Partha Pratim Roy, Umapada Pal, & Josep Llados. (2010). Touching Text Character Localization in Graphical Documents using SIFT. In Graphics Recognition. Achievements, Challenges, and Evolution. 8th International Workshop, GREC 2009. Selected Papers (Vol. 6020, pp. 199–211). LNCS. Springer Berlin Heidelberg.
Abstract: Interpretation of graphical document images is a challenging task as it requires proper understanding of text/graphics symbols present in such documents. Difficulties arise in graphical document recognition when text and symbol overlapped/touched. Intersection of text and symbols with graphical lines and curves occur frequently in graphical documents and hence separation of such symbols is very difficult.
Several pattern recognition and classification techniques exist to recognize isolated text/symbol. But, the touching/overlapping text and symbol recognition has not yet been dealt successfully. An interesting technique, Scale Invariant Feature Transform (SIFT), originally devised for object recognition can take care of overlapping problems. Even if SIFT features have emerged as a very powerful object descriptors, their employment in graphical documents context has not been investigated much. In this paper we present the adaptation of the SIFT approach in the context of text character localization (spotting) in graphical documents. We evaluate the applicability of this technique in such documents and discuss the scope of improvement by combining some state-of-the-art approaches.
Keywords: Support Vector Machine; Text Component; Graphical Line; Document Image; Scale Invariant Feature Transform
|
Christophe Rigaud, Clement Guerin, Dimosthenis Karatzas, Jean-Christophe Burie, & Jean-Marc Ogier. (2015). Knowledge-driven understanding of images in comic books. IJDAR - International Journal on Document Analysis and Recognition, 18(3), 199–221.
Abstract: Document analysis is an active field of research, which can attain a complete understanding of the semantics of a given document. One example of the document understanding process is enabling a computer to identify the key elements of a comic book story and arrange them according to a predefined domain knowledge. In this study, we propose a knowledge-driven system that can interact with bottom-up and top-down information to progressively understand the content of a document. We model the comic book’s and the image processing domains knowledge for information consistency analysis. In addition, different image processing methods are improved or developed to extract panels, balloons, tails, texts, comic characters and their semantic relations in an unsupervised way.
Keywords: Document Understanding; comics analysis; expert system
|
Adarsh Tiwari, Sanket Biswas, & Josep Llados. (2023). Can Pre-trained Language Models Help in Understanding Handwritten Symbols? In 17th International Conference on Document Analysis and Recognition (Vol. 14193, 199–211).
Abstract: The emergence of transformer models like BERT, GPT-2, GPT-3, RoBERTa, T5 for natural language understanding tasks has opened the floodgates towards solving a wide array of machine learning tasks in other modalities like images, audio, music, sketches and so on. These language models are domain-agnostic and as a result could be applied to 1-D sequences of any kind. However, the key challenge lies in bridging the modality gap so that they could generate strong features beneficial for out-of-domain tasks. This work focuses on leveraging the power of such pre-trained language models and discusses the challenges in predicting challenging handwritten symbols and alphabets.
|
|
David Rotger, Petia Radeva, E Fernandez-Nofrerias, & J. Mauri. (2007). Blood Detection In IVUS Longitudinal Cuts Using AdaBoost With a Novel Feature Stability Criterion. In Artificial Intelligence Research and Development. Proceedings of the 10th International Conference of the ACIA (Vol. 163, 197–204).
|
Olivier Penacchio, & C. Alejandro Parraga. (2011). What is the best criterion for an efficient design of retinal photoreceptor mosaics? PER - Perception, 40, 197.
Abstract: The proportions of L, M and S photoreceptors in the primate retina are arguably determined by evolutionary pressure and the statistics of the visual environment. Two information theory-based approaches have been recently proposed for explaining the asymmetrical spatial densities of photoreceptors in humans. In the first approach Garrigan et al (2010 PLoS ONE 6 e1000677), a model for computing the information transmitted by cone arrays which considers the differential blurring produced by the long-wavelength accommodation of the eye’s lens is proposed. Their results explain the sparsity of S-cones but the optimum depends weakly on the L:M cone ratio. In the second approach (Penacchio et al, 2010 Perception 39 ECVP Supplement, 101), we show that human cone arrays make the visual representation scale-invariant, allowing the total entropy of the signal to be preserved while decreasing individual neurons’ entropy in further retinotopic representations. This criterion provides a thorough description of the distribution of L:M cone ratios and does not depend on differential blurring of the signal by the lens. Here, we investigate the similarities and differences of both approaches when applied to the same database. Our results support a 2-criteria optimization in the space of cone ratios whose components are arguably important and mostly unrelated.
