are proposed. The properties of photorefractive BSO are investigated for use as the dynamic holographic recording medium in information processing systems. The moving grating technique is used for edge-enhanced image reconstruction and for making the correlation peak sharper. The object and frequency space filtering methods are presented to improve the correlation performance, the discrimination, and to realise distortion invariant pattern recognition. Circular harmonic matched filters and phase-only filters with different expansion orders are involved in the photorefractive JTC for real-time rotationally invariant pattern recognition. These filters can also be used to track an object with different orientations. The coherent triple joint transform correlator employs a third beam to modify the Fourier spectrum and hence improves the correlation performance. In the incoherent triple JTC, the wavelet transform is used in the Fourier domain to achieve a high signalto-noise ratio, noise robustness as well as discrimination. Several wavelet functions are also used, after processing, in the conventional JTC for high-speed image feature extraction. The wavelet transform functions can also be used in the JTC with circular harmonic filters to improve the output quality of rotation invariant pattern recognition.
20
Weaver, Jon. "Naming familiar objects promotes viewpoint-invariance." Thesis, Lancaster University, 2002. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.404238.
Full text
21
Graf, Thorsten. "Flexible object recognition based on invariant theory and agent technology." [S.l. : s.n.], 2000. http://deposit.ddb.de/cgi-bin/dokserv?idn=96086170X.
Full text
22
Woo, Myung Chul. "Biologically-inspired translation, scale, and rotation invariant object recognition models /." Online version of thesis, 2007. http://hdl.handle.net/1850/3933.
Full text
23
Perry, Gavin. "Computational models of invariant object representation in the inferotemporal cortex." Thesis, University of Oxford, 2005. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.425893.
Full text
24
Banarse, D. S. "A generic neural network architecture for deformation invariant object recognition." Thesis, Bangor University, 1997. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.362146.
Full text
25
Li, Nuo Ph D. Massachusetts Institute of Technology. "Unsupervised learning of invariant object representation in primate visual cortex." Thesis, Massachusetts Institute of Technology, 2011. http://hdl.handle.net/1721.1/65288.
Full textAbstract:
Thesis (Ph. D.)--Massachusetts Institute of Technology, Dept. of Brain and Cognitive Sciences, 2011.Cataloged from PDF version of thesis.
Includes bibliographical references.
Visual object recognition (categorization and identification) is one of the most fundamental cognitive functions for our survival. Our visual system has the remarkable ability to convey to us visual object and category information in a manner that is largely tolerant ("invariant") to the exact position, size, pose of the object, illumination, and clutter. The ventral visual stream in non-human primate has solved this problem. At the highest stage of the visual hierarchy, the inferior temporal cortex (IT), neurons have selectivity for objects and maintain that selectivity across variations in the images. A reasonably sized population of these tolerant neurons can support object recognition. However, we do not yet understand how IT neurons construct this neuronal tolerance. The aim of this thesis is to tackle this question and to examine the hypothesis that the ventral visual stream may leverage experience to build its neuronal tolerance. One potentially powerful idea is that time can act as an implicit teacher, in that each object's identity tends to remain temporally stable, thus different retinal images of the same object are temporally contiguous. In theory, the ventral stream could take advantage of this natural tendency and learn to associate together the neuronal representations of temporally contiguous retinal images to yield tolerant object selectivity in IT cortex. In this thesis, I report neuronal support for this hypothesis in IT of non-human primates. First, targeted alteration of temporally contiguous experience with object images at different retinal positions rapidly reshaped IT neurons' position tolerance. Second, similar temporal contiguity manipulation of experience with object images at different sizes similarly reshaped IT size tolerance. These instances of experience-induced effect were similar in magnitude, grew gradually stronger with increasing visual experience, and the size of the effect was large. Taken together, these studies show that unsupervised, temporally contiguous experience can reshape and build at least two types of IT tolerance, and that they can do so under a wide range of spatiotemporal regimes encountered during natural visual exploration. These results suggest that the ventral visual stream uses temporal contiguity visual experience with a general unsupervised tolerance learning (UTL) mechanism to build its invariant object representation.
by Nuo Li.
Ph.D.
26
Mathew, Alex. "Rotation Invariant Histogram Features for Object Detection and Tracking in Aerial Imagery." University of Dayton / OhioLINK, 2014. http://rave.ohiolink.edu/etdc/view?acc_num=dayton1397662849.
Full text
27
Dias, Malcolm Benjamin. "Implicit, view-invariant modelling of 3D non-rigid objects." Thesis, University College London (University of London), 2004. http://discovery.ucl.ac.uk/1446859/.
