Home | [81–90] << 91 92 93 94 95 96 97 98 99 100 >> [101–110] |
![]() |
Records | |||||
---|---|---|---|---|---|
Author | Simon Jégou; Michal Drozdzal; David Vazquez; Adriana Romero; Yoshua Bengio | ||||
Title | The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation | Type | Conference Article | ||
Year | 2017 | Publication | IEEE Conference on Computer Vision and Pattern Recognition Workshops | Abbreviated Journal | |
Volume ![]() |
Issue | Pages | |||
Keywords | Semantic Segmentation | ||||
Abstract | State-of-the-art approaches for semantic image segmentation are built on Convolutional Neural Networks (CNNs). The typical segmentation architecture is composed of (a) a downsampling path responsible for extracting coarse semantic features, followed by (b) an upsampling path trained to recover the input image resolution at the output of the model and, optionally, (c) a post-processing module (e.g. Conditional Random Fields) to refine the model predictions.
Recently, a new CNN architecture, Densely Connected Convolutional Networks (DenseNets), has shown excellent results on image classification tasks. The idea of DenseNets is based on the observation that if each layer is directly connected to every other layer in a feed-forward fashion then the network will be more accurate and easier to train. In this paper, we extend DenseNets to deal with the problem of semantic segmentation. We achieve state-of-the-art results on urban scene benchmark datasets such as CamVid and Gatech, without any further post-processing module nor pretraining. Moreover, due to smart construction of the model, our approach has much less parameters than currently published best entries for these datasets. |
||||
Address | Honolulu; USA; July 2017 | ||||
Corporate Author | Thesis | ||||
Publisher | Place of Publication | Editor | |||
Language | Summary Language | Original Title | |||
Series Editor | Series Title | Abbreviated Series Title | |||
Series Volume | Series Issue | Edition | |||
ISSN | ISBN | Medium | |||
Area | Expedition | Conference | CVPRW | ||
Notes | MILAB; ADAS; 600.076; 600.085; 601.281 | Approved | no | ||
Call Number | ADAS @ adas @ JDV2016 | Serial | 2866 | ||
Permanent link to this record | |||||
Author | Arash Akbarinia; C. Alejandro Parraga | ||||
Title | Biologically plausible boundary detection | Type | Conference Article | ||
Year | 2016 | Publication | 27th British Machine Vision Conference | Abbreviated Journal | |
Volume ![]() |
Issue | Pages | |||
Keywords | |||||
Abstract | Edges are key components of any visual scene to the extent that we can recognise objects merely by their silhouettes. The human visual system captures edge information through neurons in the visual cortex that are sensitive to both intensity discontinuities and particular orientations. The “classical approach” assumes that these cells are only responsive to the stimulus present within their receptive fields, however, recent studies demonstrate that surrounding regions and inter-areal feedback connections influence their responses significantly. In this work we propose a biologically-inspired edge detection model in which orientation selective neurons are represented through the first derivative of a Gaussian function resembling double-opponent cells in the primary visual cortex (V1). In our model we account for four kinds of surround, i.e. full, far, iso- and orthogonal-orientation, whose contributions are contrast-dependant. The output signal from V1 is pooled in its perpendicular direction by larger V2 neurons employing a contrast-variant centre-surround kernel. We further introduce a feedback connection from higher-level visual areas to the lower ones. The results of our model on two benchmark datasets show a big improvement compared to the current non-learning and biologically-inspired state-of-the-art algorithms while being competitive to the learning-based methods. | ||||
Address | York; UK; September 2016 | ||||
Corporate Author | Thesis | ||||
Publisher | Place of Publication | Editor | |||
Language | Summary Language | Original Title | |||
Series Editor | Series Title | Abbreviated Series Title | |||
Series Volume | Series Issue | Edition | |||
ISSN | ISBN | Medium | |||
Area | Expedition | Conference | BMVC | ||
Notes | NEUROBIT; 600.068; 600.072 | Approved | no | ||