[This work was partially funded by projects TIN2010-21771-C02-1 and Consolider-Ingenio 2010-CSD2007-00018 from the Spanish MICINN. CAP was funded by grant RYC-2007-00484]
|
|
Eloi Puertas, Sergio Escalera, & Oriol Pujol. (2011). Multi-Class Multi-Scale Stacked Sequential Learning. In Carlo Sansone, Josef Kittler, & Fabio Roli (Eds.), 10th International Conference on Multiple Classifier Systems (Vol. 6713, pp. 197–206). Springer.
|
Jordi Roca, C. Alejandro Parraga, & Maria Vanrell. (2011). Categorical Focal Colours are Structurally Invariant Under Illuminant Changes. In European Conference on Visual Perception (196). Perception 40.
Abstract: The visual system perceives the colour of surfaces approximately constant under changes of illumination. In this work, we investigate how stable is the perception of categorical \“focal\” colours and their interrelations with varying illuminants and simple chromatic backgrounds. It has been proposed that best examples of colour categories across languages cluster in small regions of the colour space and are restricted to a set of 11 basic terms (Kay and Regier, 2003 Proceedings of the National Academy of Sciences of the USA 100 9085\–9089). Following this, we developed a psychophysical paradigm that exploits the ability of subjects to reliably reproduce the most representative examples of each category, adjusting multiple test patches embedded in a coloured Mondrian. The experiment was run on a CRT monitor (inside a dark room) under various simulated illuminants. We modelled the recorded data for each subject and adapted state as a 3D interconnected structure (graph) in Lab space. The graph nodes were the subject\’s focal colours at each adaptation state. The model allowed us to get a better distance measure between focal structures under different illuminants. We found that perceptual focal structures tend to be preserved better than the structures of the physical \“ideal\” colours under illuminant changes.
|
Zhengying Liu, Zhen Xu, Sergio Escalera, Isabelle Guyon, Julio C. S. Jacques Junior, Meysam Madadi, et al. (2020). Towards automated computer vision: analysis of the AutoCV challenges 2019. PRL - Pattern Recognition Letters, 135, 196–203.
Abstract: We present the results of recent challenges in Automated Computer Vision (AutoCV, renamed here for clarity AutoCV1 and AutoCV2, 2019), which are part of a series of challenge on Automated Deep Learning (AutoDL). These two competitions aim at searching for fully automated solutions for classification tasks in computer vision, with an emphasis on any-time performance. The first competition was limited to image classification while the second one included both images and videos. Our design imposed to the participants to submit their code on a challenge platform for blind testing on five datasets, both for training and testing, without any human intervention whatsoever. Winning solutions adopted deep learning techniques based on already published architectures, such as AutoAugment, MobileNet and ResNet, to reach state-of-the-art performance in the time budget of the challenge (only 20 minutes of GPU time). The novel contributions include strategies to deliver good preliminary results at any time during the learning process, such that a method can be stopped early and still deliver good performance. This feature is key for the adoption of such techniques by data analysts desiring to obtain rapidly preliminary results on large datasets and to speed up the development process. The soundness of our design was verified in several aspects: (1) Little overfitting of the on-line leaderboard providing feedback on 5 development datasets was observed, compared to the final blind testing on the 5 (separate) final test datasets, suggesting that winning solutions might generalize to other computer vision classification tasks; (2) Error bars on the winners’ performance allow us to say with confident that they performed significantly better than the baseline solutions we provided; (3) The ranking of participants according to the any-time metric we designed, namely the Area under the Learning Curve, was different from that of the fixed-time metric, i.e. AUC at the end of the fixed time budget. We released all winning solutions under open-source licenses. At the end of the AutoDL challenge series, all data of the challenge will be made publicly available, thus providing a collection of uniformly formatted datasets, which can serve to conduct further research, particularly on meta-learning.
Keywords: Computer vision; AutoML; Deep learning
|
|
Josep Llados, & Enric Marti. (1999). A graph-edit algorithm for hand-drawn graphical document recognition and their automatic introduction into CAD systems. Machine Graphics & Vision, 8, 195–211.
|
Andreas Fischer, Ching Y. Suen, Volkmar Frinken, Kaspar Riesen, & Horst Bunke. (2013). A Fast Matching Algorithm for Graph-Based Handwriting Recognition. In 9th IAPR – TC15 Workshop on Graph-based Representation in Pattern Recognition (Vol. 7877, pp. 194–203). LNCS. Springer Berlin Heidelberg.