Full textAbstract:
This thesis describes and evaluates the Integrated Shape and Pose Model (ISPM), a novel technique for modelling the geometry of a 3D non-rigid object, such as a face, via images captured from various viewpoints. The ISPM can be trained on almost any set of images since it does not require images captured simultaneously from more than one view. This is advantageous over conventional techniques that impose such constraints on the training data. The ISPM is built by transferring the object's intrinsic shape from the view of each training image, to two basis views. This is achieved by first computing the Centred Affine Trifocal Tensor (CATT) between the view of each given image and the basis views, which implicitly encodes the 3D pose of the object. The object's intrinsic shape is then transferred to the basis views by enforcing the epipolar constraints provided by the CATT followed by an affine alignment. This process (the Implicit Pose Alignment (IPA) algorithm) requires the mean basis view images, which are not initially known. Therefore, the generalized Procrustes alignment algorithm is extended, by employing the IPA algorithm to perform the alignment steps. The extended Procrustes alignment algorithm simultaneously generates the mean basis view images and achieves the required intrinsic shape transfer. The key benefit of our approach is illustrated by the significant improvement in view-invariance and consistency in the ISPM's modelling errors as well as its specificity, in comparison to those of conventional image-based models. The ISPM is evaluated on four databases of real and synthetic face images containing variations in identity, expression and pose. Its various algorithms are also individually evaluated and their performance critically assessed. Future work on incorporating grey-level values may also be possible and, is briefly explored. Our approach may also be of relevance to theories of human vision.
28
Yadav, Kamna. "Improving Accuracy of the Edgebox Approach." DigitalCommons@USU, 2018. https://digitalcommons.usu.edu/etd/7326.
Full textAbstract:
Object region detection plays a vital role in many domains ranging from self-driving cars to lane detection, which heavily involves the task of object detection. Improving the performance of object region detection approaches is of great importance and therefore is an active ongoing research in Computer Vision. Traditional sliding window paradigm has been widely used to identify hundreds of thousands of windows (covering different scales, angles, and aspect ratios for objects) before the classification step. However, it is not only computationally expensive but also produces relatively low accuracy in terms of the classifier output by providing many negative samples. Object detection proposals, as discussed in detail in [19, 20], tackle these issues by filtering the windows using different features in the image before passing them to the classifier. This filtering process helps to control the quality as well as the quantity of the windows. EdgeBox is one of the most effective proposal detection approaches that focuses on the presence of dense edges in an image to identify quality proposal windows.
This thesis proposes an innovative approach that improves the accuracy of the EdgeBox approach. The improved approach uses both the color properties and the corner information from an image along with the edge information to evaluate the candidate windows. We also describe two variations of the proposed approach. Our extensive experimental results on the Visual Object Classification (VOC) [29,30] dataset clearly demonstrate the effectiveness of the proposed approach together with its two variances to improve the accuracy of the EdgeBox approach.
29
Eskizara, Omer. "3d Geometric Hashing Using Transform Invariant Features." Master's thesis, METU, 2009. http://etd.lib.metu.edu.tr/upload/12610546/index.pdf.
Full textAbstract:
3D object recognition is performed by using geometric hashing where transformation and scale invariant 3D surface features are utilized. 3D features are extracted from object surfaces after a scale space search where size of each feature is also estimated.
Scale space is constructed based on orientation invariant surface curvature values which classify each surface point's shape. Extracted features are grouped into triplets and orientation invariant descriptors are defined for each triplet. Each pose of each object is indexed in a hash table using these triplets. For scale invariance matching, cosine similarity is applied for scale variant triple variables. Tests were performed on Stuttgart database where 66 poses of 42 objects are stored in the hash table during training and 258 poses of 42 objects are used during testing. %90.97 recognition rate is achieved.
30
Riley, Timothy Rupert. "Asymptotic invariants of infinite discrete groups." Thesis, University of Oxford, 2002. http://ora.ox.ac.uk/objects/uuid:30f42f4c-e592-44c2-9954-7d9e8c1f3d13.