Call Number | Admin @ si @ AkP2016a | Serial | 2867 | ||
Permanent link to this record | |||||
Author | Azadeh S. Mozafari; David Vazquez; Mansour Jamzad; Antonio Lopez | ||||
Title | Node-Adapt, Path-Adapt and Tree-Adapt:Model-Transfer Domain Adaptation for Random Forest | Type | Miscellaneous | ||
Year | 2016 | Publication | Arxiv | Abbreviated Journal | |
Volume ![]() |
Issue | Pages | |||
Keywords | Domain Adaptation; Pedestrian detection; Random Forest | ||||
Abstract | Random Forest (RF) is a successful paradigm for learning classifiers due to its ability to learn from large feature spaces and seamlessly integrate multi-class classification, as well as the achieved accuracy and processing efficiency. However, as many other classifiers, RF requires domain adaptation (DA) provided that there is a mismatch between the training (source) and testing (target) domains which provokes classification degradation. Consequently, different RF-DA methods have been proposed, which not only require target-domain samples but revisiting the source-domain ones, too. As novelty, we propose three inherently different methods (Node-Adapt, Path-Adapt and Tree-Adapt) that only require the learned source-domain RF and a relatively few target-domain samples for DA, i.e. source-domain samples do not need to be available. To assess the performance of our proposals we focus on image-based object detection, using the pedestrian detection problem as challenging proof-of-concept. Moreover, we use the RF with expert nodes because it is a competitive patch-based pedestrian model. We test our Node-, Path- and Tree-Adapt methods in standard benchmarks, showing that DA is largely achieved. | ||||
Address | |||||
Corporate Author | Thesis | ||||
Publisher | Place of Publication | Editor | |||
Language | Summary Language | Original Title | |||
Series Editor | Series Title | Abbreviated Series Title | |||
Series Volume | Series Issue | Edition | |||
ISSN | ISBN | Medium | |||
Area | Expedition | Conference | |||
Notes | ADAS | Approved | no | ||
Call Number | ADAS @ adas @ MVJ2016 | Serial | 2868 | ||
Permanent link to this record | |||||
Author | Youssef El Rhabi; Simon Loic; Brun Luc; Josep Llados; Felipe Lumbreras | ||||
Title | Information Theoretic Rotationwise Robust Binary Descriptor Learning | Type | Conference Article | ||
Year | 2016 | Publication | Joint IAPR International Workshops on Statistical Techniques in Pattern Recognition (SPR) and Structural and Syntactic Pattern Recognition (SSPR) | Abbreviated Journal | |
Volume ![]() |
Issue | Pages | 368-378 | ||
Keywords | |||||
Abstract | In this paper, we propose a new data-driven approach for binary descriptor selection. In order to draw a clear analysis of common designs, we present a general information-theoretic selection paradigm. It encompasses several standard binary descriptor construction schemes, including a recent state-of-the-art one named BOLD. We pursue the same endeavor to increase the stability of the produced descriptors with respect to rotations. To achieve this goal, we have designed a novel offline selection criterion which is better adapted to the online matching procedure. The effectiveness of our approach is demonstrated on two standard datasets, where our descriptor is compared to BOLD and to several classical descriptors. In particular, it emerges that our approach can reproduce equivalent if not better performance as BOLD while relying on twice shorter descriptors. Such an improvement can be influential for real-time applications. | ||||
Address | Mérida; Mexico; November 2016 | ||||
Corporate Author | Thesis | ||||
Publisher | Place of Publication | Editor | |||
Language | Summary Language | Original Title | |||
Series Editor | Series Title | Abbreviated Series Title | |||
Series Volume | Series Issue | Edition | |||
ISSN | ISBN | Medium | |||
Area | Expedition | Conference | S+SSPR | ||
Notes | DAG; ADAS; 600.097; 600.086 | Approved | no | ||
Call Number | Admin @ si @ RLL2016 | Serial | 2871 | ||
Permanent link to this record | |||||
Author | Antonio Lopez; Jiaolong Xu; Jose Luis Gomez; David Vazquez; German Ros | ||||
Title | From Virtual to Real World Visual Perception using Domain Adaptation -- The DPM as Example | Type | Book Chapter | ||
