Subhajit Maity, Sanket Biswas, Siladittya Manna, Ayan Banerjee, Josep Llados, Saumik Bhattacharya, et al. (2023). SelfDocSeg: A Self-Supervised vision-based Approach towards Document Segmentation. In 17th International Conference on Doccument Analysis and Recognition (Vol. 14187, 342–360).
Abstract: Document layout analysis is a known problem to the documents research community and has been vastly explored yielding a multitude of solutions ranging from text mining, and recognition to graph-based representation, visual feature extraction, etc. However, most of the existing works have ignored the crucial fact regarding the scarcity of labeled data. With growing internet connectivity to personal life, an enormous amount of documents had been available in the public domain and thus making data annotation a tedious task. We address this challenge using self-supervision and unlike, the few existing self-supervised document segmentation approaches which use text mining and textual labels, we use a complete vision-based approach in pre-training without any ground-truth label or its derivative. Instead, we generate pseudo-layouts from the document images to pre-train an image encoder to learn the document object representation and localization in a self-supervised framework before fine-tuning it with an object detection model. We show that our pipeline sets a new benchmark in this context and performs at par with the existing methods and the supervised counterparts, if not outperforms. The code is made publicly available at: this https URL
|
Jorge Charco, Angel Sappa, & Boris X. Vintimilla. (2022). Human Pose Estimation through a Novel Multi-view Scheme. In 17th International Conference on Computer Vision Theory and Applications (VISAPP 2022) (Vol. 5, pp. 855–862).
Abstract: This paper presents a multi-view scheme to tackle the challenging problem of the self-occlusion in human pose estimation problem. The proposed approach first obtains the human body joints of a set of images, which are captured from different views at the same time. Then, it enhances the obtained joints by using a
multi-view scheme. Basically, the joints from a given view are used to enhance poorly estimated joints from another view, especially intended to tackle the self occlusions cases. A network architecture initially proposed for the monocular case is adapted to be used in the proposed multi-view scheme. Experimental results and
comparisons with the state-of-the-art approaches on Human3.6m dataset are presented showing improvements in the accuracy of body joints estimations.
Keywords: Multi-view Scheme; Human Pose Estimation; Relative Camera Pose; Monocular Approach
|
Rafael E. Rivadeneira, Angel Sappa, & Boris X. Vintimilla. (2022). Multi-Image Super-Resolution for Thermal Images. In 17th International Conference on Computer Vision Theory and Applications (VISAPP 2022) (Vol. 4, pp. 635–642).
Abstract: This paper proposes a novel CNN architecture for the multi-thermal image super-resolution problem. In the proposed scheme, the multi-images are synthetically generated by downsampling and slightly shifting the given image; noise is also added to each of these synthesized images. The proposed architecture uses two
attention blocks paths to extract high-frequency details taking advantage of the large information extracted from multiple images of the same scene. Experimental results are provided, showing the proposed scheme has overcome the state-of-the-art approaches.
Keywords: Thermal Images; Multi-view; Multi-frame; Super-Resolution; Deep Learning; Attention Block
|
Maedeh Aghaei, & Petia Radeva. (2014). Bag-of-Tracklets for Person Tracking in Life-Logging Data. In 17th International Conference of the Catalan Association for Artificial Intelligence (Vol. 269, pp. 35–44).
Abstract: By increasing popularity of wearable cameras, life-logging data analysis is becoming more and more important and useful to derive significant events out of this substantial collection of images. In this study, we introduce a new tracking method applied to visual life-logging, called bag-of-tracklets, which is based on detecting, localizing and tracking of people. Given the low spatial and temporal resolution of the image data, our model generates and groups tracklets in a unsupervised framework and extracts image sequences of person appearance according to a similarity score of the bag-of-tracklets. The model output is a meaningful sequence of events expressing human appearance and tracking them in life-logging data. The achieved results prove the robustness of our model in terms of efficiency and accuracy despite the low spatial and temporal resolution of the data.
|
Agata Lapedriza, David Masip, & D.Sanchez. (2014). Emotions Classification using Facial Action Units Recognition. In 17th International Conference of the Catalan Association for Artificial Intelligence (Vol. 269, pp. 55–64).
Abstract: In this work we build a system for automatic emotion classification from image sequences. We analyze subtle changes in facial expressions by detecting a subset of 12 representative facial action units (AUs). Then, we classify emotions based on the output of these AUs classifiers, i.e. the presence/absence of AUs. We base the AUs classification upon a set of spatio-temporal geometric and appearance features for facial representation, fusing them within the emotion classifier. A decision tree is trained for emotion classifying, making the resulting model easy to interpret by capturing the combination of AUs activation that lead to a particular emotion. For Cohn-Kanade database, the proposed system classifies 7 emotions with a mean accuracy of near 90%, attaining a similar recognition accuracy in comparison with non-interpretable models that are not based in AUs detection.
|
Fernando Barrera, Felipe Lumbreras, & Angel Sappa. (2010). Multimodal Template Matching based on Gradient and Mutual Information using Scale-Space. In 17th IEEE International Conference on Image Processing (2749–2752).