Full textAbstract:
Asymptotic cones. A finitely generated group has a word metric, which one can scale and thereby view the group from increasingly distant vantage points. The group coalesces to an "asymptotic cone" in the limit (this is made precise using techniques of non-standard analysis). The reward is that in place of the discrete group one has a continuous object "that is amenable to attack by geometric (e.g. topological, infinitesimal) machinery" (to quote Gromov). We give coarse geometric conditions for a metric space X to have N-connected asymptotic cones. These conditions are expressed in terms of certain filling functions concerning filling N-spheres in an appropriately coarse sense. We interpret the criteria in the case where X is a finitely generated group Γ with a word metric. This leads to upper bounds on filling functions for groups with simply connected cones -- in particular they have linearly bounded filling length functions. We prove that if all the asymptotic cones of Γ are N-connected then Γ is of type FN+1 and we provide N-th order isoperimetric and isodiametric functions. Also we show that the asymptotic cones of a virtually polycyclic group Γ are all contractible if and only if Γ is virtually nilpotent. Combable groups and almost-convex groups. A combing of a finitely generated group Γ is a normal form; that is a choice of word (a combing line) for each group element that satisfies a geometric constraint: nearby group elements have combing lines that fellow travel. An almost-convexity condition concerns the geometry of closed balls in the Cayley graph for Γ. We show that even the most mild combability or almost-convexity restrictions on a finitely presented group already force surprisingly strong constraints on the geometry of its word problem. In both cases we obtain an n! isoperimetric function, and upper bounds of ~ n2 on both the minimal isodiametric function and the filling length function.
31
Ghedin, Emanuele. "Rational Cherednik algebras and link invariants." Thesis, University of Oxford, 2015. https://ora.ox.ac.uk/objects/uuid:409475e8-ef3b-490a-8973-d2b2d52b2f5e.
Full textAbstract:
Motivated by homological mirror symmetry, Smith and Thomas tried to construct a link invariant considering the derived category of coherent sheaves on the Hilbert scheme of n points on the minimal resolution of the Klenian singularity of type A, and an object L(n) thereof. The braid group acts on this category by spherical twists, so one obtains a braid invariant by taking the Ext between L(n) and its image under the braid group action. Smith and Thomas proved that taking the plat closure of the braid, this cohomology does not produce a link invariant but is close to doing so, and they conjectured that, in order to fix the one knot relation that is not satisfied, one has to consider a deformation of the Hilbert scheme. In this thesis, we give a non-commutative approach to this problem: the commutative picture can be quantised by considering modules for the rational Cherednik algebra of cyclotomic type. This algebra gives a quantisation of the Hilbert scheme and there is a localisation theorem which allows one to work in the algebraic setting. In this context, the role of L(n) turns out to be played by a certain module for the rational Cherednik algebra which we define for k=0. We then show that this module deforms to non-zero values of k. There is an action of the braid group on the derived category of category ? by twisting functors, which is defined at all deformation parameters, whereas the existence of the action on deformed Hilbert schemes in the commutative setting has not been rigorously established. We prove the analogue of the Smith-Thomas theorem, and conjecture that the braid invariant given by the algebraic analogue of the Smith-Thomas construction yields a link invariant for certain non-zero values of the deformation parameter.
32
Voils, Danny. "Scale Invariant Object Recognition Using Cortical Computational Models and a Robotic Platform." PDXScholar, 2012. https://pdxscholar.library.pdx.edu/open_access_etds/632.
Full textAbstract:
This paper proposes an end-to-end, scale invariant, visual object recognition system, composed of computational components that mimic the cortex in the brain. The system uses a two stage process. The first stage is a filter that extracts scale invariant features from the visual field. The second stage uses inference based spacio-temporal analysis of these features to identify objects in the visual field. The proposed model combines Numenta's Hierarchical Temporal Memory (HTM), with HMAX developed by MIT's Brain and Cognitive Science Department. While these two biologically inspired paradigms are based on what is known about the visual cortex, HTM and HMAX tackle the overall object recognition problem from different directions. Image pyramid based methods like HMAX make explicit use of scale, but have no sense of time. HTM, on the other hand, only indirectly tackles scale, but makes explicit use of time. By combining HTM and HMAX, both scale and time are addressed. In this paper, I show that HTM and HMAX can be combined to make a com- plete cortex inspired object recognition model that explicitly uses both scale and time to recognize objects in temporal sequences of images. Additionally, through experimentation, I examine several variations of HMAX and its
33
Leung, Wai-Man Raymond. "On spin c-invariants of four-manifolds." Thesis, University of Oxford, 1995. http://ora.ox.ac.uk/objects/uuid:a9790f36-748f-4574-a97c-4f416ca67207.