Year | 2017 | Publication | Domain Adaptation in Computer Vision Applications | Abbreviated Journal | |
Volume ![]() |
Issue | 13 | Pages | 243-258 | |
Keywords | Domain Adaptation | ||||
Abstract | Supervised learning tends to produce more accurate classifiers than unsupervised learning in general. This implies that training data is preferred with annotations. When addressing visual perception challenges, such as localizing certain object classes within an image, the learning of the involved classifiers turns out to be a practical bottleneck. The reason is that, at least, we have to frame object examples with bounding boxes in thousands of images. A priori, the more complex the model is regarding its number of parameters, the more annotated examples are required. This annotation task is performed by human oracles, which ends up in inaccuracies and errors in the annotations (aka ground truth) since the task is inherently very cumbersome and sometimes ambiguous. As an alternative we have pioneered the use of virtual worlds for collecting such annotations automatically and with high precision. However, since the models learned with virtual data must operate in the real world, we still need to perform domain adaptation (DA). In this chapter we revisit the DA of a deformable part-based model (DPM) as an exemplifying case of virtual- to-real-world DA. As a use case, we address the challenge of vehicle detection for driver assistance, using different publicly available virtual-world data. While doing so, we investigate questions such as: how does the domain gap behave due to virtual-vs-real data with respect to dominant object appearance per domain, as well as the role of photo-realism in the virtual world. | ||||
Address | |||||
Corporate Author | Thesis | ||||
Publisher | Springer | Place of Publication | Editor | Gabriela Csurka | |
Language | Summary Language | Original Title | |||
Series Editor | Series Title | Abbreviated Series Title | |||
Series Volume | Series Issue | Edition | |||
ISSN | ISBN | Medium | |||
Area | Expedition | Conference | |||
Notes | ADAS; 600.085; 601.223; 600.076; 600.118 | Approved | no | ||
Call Number | ADAS @ adas @ LXG2017 | Serial | 2872 | ||
Permanent link to this record | |||||
Author | Pau Riba; Alicia Fornes; Josep Llados | ||||
Title | Towards the Alignment of Handwritten Music Scores | Type | Conference Article | ||
Year | 2015 | Publication | 11th IAPR International Workshop on Graphics Recognition | Abbreviated Journal | |
Volume ![]() |
Issue | Pages | |||
Keywords | |||||
Abstract | It is very common to find different versions of the same music work in archives of Opera Theaters. These differences correspond to modifications and annotations from the musicians. From the musicologist point of view, these variations are very interesting and deserve study. This paper explores the alignment of music scores as a tool for automatically detecting the passages that contain such differences. Given the difficulties in the recognition of handwritten music scores, our goal is to align the music scores and at the same time, avoid the recognition of music elements as much as possible. After removing the staff lines, braces and ties, the bar lines are detected. Then, the bar units are described as a whole using the Blurred Shape Model. The bar units alignment is performed by using Dynamic Time Warping. The analysis of the alignment path is used to detect the variations in the music scores. The method has been evaluated on a subset of the CVC-MUSCIMA dataset, showing encouraging results. | ||||
Address | Nancy; France; August 2015 | ||||
Corporate Author | Thesis | ||||
Publisher | Springer International Publishing | Place of Publication | Editor | Bart Lamiroy; Rafael Dueire Lins | |
Language | Summary Language | Original Title | |||
Series Editor | Series Title | Abbreviated Series Title | LNCS | ||
Series Volume | Series Issue | Edition | |||
ISSN | ISBN | 978-3-319-52158-9 | Medium | ||
Area | Expedition | Conference | GREC | ||
Notes | DAG | Approved | no | ||
Call Number | Admin @ si @ | Serial | 2874 | ||
Permanent link to this record | |||||
Author | Anjan Dutta; Umapada Pal; Josep Llados | ||||
Title | Compact Correlated Features for Writer Independent Signature Verification | Type | Conference Article | ||
Year | 2016 | Publication | 23rd International Conference on Pattern Recognition | Abbreviated Journal | |