Abstract: This paper presents the combined use of gradient and mutual information for infrared and intensity templates matching. We propose to joint: (i) feature matching in a multiresolution context and (ii) information propagation through scale-space representations. Our method consists in combining mutual information with a shape descriptor based on gradient, and propagate them following a coarse-to-fine strategy. The main contributions of this work are: to offer a theoretical formulation towards a multimodal stereo matching; to show that gradient and mutual information can be reinforced while they are propagated between consecutive levels; and to show that they are valid cost functions in multimodal template matchings. Comparisons are presented showing the improvements and viability of the proposed approach.
|
Mohammad Rouhani, & Angel Sappa. (2010). A Fast accurate Implicit Polynomial Fitting Approach. In 17th IEEE International Conference on Image Processing (1429–1432).
Abstract: This paper presents a novel hybrid approach that combines state of the art fitting algorithms: algebraic-based and geometric-based. It consists of two steps; first, the 3L algorithm is used as an initialization and then, the obtained result, is improved through a geometric approach. The adopted geometric approach is based on a distance estimation that avoids costly search for the real orthogonal distance. Experimental results are presented as well as quantitative comparisons.
|
Marc Masana, Joost Van de Weijer, Luis Herranz, Andrew Bagdanov, & Jose Manuel Alvarez. (2017). Domain-adaptive deep network compression. In 17th IEEE International Conference on Computer Vision.
Abstract: Deep Neural Networks trained on large datasets can be easily transferred to new domains with far fewer labeled examples by a process called fine-tuning. This has the advantage that representations learned in the large source domain can be exploited on smaller target domains. However, networks designed to be optimal for the source task are often prohibitively large for the target task. In this work we address the compression of networks after domain transfer.
We focus on compression algorithms based on low-rank matrix decomposition. Existing methods base compression solely on learned network weights and ignore the statistics of network activations. We show that domain transfer leads to large shifts in network activations and that it is desirable to take this into account when compressing.
We demonstrate that considering activation statistics when compressing weights leads to a rank-constrained regression problem with a closed-form solution. Because our method takes into account the target domain, it can more optimally
remove the redundancy in the weights. Experiments show that our Domain Adaptive Low Rank (DALR) method significantly outperforms existing low-rank compression techniques. With our approach, the fc6 layer of VGG19 can be compressed more than 4x more than using truncated SVD alone – with only a minor or no loss in accuracy. When applied to domain-transferred networks it allows for compression down to only 5-20% of the original number of parameters with only a minor drop in performance.
|
Xialei Liu, Joost Van de Weijer, & Andrew Bagdanov. (2017). RankIQA: Learning from Rankings for No-reference Image Quality Assessment. In 17th IEEE International Conference on Computer Vision.
Abstract: We propose a no-reference image quality assessment (NR-IQA) approach that learns from rankings (RankIQA). To address the problem of limited IQA dataset size, we train a Siamese Network to rank images in terms of image quality by using synthetically generated distortions for which relative image quality is known. These ranked image sets can be automatically generated without laborious human labeling. We then use fine-tuning to transfer the knowledge represented in the trained Siamese Network to a traditional CNN that estimates absolute image quality from single images. We demonstrate how our approach can be made significantly more efficient than traditional Siamese Networks by forward propagating a batch of images through a single network and backpropagating gradients derived from all pairs of images in the batch. Experiments on the TID2013 benchmark show that we improve the state-of-the-art by over 5%. Furthermore, on the LIVE benchmark we show that our approach is superior to existing NR-IQA techniques and that we even outperform the state-of-the-art in full-reference IQA (FR-IQA) methods without having to resort to high-quality reference images to infer IQA.
|
Ekaterina Zaytseva, Santiago Segui, & Jordi Vitria. (2012). Sketchable Histograms of Oriented Gradients for Object Detection. In 17th Iberomerican Conference on Pattern Recognition (Vol. 7441, pp. 374–381). Springer Berlin Heidelberg.