Full textAbstract:
The spinc-invariants for a compact smooth simply-connected oriented four-manifold, as defined by Pidstrigach and Tyurin, are studied in this thesis. Unlike the Donaldson polynomial invariants, they are defined by cutting down the moduli space M' of '1-instantons', which is the subspace of the moduli space M of anti-self-dual connections parametrizing coupled (spinc) Dirac operators with non-trivial kernel. Our main goal is to study the relationship between these spinc-invariants and the Donaldson polynomial invariants. The 'jumping subset' M' defined a cohomology class P of M which is given by the generalised Porteous formula. When the index l of the coupled Dirac operator is 1, the two smooth invariants are the same by definition. When l = 0 (or when M is compact), the spinc-invariants are expressable as a Donaldson polynomial evaluating the 'Porteous class' P. Our main results concern the first two non-trivial cases l = -1 and -2, when the generalised Porteous formula can not be applied directly. Using cut-and-paste arguments to the moduli space M, we show that for the former case the spinc-invariants and the contracted Donaldson invariants differ by a correction term. It is the number of points in the immediate lower stratum of the Uhlenbeck compactification times a universal 'linking invariant' on S4, which is obtained by computing an example (the K3 surface). The case when l = -2 and dimM = 8 is a parametrized version of the l = -1 situation and the correction term, which involves the same 'linking invariant', is obtained from a suitable obstruction theory.
34
Evans, Benjamin D. "Learning transformation-invariant visual representations in spiking neural networks." Thesis, University of Oxford, 2012. https://ora.ox.ac.uk/objects/uuid:15bdf771-de28-400e-a1a7-82228c7f01e4.
Full textAbstract:
This thesis aims to understand the learning mechanisms which underpin the process of visual object recognition in the primate ventral visual system. The computational crux of this problem lies in the ability to retain specificity to recognize particular objects or faces, while exhibiting generality across natural variations and distortions in the view (DiCarlo et al., 2012). In particular, the work presented is focussed on gaining insight into the processes through which transformation-invariant visual representations may develop in the primate ventral visual system. The primary motivation for this work is the belief that some of the fundamental mechanisms employed in the primate visual system may only be captured through modelling the individual action potentials of neurons and therefore, existing rate-coded models of this process constitute an inadequate level of description to fully understand the learning processes of visual object recognition. To this end, spiking neural network models are formulated and applied to the problem of learning transformation-invariant visual representations, using a spike-time dependent learning rule to adjust the synaptic efficacies between the neurons. The ways in which the existing rate-coded CT (Stringer et al., 2006) and Trace (Földiák, 1991) learning mechanisms may operate in a simple spiking neural network model are explored, and these findings are then applied to a more accurate model using realistic 3-D stimuli. Three mechanisms are then examined, through which a spiking neural network may solve the problem of learning separate transformation-invariant representations in scenes composed of multiple stimuli by temporally segmenting competing input representations. The spike-time dependent plasticity in the feed-forward connections is then shown to be able to exploit these input layer dynamics to form individual stimulus representations in the output layer. Finally, the work is evaluated and future directions of investigation are proposed.
35
Weismantel, Eric. "Perceptual Salience of Non-accidental Properties." The Ohio State University, 2013. http://rave.ohiolink.edu/etdc/view?acc_num=osu1376610211.
Full text
36
Isik, Leyla. "The dynamics of invariant object and action recognition in the human visual system." Thesis, Massachusetts Institute of Technology, 2015. http://hdl.handle.net/1721.1/98000.
Full textAbstract:
Thesis: Ph. D., Massachusetts Institute of Technology, Computational and Systems Biology Program, 2015.Cataloged from PDF version of thesis.
Includes bibliographical references (pages 123-138).
Humans can quickly and effortlessly recognize objects, and people and their actions from complex visual inputs. Despite the ease with which the human brain solves this problem, the underlying computational steps have remained enigmatic. What makes object and action recognition challenging are identity-preserving transformations that alter the visual appearance of objects and actions, such as changes in scale, position, and viewpoint. The majority of visual neuroscience studies examining visual recognition either use physiology recordings, which provide high spatiotemporal resolution data with limited brain coverage, or functional MRI, which provides high spatial resolution data from across the brain with limited temporal resolution. High temporal resolution data from across the brain is needed to break down and understand the computational steps underlying invariant visual recognition. In this thesis I use magenetoencephalography, machine learning, and computational modeling to study invariant visual recognition. I show that a temporal association learning rule for learning invariance in hierarchical visual systems is very robust to manipulations and visual disputations that happen during development (Chapter 2). I next show that object recognition occurs very quickly, with invariance to size and position developing in stages beginning around 100ms after stimulus onset (Chapter 3), and that action recognition occurs on a similarly fast time scale, 200 ms after video onset, with this early representation being invariant to changes in actor and viewpoint (Chapter 4). Finally, I show that the same hierarchical feedforward model can explain both the object and action recognition timing results, putting this timing data in the broader context of computer vision systems and models of the brain. This work sheds light on the computational mechanisms underlying invariant object and action recognition in the brain and demonstrates the importance of using high temporal resolution data to understand neural computations.
by Leyla Isik.