Volume ![]() |
Issue | Pages | |||
Keywords | |||||
Abstract | This paper considers the offline signature verification problem which is considered to be an important research line in the field of pattern recognition. In this work we propose hybrid features that consider the local features and their global statistics in the signature image. This has been done by creating a vocabulary of histogram of oriented gradients (HOGs). We impose weights on these local features based on the height information of water reservoirs obtained from the signature. Spatial information between local features are thought to play a vital role in considering the geometry of the signatures which distinguishes the originals from the forged ones. Nevertheless, learning a condensed set of higher order neighbouring features based on visual words, e.g., doublets and triplets, continues to be a challenging problem as possible combinations of visual words grow exponentially. To avoid this explosion of size, we create a code of local pairwise features which are represented as joint descriptors. Local features are paired based on the edges of a graph representation built upon the Delaunay triangulation. We reveal the advantage of combining both type of visual codebooks (order one and pairwise) for signature verification task. This is validated through an encouraging result on two benchmark datasets viz. CEDAR and GPDS300. | ||||
Address | Cancun; Mexico; December 2016 | ||||
Corporate Author | Thesis | ||||
Publisher | Place of Publication | Editor | |||
Language | Summary Language | Original Title | |||
Series Editor | Series Title | Abbreviated Series Title | |||
Series Volume | Series Issue | Edition | |||
ISSN | ISBN | Medium | |||
Area | Expedition | Conference | ICPR | ||
Notes | DAG; 600.097 | Approved | no | ||
Call Number | Admin @ si @ DPL2016 | Serial | 2875 | ||
Permanent link to this record | |||||
Author | Sounak Dey; Anguelos Nicolaou; Josep Llados; Umapada Pal | ||||
Title | Local Binary Pattern for Word Spotting in Handwritten Historical Document | Type | Conference Article | ||
Year | 2016 | Publication | Joint IAPR International Workshops on Statistical Techniques in Pattern Recognition (SPR) and Structural and Syntactic Pattern Recognition (SSPR) | Abbreviated Journal | |
Volume ![]() |
Issue | Pages | 574-583 | ||
Keywords | Local binary patterns; Spatial sampling; Learning-free; Word spotting; Handwritten; Historical document analysis; Large-scale data | ||||
Abstract | Digital libraries store images which can be highly degraded and to index this kind of images we resort to word spotting as our information retrieval system. Information retrieval for handwritten document images is more challenging due to the difficulties in complex layout analysis, large variations of writing styles, and degradation or low quality of historical manuscripts. This paper presents a simple innovative learning-free method for word spotting from large scale historical documents combining Local Binary Pattern (LBP) and spatial sampling. This method offers three advantages: firstly, it operates in completely learning free paradigm which is very different from unsupervised learning methods, secondly, the computational time is significantly low because of the LBP features, which are very fast to compute, and thirdly, the method can be used in scenarios where annotations are not available. Finally, we compare the results of our proposed retrieval method with other methods in the literature and we obtain the best results in the learning free paradigm. | ||||
Address | Merida; Mexico; December 2016 | ||||
Corporate Author | Thesis | ||||
Publisher | Place of Publication | Editor | |||
Language | Summary Language | Original Title | |||
Series Editor | Series Title | Abbreviated Series Title | LNCS | ||
Series Volume | Series Issue | Edition | |||
ISSN | ISBN | Medium | |||
Area | Expedition | Conference | S+SSPR | ||
Notes | DAG; 600.097; 602.006; 603.053 | Approved | no | ||
Call Number | Admin @ si @ DNL2016 | Serial | 2876 | ||
Permanent link to this record | |||||
Author | Daniel Hernandez; Antonio Espinosa; David Vazquez; Antonio Lopez; Juan Carlos Moure | ||||
Title | Embedded Real-time Stixel Computation | Type | Conference Article | ||