Abstract: The recognition of unconstrained handwriting images is usually based on vectorial representation and statistical classification. Despite their high representational power, graphs are rarely used in this field due to a lack of efficient graph-based recognition methods. Recently, graph similarity features have been proposed to bridge the gap between structural representation and statistical classification by means of vector space embedding. This approach has shown a high performance in terms of accuracy but had shortcomings in terms of computational speed. The time complexity of the Hungarian algorithm that is used to approximate the edit distance between two handwriting graphs is demanding for a real-world scenario. In this paper, we propose a faster graph matching algorithm which is derived from the Hausdorff distance. On the historical Parzival database it is demonstrated that the proposed method achieves a speedup factor of 12.9 without significant loss in recognition accuracy.
|
Eloi Puertas, Sergio Escalera, & Oriol Pujol. (2010). Classifying Objects at Different Sizes with Multi-Scale Stacked Sequential Learning. In J. Aguilar A. M. R. Alquezar (Ed.), 13th International Conference of the Catalan Association for Artificial Intelligence (Vol. 220, 193–200).
Abstract: Sequential learning is that discipline of machine learning that deals with dependent data. In this paper, we use the Multi-scale Stacked Sequential Learning approach (MSSL) to solve the task of pixel-wise classification based on contextual information. The main contribution of this work is a shifting technique applied during the testing phase that makes possible, thanks to template images, to classify objects at different sizes. The results show that the proposed method robustly classifies such objects capturing their spatial relationships.
|
Ernest Valveny, & Enric Marti. (2000). Deformable Template Matching within a Bayesian Framework for Hand-Written Graphic Symbol Recognition. Graphics Recognition Recent Advances, 1941, 193–208.
Abstract: We describe a method for hand-drawn symbol recognition based on deformable template matching able to handle uncertainty and imprecision inherent to hand-drawing. Symbols are represented as a set of straight lines and their deformations as geometric transformations of these lines. Matching, however, is done over the original binary image to avoid loss of information during line detection. It is defined as an energy minimization problem, using a Bayesian framework which allows to combine fidelity to ideal shape of the symbol and flexibility to modify the symbol in order to get the best fit to the binary input image. Prior to matching, we find the best global transformation of the symbol to start the recognition process, based on the distance between symbol lines and image lines. We have applied this method to the recognition of dimensions and symbols in architectural floor plans and we show its flexibility to recognize distorted symbols.
|
Petia Radeva, A.Amini, J.Huang, & Enric Marti. (1996). Deformable B-Solids and Implicit Snakes for Localization and Tracking of SPAMM MRI-Data. In Workshop on Mathematical Methods in Biomedical Image Analysis (pp. 192–201). IEEE Computer Society.
Abstract: To date, MRI-SPAMM data from different image slices have been analyzed independently. In this paper, we propose an approach for 3D tag localization and tracking of SPAMM data by a novel deformable B-solid. The solid is defined in terms of a 3D tensor product B-spline. The isoparametric curves of the B-spline solid have special importance. These are termed implicit snakes as they deform under image forces from tag lines in different image slices. The localization and tracking of tag lines is performed under constraints of continuity and smoothness of the B-solid. The framework unifies the problems of localization, and displacement fitting and interpolation into the same procedure utilizing B-spline bases for interpolation. To track motion from boundaries and restrict image forces to the myocardium, a volumetric model is employed as a pair of coupled endocardial and epicardial B-spline surfaces. To recover deformations in the LV an energy-minimization problem is posed where both tag and ...
|
Frederic Sampedro, Sergio Escalera, Anna Domenech, & Ignasi Carrio. (2015). Automatic Tumor Volume Segmentation in Whole-Body PET/CT Scans: A Supervised Learning Approach Source. JMIHI - Journal of Medical Imaging and Health Informatics, 5(2), 192–201.
Abstract: Whole-body 3D PET/CT tumoral volume segmentation provides relevant diagnostic and prognostic information in clinical oncology and nuclear medicine. Carrying out this procedure manually by a medical expert is time consuming and suffers from inter- and intra-observer variabilities. In this paper, a completely automatic approach to this task is presented. First, the problem is stated and described both in clinical and technological terms. Then, a novel supervised learning segmentation framework is introduced. The segmentation by learning approach is defined within a Cascade of Adaboost classifiers and a 3D contextual proposal of Multiscale Stacked Sequential Learning. Segmentation accuracy results on 200 Breast Cancer whole body PET/CT volumes show mean 49% sensitivity, 99.993% specificity and 39% Jaccard overlap Index, which represent good performance results both at the clinical and technological level.
Keywords: CONTEXTUAL CLASSIFICATION; PET/CT; SUPERVISED LEARNING; TUMOR SEGMENTATION; WHOLE BODY
|
|
R. Clariso, David Masip, & A. Rius. (2014). Student projects empowering mobile learning in higher education. RUSC - Revista de Universidad y Sociedad del Conocimiento, 192–207.
|