Ph. D.
37
Christou, Alexis. "Dynamics on scale-invariant structures." Thesis, University of Oxford, 1987. http://ora.ox.ac.uk/objects/uuid:15fd6e54-0ac4-4f4d-8115-0ee51ad74504.
Full textAbstract:
We investigate dynamical processes on random and regular fractals. The (static) problem of percolation in the semi-infinite plane introduces many pertinent ideas including real space renormalisation group (RSRG) fugacity transformations and scaling forms. We study the percolation probability to determine the surface critical behaviour and to establish exponent relations. The fugacity approach is generalised to study random walks on diffusion-limited aggregates (DLA). Using regular and random models, we calculate the walk dimensionality and demonstrate that it is consistent with a conjecture by Aharony and Stauffer. It is shown that the kinetically grown DLA is in a distinct dynamic universality class to lattice animals. Similarly, the speculation of Helman-Coniglio-Tsallis regarding diffusion on self-avoiding walks (SAWs) is shown to be incorrect. The results are corroborated by an exact enumeration analysis of the internal structure of SAWs. A 'spin' and field theoretic Hamiltonian formulation for the conformational and resistance properties of random walks is presented. We consider Gaussian random walks, SAWs, spiral SAWs and valence walks. We express resistive susceptibilities as correlation functions and hence e-expansions are calculated for the resistance exponents. For SAWs, the local crosslinks are shown to be irrelevant and we calculate corrections to scaling. A scaling description is introduced into an equation-of-motion method in order to study spin wave damping in d-dimensional isotropic Heisenberg ferro-, antiferro- and ferri- magnets near pc . Dynamic scaling is shown to be obeyed by the Lorentzian spin wave response function and lifetime. The ensemble of finite clusters and multicritical behaviour is also treated. In contrast, the relaxational dynamics of the dilute Anisotropic Heisenberg model is shown to violate conventional dynamic scaling near the percolation bicritical point but satisfies instead a singular scaling behaviour arising from activation of Bloch walls over percolation cluster energy barriers.
38
Li, Muhua 1973. "Learning invariant neuronal representations for objects across visual-related self-actions." Thesis, McGill University, 2005. http://digitool.Library.McGill.CA:80/R/?func=dbin-jump-full&object_id=85565.
Full textAbstract:
This work is aimed at understanding and modelling the perceptual stability mechanisms of human visual systems, regardless of large changes in the visual sensory input resulting from some visual-related motions. Invariant neuronal representation plays an important role for memory systems to associate and recognize objects.In contrast to the bulk of previous research work on the learning of invariance that focuses on the pure bottom-up visual information, we incorporate visual-related self-action signals such as commands for eye, head or body movements, to actively collect the changing visual information and gate the learning process. This helps neural networks learn certain degrees of invariance in an efficient way. We describe a method that can produce a network with invariance to changes in visual input caused by eye movements and covert attention shifts. Training of the network is controlled by signals associated with eye movements and covert attention shifting. A temporal perceptual stability constraint is used to drive the output of the network towards remaining constant across temporal sequences of saccadic motions and covert attention shifts. We use a four-layer neural network model to perform the position-invariant extraction of local features and temporal integration of invariant presentations of local features. The model is further extended to handle viewpoint invariance over eye, head, and/or body movements. We also study cases of multiple features instead of single features in the retinal images, which need a self-organized system to learn over a set of feature classes. A modified saliency map mechanism with spatial constraint is employed to assure that attention stays as much as possible on the same targeted object in a multiple-object scene during the first few shifts.
We present results on both simulated data and real images, to demonstrate that our network can acquire invariant neuronal representations, such as position and attention shift invariance. We also demonstrate that our method performs well in realistic situations in which the temporal sequence of input data is not smooth, situations in which earlier approaches have difficulty.
39
Baris, Yuksel. "Automated Building Detection From Satellite Images By Using Shadow Information As An Object Invariant." Master's thesis, METU, 2012. http://etd.lib.metu.edu.tr/upload/12614909/index.pdf.