Year | 2017 | Publication | GPU Technology Conference | Abbreviated Journal | |
Volume ![]() |
Issue | Pages | |||
Keywords | GPU; CUDA; Stixels; Autonomous Driving | ||||
Abstract | |||||
Address | Silicon Valley; USA; May 2017 | ||||
Corporate Author | Thesis | ||||
Publisher | Place of Publication | Editor | |||
Language | Summary Language | Original Title | |||
Series Editor | Series Title | Abbreviated Series Title | |||
Series Volume | Series Issue | Edition | |||
ISSN | ISBN | Medium | |||
Area | Expedition | Conference | GTC | ||
Notes | ADAS; 600.118 | Approved | no | ||
Call Number | ADAS @ adas @ HEV2017a | Serial | 2879 | ||
Permanent link to this record | |||||
Author | David Vazquez; Jorge Bernal; F. Javier Sanchez; Gloria Fernandez Esparrach; Antonio Lopez; Adriana Romero; Michal Drozdzal; Aaron Courville | ||||
Title | A Benchmark for Endoluminal Scene Segmentation of Colonoscopy Images | Type | Conference Article | ||
Year | 2017 | Publication | 31st International Congress and Exhibition on Computer Assisted Radiology and Surgery | Abbreviated Journal | |
Volume ![]() |
Issue | Pages | |||
Keywords | Deep Learning; Medical Imaging | ||||
Abstract | Colorectal cancer (CRC) is the third cause of cancer death worldwide. Currently, the standard approach to reduce CRC-related mortality is to perform regular screening in search for polyps and colonoscopy is the screening tool of choice. The main limitations of this screening procedure are polyp miss-rate and inability to perform visual assessment of polyp malignancy. These drawbacks can be reduced by designing Decision Support Systems (DSS) aiming to help clinicians in the different stages of the procedure by providing endoluminal scene segmentation. Thus, in this paper, we introduce an extended benchmark of colonoscopy image, with the hope of establishing a new strong benchmark for colonoscopy image analysis research. We provide new baselines on this dataset by training standard fully convolutional networks (FCN) for semantic segmentation and significantly outperforming, without any further post-processing, prior results in endoluminal scene segmentation. | ||||
Address | |||||
Corporate Author | Thesis | ||||
Publisher | Place of Publication | Editor | |||
Language | Summary Language | Original Title | |||
Series Editor | Series Title | Abbreviated Series Title | |||
Series Volume | Series Issue | Edition | |||
ISSN | ISBN | Medium | |||
Area | Expedition | Conference | CARS | ||
Notes | ADAS; MV; 600.075; 600.085; 600.076; 601.281; 600.118 | Approved | no | ||
Call Number | ADAS @ adas @ VBS2017a | Serial | 2880 | ||
Permanent link to this record | |||||
Author | David Geronimo; David Vazquez; Arturo de la Escalera | ||||
Title | Vision-Based Advanced Driver Assistance Systems | Type | Book Chapter | ||
Year | 2017 | Publication | Computer Vision in Vehicle Technology: Land, Sea, and Air | Abbreviated Journal | |
Volume ![]() |
Issue | Pages | |||
Keywords | ADAS; Autonomous Driving | ||||
Abstract | |||||
Address | |||||
Corporate Author | Thesis | ||||
Publisher | Place of Publication | Editor | |||
Language | Summary Language | Original Title | |||
Series Editor | Series Title | Abbreviated Series Title | |||
Series Volume | Series Issue | Edition | |||
ISSN | ISBN | Medium | |||
Area | Expedition | Conference | |||
Notes | ADAS; 600.118 | Approved | no | ||
Call Number | ADAS @ adas @ GVE2017 | Serial | 2881 | ||
Permanent link to this record | |||||
Author | Juan A. Carvajal Ayala; Dennis Romero; Angel Sappa | ||||
Title | Fine-tuning based deep convolutional networks for lepidopterous genus recognition | Type | Conference Article | ||
Year | 2016 | Publication | 21st Ibero American Congress on Pattern Recognition | Abbreviated Journal | |
Volume ![]() |
Issue | Pages | 467-475 | ||
Keywords | |||||
Abstract | This paper describes an image classification approach oriented to identify specimens of lepidopterous insects at Ecuadorian ecological reserves. This work seeks to contribute to studies in the area of biology about genus of butterflies and also to facilitate the registration of unrecognized specimens. The proposed approach is based on the fine-tuning of three widely used pre-trained Convolutional Neural Networks (CNNs). This strategy is intended to overcome the reduced number of labeled images. Experimental results with a dataset labeled by expert biologists is presented, reaching a recognition accuracy above 92%. | ||||