Abstract: In this paper we investigate a new representation approach for visual object recognition. The new representation, called sketchable-HoG, extends the classical histogram of oriented gradients (HoG) feature by adding two different aspects: the stability of the majority orientation and the continuity of gradient orientations. In this way, the sketchable-HoG locally characterizes the complexity of an object model and introduces global structure information while still keeping simplicity, compactness and robustness. We evaluated the proposed image descriptor on publicly Catltech 101 dataset. The obtained results outperforms classical HoG descriptor as well as other reported descriptors in the literature.
|
Onur Ferhat, & Fernando Vilariño. (2013). A Cheap Portable Eye-Tracker Solution for Common Setups. In 17th European Conference on Eye Movements.
Abstract: We analyze the feasibility of a cheap eye-tracker where the hardware consists of a single webcam and a Raspberry Pi device. Our aim is to discover the limits of such a system and to see whether it provides an acceptable performance. We base our work on the open source Opengazer (Zielinski, 2013) and we propose several improvements to create a robust, real-time system. After assessing the accuracy of our eye-tracker in elaborated experiments involving 18 subjects under 4 different system setups, we developed a simple game to see how it performs in practice and we also installed it on a Raspberry Pi to create a portable stand-alone eye-tracker which achieves 1.62° horizontal accuracy with 3 fps refresh rate for a building cost of 70 Euros.
Keywords: Low cost; eye-tracker; software; webcam; Raspberry Pi
|
Andrea Gemelli, Sanket Biswas, Enrico Civitelli, Josep Llados, & Simone Marinai. (2022). Doc2Graph: A Task Agnostic Document Understanding Framework Based on Graph Neural Networks. In 17th European Conference on Computer Vision Workshops (Vol. 13804, 329–344). LNCS.
Abstract: Geometric Deep Learning has recently attracted significant interest in a wide range of machine learning fields, including document analysis. The application of Graph Neural Networks (GNNs) has become crucial in various document-related tasks since they can unravel important structural patterns, fundamental in key information extraction processes. Previous works in the literature propose task-driven models and do not take into account the full power of graphs. We propose Doc2Graph, a task-agnostic document understanding framework based on a GNN model, to solve different tasks given different types of documents. We evaluated our approach on two challenging datasets for key information extraction in form understanding, invoice layout analysis and table detection.
|
Oriol Ramos Terrades, N. Serrano, Albert Gordo, Ernest Valveny, & Alfons Juan-Ciscar. (2010). Interactive-predictive detection of handwritten text blocks. In 17th Document Recognition and Retrieval Conference, part of the IS&T-SPIE Electronic Imaging Symposium (Vol. 7534, 75340Q–75340Q–10).
Abstract: A method for text block detection is introduced for old handwritten documents. The proposed method takes advantage of sequential book structure, taking into account layout information from pages previously transcribed. This glance at the past is used to predict the position of text blocks in the current page with the help of conventional layout analysis methods. The method is integrated into the GIDOC prototype: a first attempt to provide integrated support for interactive-predictive page layout analysis, text line detection and handwritten text transcription. Results are given in a transcription task on a 764-page Spanish manuscript from 1891.
|
Olivier Lefebvre, Pau Riba, Charles Fournier, Alicia Fornes, Josep Llados, Rejean Plamondon, et al. (2015). Monitoring neuromotricity on-line: a cloud computing approach. In 17th Conference of the International Graphonomics Society IGS2015.
Abstract: The goal of our experiment is to develop a useful and accessible tool that can be used to evaluate a patient's health by analyzing handwritten strokes. We use a cloud computing approach to analyze stroke data sampled on a commercial tablet working on the Android platform and a distant server to perform complex calculations using the Delta and Sigma lognormal algorithms. A Google Drive account is used to store the data and to ease the development of the project. The communication between the tablet, the cloud and the server is encrypted to ensure biomedical information confidentiality. Highly parameterized biomedical tests are implemented on the tablet as well as a free drawing test to evaluate the validity of the data acquired by the first test compared to the second one. A blurred shape model descriptor pattern recognition algorithm is used to classify the data obtained by the free drawing test. The functions presented in this paper are still currently under development and other improvements are needed before launching the application in the public domain.
|
Mohammad Ali Bagheri, Qigang Gao, & Sergio Escalera. (2012). Error Correcting Output Codes for multiclass classification: Application to two image vision problems. In 16th symposium on Artificial Intelligence & Signal Processing (pp. 508–513). IEEE Xplore.
Abstract: Error-correcting output codes (ECOC) represents a powerful framework to deal with multiclass classification problems based on combining binary classifiers. The key factor affecting the performance of ECOC methods is the independence of binary classifiers, without which the ECOC method would be ineffective. In spite of its ability on classification of problems with relatively large number of classes, it has been applied in few real world problems. In this paper, we investigate the behavior of the ECOC approach on two image vision problems: logo recognition and shape classification using Decision Tree and AdaBoost as the base learners. The results show that the ECOC method can be used to improve the classification performance in comparison with the classical multiclass approaches.
|