Full textAbstract:
Apart from classical pattern recognition techniques applied for automated building detection in satellite images, a robust building detection methodology is proposed, where self-supervision data can be automatically extracted from the image by using shadow and its direction as an invariant for building object. In this methodologyfirst the vegetation, water and shadow regions are detected from a given satellite image and local directional fuzzy landscapes representing the existence of building are generated from the shadow regions using the direction of illumination obtained from image metadata. For each landscape, foreground (building) and background pixels are automatically determined and a bipartitioning is obtained using a graph-based algorithm, Grabcut. Finally, local results are merged to obtain the final building detection result. Considering performance evaluation results, this approach can be seen as a proof of concept that the shadow is an invariant for a building object and promising detection results can be obtained when even a single invariant for an object is used.
40
Nelson, Eric D. "Zoom techniques for achieving scale invariant object tracking in real-time active vision systems /." Online version of the thesis, 2006. https://ritdml.rit.edu/dspace/handle/1850/2620.
Full text
41
Zografos, V. "Pose-invariant, model-based object recognition, using linear combination of views and Bayesian statistics." Thesis, University College London (University of London), 2009. http://discovery.ucl.ac.uk/18954/.
Full textAbstract:
This thesis presents an in-depth study on the problem of object recognition, and in particular the detection of 3-D objects in 2-D intensity images which may be viewed from a variety of angles. A solution to this problem remains elusive to this day, since it involves dealing with variations in geometry, photometry and viewing angle, noise, occlusions and incomplete data. This work restricts its scope to a particular kind of extrinsic variation; variation of the image due to changes in the viewpoint from which the object is seen. A technique is proposed and developed to address this problem, which falls into the category of view-based approaches, that is, a method in which an object is represented as a collection of a small number of 2-D views, as opposed to a generation of a full 3-D model. This technique is based on the theoretical observation that the geometry of the set of possible images of an object undergoing 3-D rigid transformations and scaling may, under most imaging conditions, be represented by a linear combination of a small number of 2-D views of that object. It is therefore possible to synthesise a novel image of an object given at least two existing and dissimilar views of the object, and a set of linear coefficients that determine how these views are to be combined in order to synthesise the new image. The method works in conjunction with a powerful optimization algorithm, to search and recover the optimal linear combination coefficients that will synthesize a novel image, which is as similar as possible to the target, scene view. If the similarity between the synthesized and the target images is above some threshold, then an object is determined to be present in the scene and its location and pose are defined, in part, by the coefficients. The key benefits of using this technique is that because it works directly with pixel values, it avoids the need for problematic, low-level feature extraction and solution of the correspondence problem. As a result, a linear combination of views (LCV) model is easy to construct and use, since it only requires a small number of stored, 2-D views of the object in question, and the selection of a few landmark points on the object, the process which is easily carried out during the offline, model building stage. In addition, this method is general enough to be applied across a variety of recognition problems and different types of objects. The development and application of this method is initially explored looking at two-dimensional problems, and then extending the same principles to 3-D. Additionally, the method is evaluated across synthetic and real-image datasets, containing variations in the objects’ identity and pose. Future work on possible extensions to incorporate a foreground/background model and lighting variations of the pixels are examined.
42
Rahtu, E. (Esa). "A multiscale framework for affine invariant pattern recognition and registration." Doctoral thesis, University of Oulu, 2007. http://urn.fi/urn:isbn:9789514286018.
Full textAbstract:
Abstract
This thesis presents a multiscale framework for the construction of affine invariant pattern recognition and registration methods. The idea in the introduced approach is to extend the given pattern to a set of affine covariant versions, each carrying slightly different information, and then to apply known affine invariants to each of them separately. The key part of the framework is the construction of the affine covariant set, and this is done by combining several scaled representations of the original pattern. The advantages compared to previous approaches include the possibility of many variations and the inclusion of spatial information on the patterns in the features.
The application of the multiscale framework is demonstrated by constructing several new affine invariant methods using different preprocessing techniques, combination schemes, and final recognition and registration approaches. The techniques introduced are briefly described from the perspective of the multiscale framework, and further treatment and properties are presented in the corresponding original publications. The theoretical discussion is supported by several experiments where the new methods are compared to existing approaches.
In this thesis the patterns are assumed to be gray scale images, since this is the main application where affine relations arise. Nevertheless, multiscale methods can also be applied to other kinds of patterns where an affine relation is present.