Address | Lima; Perú; November 2016 | ||||
Corporate Author | Thesis | ||||
Publisher | Place of Publication | Editor | |||
Language | Summary Language | Original Title | |||
Series Editor | Series Title | Abbreviated Series Title | LNCS | ||
Series Volume | Series Issue | Edition | |||
ISSN | ISBN | Medium | |||
Area | Expedition | Conference | CIARP | ||
Notes | ADAS; 600.086 | Approved | no | ||
Call Number | Admin @ si @ CRS2016 | Serial | 2913 | ||
Permanent link to this record | |||||
Author | Albert Berenguel; Oriol Ramos Terrades; Josep Llados; Cristina Cañero | ||||
Title | Banknote counterfeit detection through background texture printing analysis | Type | Conference Article | ||
Year | 2016 | Publication | 12th IAPR Workshop on Document Analysis Systems | Abbreviated Journal | |
Volume ![]() |
Issue | Pages | |||
Keywords | |||||
Abstract | This paper is focused on the detection of counterfeit photocopy banknotes. The main difficulty is to work on a real industrial scenario without any constraint about the acquisition device and with a single image. The main contributions of this paper are twofold: first the adaptation and performance evaluation of existing approaches to classify the genuine and photocopy banknotes using background texture printing analysis, which have not been applied into this context before. Second, a new dataset of Euro banknotes images acquired with several cameras under different luminance conditions to evaluate these methods. Experiments on the proposed algorithms show that mixing SIFT features and sparse coding dictionaries achieves quasi perfect classification using a linear SVM with the created dataset. Approaches using dictionaries to cover all possible texture variations have demonstrated to be robust and outperform the state-of-the-art methods using the proposed benchmark. | ||||
Address | Rumania; May 2016 | ||||
Corporate Author | Thesis | ||||
Publisher | Place of Publication | Editor | |||
Language | Summary Language | Original Title | |||
Series Editor | Series Title | Abbreviated Series Title | |||
Series Volume | Series Issue | Edition | |||
ISSN | ISBN | Medium | |||
Area | Expedition | Conference | DAS | ||
Notes | DAG; 600.061; 601.269; 600.097 | Approved | no | ||
Call Number | Admin @ si @ BRL2016 | Serial | 2950 | ||
Permanent link to this record | |||||
Author | Lluis Gomez; Y. Patel; Marçal Rusiñol; C.V. Jawahar; Dimosthenis Karatzas | ||||
Title | Self‐supervised learning of visual features through embedding images into text topic spaces | Type | Conference Article | ||
Year | 2017 | Publication | 30th IEEE Conference on Computer Vision and Pattern Recognition | Abbreviated Journal | |
Volume ![]() |
Issue | Pages | |||
Keywords | |||||
Abstract | End-to-end training from scratch of current deep architectures for new computer vision problems would require Imagenet-scale datasets, and this is not always possible. In this paper we present a method that is able to take advantage of freely available multi-modal content to train computer vision algorithms without human supervision. We put forward the idea of performing self-supervised learning of visual features by mining a large scale corpus of multi-modal (text and image) documents. We show that discriminative visual features can be learnt efficiently by training a CNN to predict the semantic context in which a particular image is more probable to appear as an illustration. For this we leverage the hidden semantic structures discovered in the text corpus with a well-known topic modeling technique. Our experiments demonstrate state of the art performance in image classification, object detection, and multi-modal retrieval compared to recent self-supervised or natural-supervised approaches. | ||||
Address | Honolulu; Hawaii; July 2017 | ||||
Corporate Author | Thesis | ||||
Publisher | Place of Publication | Editor | |||
Language | Summary Language | Original Title | |||
Series Editor | Series Title | Abbreviated Series Title | |||
Series Volume | Series Issue | Edition | |||
ISSN | ISBN | Medium | |||
Area | Expedition | Conference | CVPR | ||
Notes | DAG; 600.084; 600.121 | Approved | no | ||
Call Number | Admin @ si @ GPR2017 | Serial | 2889 | ||
Permanent link to this record | |||||
Author | Lluis Gomez | ||||
Title | Exploiting Similarity Hierarchies for Multi-script Scene Text Understanding | Type | Book Whole | ||
Year | 2016 | Publication | PhD Thesis, Universitat Autonoma de Barcelona-CVC | Abbreviated Journal | |
Volume ![]() |
Issue | Pages | |||
Keywords | |||||
Abstract | This thesis addresses the problem of automatic scene text understanding in unconstrained conditions. In particular, we tackle the tasks of multi-language and arbitrary-oriented text detection, tracking, and script identification in natural scenes.
For this we have developed a set of generic methods that build on top of the basic observation that text has always certain key visual and structural characteristics that are independent of the language or script in which it is written. Text instances in any language or script are always formed as groups of similar atomic parts, being them either individual characters, small stroke parts, or even whole words in the case of cursive text. This holistic (sumof-parts) and recursive perspective has lead us to explore different variants of the “segmentation and grouping” paradigm of computer vision. Scene text detection methodologies are usually based in classification of individual regions or patches, using a priory knowledge for a given script or language. Human perception of text, on the other hand, is based on perceptual organization through which text emerges as a perceptually significant group of atomic objects. In this thesis, we argue that the text detection problem must be posed as the detection of meaningful groups of regions. We address the problem of text detection in natural scenes from a hierarchical perspective, making explicit use of the recursive nature of text, aiming directly to the detection of region groupings corresponding to text within a hierarchy produced by an agglomerative similarity clustering process over individual regions. We propose an optimal way to construct such an hierarchy introducing a feature space designed to produce text group hypothese with high recall and a novel stopping rule combining a discriminative classifier and a probabilistic measure of group meaningfulness based in perceptual organization. Within this generic framework, we design a text-specific object proposals algorithm that, contrary to existing generic object proposals methods, aims directly to the detection of text regions groupings. For this, we abandon the rigid definition of “what is text” of traditional specialized text detectors, and move towards more fuzzy perspective of grouping-based object proposals methods. Then, we present a hybrid algorithm for detection and tracking of scene text where the notion of region groupings plays also a central role. By leveraging the structural arrangement of text group components between consecutive frames we can improve the overall tracking performance of the system. Finally, since our generic detection framework is inherently designed for multi-language environments, we focus on the problem of script identification in order to build a multi-language end-toend reading system. Facing this problem with state of the art CNN classifiers is not straightforward, as they fail to address a key characteristic of scene text instances: their extremely variable aspect ratio. Instead of resizing input images to a fixed size as in the typical use of holistic CNN classifiers, we propose a patch-based classification framework in order to preserve discriminative parts of the image that are characteristic of its class. We describe a novel method based on the use of ensembles of conjoined networks to jointly learn discriminative stroke-parts representations and their relative importance in a patch-based classification scheme. |
||||
Address | |||||
Corporate Author | Thesis | Ph.D. thesis | |||
Publisher | Place of Publication | Editor | Dimosthenis Karatzas | ||
Language | Summary Language | Original Title | |||
Series Editor | Series Title | Abbreviated Series Title | |||
Series Volume | Series Issue | Edition | |||
ISSN | ISBN | Medium | |||
Area | Expedition | Conference | |||
Notes | DAG | Approved | no | ||
Call Number | Admin @ si @ Gom2016 | Serial | 2891 | ||
Permanent link to this record |