An additional application of one multiscale based technique in convexity measurements is introduced. The method, called multiscale autoconvolution, can be used to build a convexity measure which is a descriptor of object shape. The proposed measure has two special features compared to existing approaches. It can be applied directly to gray scale images approximating binary objects, and it can be easily modified to produce a number of measures. The new measure is shown to be straightforward to evaluate for a given shape, and it performs well in the applications, as demonstrated by the experiments in the original paper.
43
Huguet, Casades Gemma. "The role of hyperbolic invariant objects: From Arnold diffusion to biological clocks." Doctoral thesis, Universitat Politècnica de Catalunya, 2008. http://hdl.handle.net/10803/5856.
Full textAbstract:
El marc d'aquesta tesi són els objectes invariants hiperbòlics (tors amb bigotis, cicles límit, NHIM,. . .), que constitueixen, per aquesta tesi, els objectes essencials per a l'estudi de diversos problemes des de la difusió d'Arnold fins als rellotges biològics. Treballem en tres temes diferents des d'un enfocament tant teòric com numèric, amb una especial atenció per a les aplicacions, especialment en neurobiologia:· Existència de difusió d'Arnold per a sistemes Hamiltonians a priori inestables
· Algorismes numèrics ràpids per al càlcul de tors invariants i els "bigotis" associats, per a sistemes Hamiltonians utilitzant el mètode de la parametrització.
· Càlcul d'isòcrones i corbes de resposta de fase (PRC) en sistemes neurobiològics usant el mètode de la parametrització.
En la primera part de la tesi, hem considerat el cas d'un sistema Hamiltonià a priori inestable amb 2+1/2 graus de llibertat sotmès a una pertorbació de tipus general. "A priori inestable" significa que el sistema no pertorbat presenta un punt d'equilibri hiperbòlic amb una òrbita homoclínica associada. El resultat principal d'aquesta part de la tesi és que per a un conjunt genèric de pertorbacions prou regulars, el sistema presenta el fenòmen de la difusió d'Arnold, és a dir, existeixen trajectòries la variable acció de les quals experimenta un canvi d'ordre 1. La demostració es basa en un estudi detallat de les zones ressonants i els objectes invariants generats en elles, i ofereix una descripció completa de la geografia de les ressonàncies generades per una pertorbació genèrica.
En la segona part d'aquest memòria, desenvolupem mètodes numèrics eficients que requereixen poca memòria i operacions per al càlcul de tors invariants i els "bigotis" associats en sistemes Hamiltonians (aplicacions simplèctiques i camps vectorials Hamiltonians).
En particular, això inclou els objectes invariants involucrats en el mecanisme de la difusió d'Arnold, estudiat en el capítol anterior. Els algorismes es basen en el mètode de la parametrització i segueixen de prop demostracions recents del teorema KAM que no usen variables acció-angle. Donem detalls de la implementació numèrica que hem dut a terme i mostrem alguns exemples.
En la darrera part de la tesi relacionem problemes de temps en sistemes biològics amb algunes eines conegudes de sistemes dinàmics. En particular, usem el mètode de la parametrització i les simetries de Lie per a calcular numèricament les isòcrones i les corbes de resposta de fase (PRC) associades a oscil·ladors i ho apliquem a diversos models biològics ben coneguts. A més a més, aconseguim estendre el càlcul de PRCs en un entorn de l'oscil·lador. Les PRCs són útils per a l'estudi de la sincronització d'oscil·ladors acoblats i una eina bàsica en biologia experimental (ritmes circadians, acoblament sinàptic i elèctric de neurones,. . . ).
44
Hall, Daniela. "Viewpoint independent recognition of objects from local appearance." Grenoble INPG, 2001. http://www.theses.fr/2001INPG0086.
Full text
45
Baston, Robert J. "The algebraic construction of invariant differential operators." Thesis, University of Oxford, 1985. http://ora.ox.ac.uk/objects/uuid:a7cb5790-7267-47d2-9179-df705405ae08.
Full textAbstract:
Let G be a complex semisimple Lie Group with parabolic subgroup P, so that G/P is a generalized flag manifold. An algebraic construction of invariant differential operators between sections of homogeneous bundles over such spaces is given and it is shown how this leads to the classification of all such operators. As an example of a process which naturally generates such operators, the algebraic Penrose transform between generalized flag manifolds is given and computed for several cases, extending standard results in Twistor Theory to higher dimensions. It is then shown how to adapt the homogeneous construction to manifolds with a certain class of tangent bundle structure, including conformal manifolds. This leads to a natural definition of invariant differential operators on such manifolds, and an algebraic method for their construction. A curved analogue of the Penrose transform is given.
46
Umasuthan, M. "Recognition and position estimation of 3D objects from range images using algebraic and moment invariants." Thesis, Heriot-Watt University, 1995. http://hdl.handle.net/10399/763.
Full text
47
Glauser, Thomas. "CAD-based recognition of polyhedral 3-D objects using affine invariant surface representations /." Bern : Universität Bern Institut für Informatik und angewandte Mathematik, 1992. http://www.ub.unibe.ch/content/bibliotheken_sammlungen/sondersammlungen/dissen_bestellformular/index_ger.html.
Full text
48
Smart, Michael Howard William. "Adaptive, linear, subspatial projections for invariant recognition of objects in real infrared images." Thesis, University of Edinburgh, 1998. http://hdl.handle.net/1842/12974.
Full textAbstract:
In recent years computer technology has advanced to a state whereby large quantities of data can be processed. This advancement has fuelled a dramatic increased in research into areas of image processing which were previously impractical, such as automated vision systems for, both military, and domestic purposes. Automatic Target Recognition (ATR) systems are one such example of these automated processes. ATR is the automatic detection, isolation and identification of objects, often derived from raw video, in a real-world, potentially hostile environment. The ability to rapidly, and accurately, process each frame of the incoming video stream is paramount to the success of the system, in order to output suitable actions against constantly changing situations. One of the main functions of an ATR system is to identify correctly all the objects detected in each frame of data. The standard approach to implementing this component is to divide the identification process into two separate modules; feature extraction and classification. However, it is often difficult to optimise such a dual system with respect to reducing the probability of mis-identification. This can lead to reduced performance. One potential solution is a neural network that accepts image data at the input, and outputs estimated classification. Unfortunately, neural network models of this type are prone to misuse due to their apparent black box solutions. In this thesis a new technique, based on existing adaptive wavelet algorithms, is implemented that offers ease-of-use, adaptability to new environments, and good generalisation in a single image-in-classification-out model that avoids many of the problems of the neural network approach. This new model is compared with the standard two stage approach using real-world, infrared, ATR data. Various extensions to the model are proposed to incorporate invariance to particular object deformations, such as size and rotation, which are necessary for reliable ATR performance. Further work increases the flexibility of the model to further improve generalisation. Other aspects, such as data analysis and object generation accuracy, which are often neglected, are also considered.
49
Donatti, Guillermo Sebastián [Verfasser], Rolf [Gutachter] Würtz, and Boris [Gutachter] Suchan. "Memory organization for invariant object recognition and categorization / Guillermo Sebastián Donatti ; Gutachter: Rolf Würtz, Boris Suchan." Bochum : Ruhr-Universität Bochum, 2016. http://d-nb.info/1114496944/34.
Full text
50
Ojansivu, V. (Ville). "Blur invariant pattern recognition and registration in the Fourier domain." Doctoral thesis, University of Oulu, 2009. http://urn.fi/urn:isbn:9789514292552.
Full textAbstract:
Abstract
Pattern recognition and registration are integral elements of computer vision, which considers image patterns. This thesis presents novel blur, and combined blur and geometric invariant features for pattern recognition and registration related to images. These global or local features are based on the Fourier transform phase, and are invariant or insensitive to image blurring with a centrally symmetric point spread function which can result, for example, from linear motion or out of focus.
The global features are based on the even powers of the phase-only discrete Fourier spectrum or bispectrum of an image and are invariant to centrally symmetric blur. These global features are used for object recognition and image registration. The features are extended for geometrical invariances up to similarity transformation: shift invariance is obtained using bispectrum, and rotation-scale invariance using log-polar mapping of bispectrum slices. Affine invariance can be achieved as well using rotated sets of the log-log mapped bispectrum slices. The novel invariants are shown to be more robust to additive noise than the earlier blur, and combined blur and geometric invariants based on image moments.
The local features are computed using the short term Fourier transform in local windows around the points of interest. Only the lowest horizontal, vertical, and diagonal frequency coefficients are used, the phase of which is insensitive to centrally symmetric blur. The phases of these four frequency coefficients are quantized and used to form a descriptor code for the local region. When these local descriptors are used for texture classification, they are computed for every pixel, and added up to a histogram which describes the local pattern. There are no earlier textures features which have been claimed to be invariant to blur. The proposed descriptors were superior in the classification of blurred textures compared to a few non-blur invariant state of the art texture classification methods.