|
Marwa Dhiaf and 6 others. 2023. CSSL-MHTR: Continual Self-Supervised Learning for Scalable Multi-script Handwritten Text Recognition.
Abstract: Self-supervised learning has recently emerged as a strong alternative in document analysis. These approaches are now capable of learning high-quality image representations and overcoming the limitations of supervised methods, which require a large amount of labeled data. However, these methods are unable to capture new knowledge in an incremental fashion, where data is presented to the model sequentially, which is closer to the realistic scenario. In this paper, we explore the potential of continual self-supervised learning to alleviate the catastrophic forgetting problem in handwritten text recognition, as an example of sequence recognition. Our method consists in adding intermediate layers called adapters for each task, and efficiently distilling knowledge from the previous model while learning the current task. Our proposed framework is efficient in both computation and memory complexity. To demonstrate its effectiveness, we evaluate our method by transferring the learned model to diverse text recognition downstream tasks, including Latin and non-Latin scripts. As far as we know, this is the first application of continual self-supervised learning for handwritten text recognition. We attain state-of-the-art performance on English, Italian and Russian scripts, whilst adding only a few parameters per task. The code and trained models will be publicly available.
|
|
|
Souhail Bakkali and 6 others. 2023. TransferDoc: A Self-Supervised Transferable Document Representation Learning Model Unifying Vision and Language.
Abstract: The field of visual document understanding has witnessed a rapid growth in emerging challenges and powerful multi-modal strategies. However, they rely on an extensive amount of document data to learn their pretext objectives in a ``pre-train-then-fine-tune'' paradigm and thus, suffer a significant performance drop in real-world online industrial settings. One major reason is the over-reliance on OCR engines to extract local positional information within a document page. Therefore, this hinders the model's generalizability, flexibility and robustness due to the lack of capturing global information within a document image. We introduce TransferDoc, a cross-modal transformer-based architecture pre-trained in a self-supervised fashion using three novel pretext objectives. TransferDoc learns richer semantic concepts by unifying language and visual representations, which enables the production of more transferable models. Besides, two novel downstream tasks have been introduced for a ``closer-to-real'' industrial evaluation scenario where TransferDoc outperforms other state-of-the-art approaches.
|
|
|
Antonio Lopez, Ernest Valveny and Juan J. Villanueva. 2005. Real-time quality control of surgical material packaging by artificial vision. Assembly Automation, 25(3).
|
|
|
Fernando Vilariño. 2019. 3D Scanning of Capitals at Library Living Lab.
|
|
|
Oriol Ramos Terrades, Albert Berenguel and Debora Gil. 2022. A Flexible Outlier Detector Based on a Topology Given by Graph Communities. BDR, 29, 100332.
Abstract: Outlier detection is essential for optimal performance of machine learning methods and statistical predictive models. Their detection is especially determinant in small sample size unbalanced problems, since in such settings outliers become highly influential and significantly bias models. This particular experimental settings are usual in medical applications, like diagnosis of rare pathologies, outcome of experimental personalized treatments or pandemic emergencies. In contrast to population-based methods, neighborhood based local approaches compute an outlier score from the neighbors of each sample, are simple flexible methods that have the potential to perform well in small sample size unbalanced problems. A main concern of local approaches is the impact that the computation of each sample neighborhood has on the method performance. Most approaches use a distance in the feature space to define a single neighborhood that requires careful selection of several parameters, like the number of neighbors.
This work presents a local approach based on a local measure of the heterogeneity of sample labels in the feature space considered as a topological manifold. Topology is computed using the communities of a weighted graph codifying mutual nearest neighbors in the feature space. This way, we provide with a set of multiple neighborhoods able to describe the structure of complex spaces without parameter fine tuning. The extensive experiments on real-world and synthetic data sets show that our approach outperforms, both, local and global strategies in multi and single view settings.
Keywords: Classification algorithms; Detection algorithms; Description of feature space local structure; Graph communities; Machine learning algorithms; Outlier detectors
|
|
|
Marçal Rusiñol, Lluis Gomez, A. Landman, M. Silva Constenla and Dimosthenis Karatzas. 2019. Automatic Structured Text Reading for License Plates and Utility Meters. BMVC Workshop on Visual Artificial Intelligence and Entrepreneurship.
Abstract: Reading text in images has attracted interest from computer vision researchers for
many years. Our technology focuses on the extraction of structured text – such as serial
numbers, machine readings, product codes, etc. – so that it is able to center its attention just on the relevant textual elements. It is conceived to work in an end-to-end fashion, bypassing any explicit text segmentation stage. In this paper we present two different industrial use cases where we have applied our automatic structured text reading technology. In the first one, we demonstrate an outstanding performance when reading license plates compared to the current state of the art. In the second one, we present results on our solution for reading utility meters. The technology is commercialized by a recently created spin-off company, and both solutions are at different stages of integration with final clients.
|
|
|
Joan M. Nuñez, Jorge Bernal, Miquel Ferrer and Fernando Vilariño. 2014. Impact of Keypoint Detection on Graph-based Characterization of Blood Vessels in Colonoscopy Videos. CARE workshop.
Abstract: We explore the potential of the use of blood vessels as anatomical landmarks for developing image registration methods in colonoscopy images. An unequivocal representation of blood vessels could be used to guide follow-up methods to track lesions over different interventions. We propose a graph-based representation to characterize network structures, such as blood vessels, based on the use of intersections and endpoints. We present a study consisting of the assessment of the minimal performance a keypoint detector should achieve so that the structure can still be recognized. Experimental results prove that, even by achieving a loss of 35% of the keypoints, the descriptive power of the associated graphs to the vessel pattern is still high enough to recognize blood vessels.
Keywords: Colonoscopy; Graph Matching; Biometrics; Vessel; Intersection
|
|
|
Chenyang Fu, Kaida Xiao, Dimosthenis Karatzas and Sophie Wuerger. 2011. Investigation of Unique Hue Setting Changes with Ageing. COL, 9(5), 053301-5.
Abstract: Clromatic sensitivity along the protan, deutan, and tritan lines and the loci of the unique hues (red, green, yellow, blue) for a very large sample (n = 185) of colour-normal observers ranging from 18 to 75 years of age are assessed. Visual judgments are obtained under normal viewing conditions using colour patches on self-luminous display under controlled adaptation conditions. Trivector discrimination thresholds show an increase as a function of age along the protan, deutan, and tritan axes, with the largest increase present along the tritan line, less pronounced shifts in unique hue settings are also observed. Based on the chromatic (protan, deutan, tritan) thresholds and using scaled cone signals, we predict the unique hue changes with ageing. A dependency on age for unique red and unique yellow for predicted hue angle is found. We conclude that the chromatic sensitivity deteriorates significantly with age, whereas the appearance of unique hues is much less affected, remaining almost constant despite the known changes in the ocular media.
|
|
|
Antonio Clavelli, Dimosthenis Karatzas, Josep Llados, Mario Ferraro and Giuseppe Boccignone. 2014. Modelling task-dependent eye guidance to objects in pictures. CoCom, 6(3), 558–584.
Abstract: 5Y Impact Factor: 1.14 / 3rd (Computer Science, Artificial Intelligence)
We introduce a model of attentional eye guidance based on the rationale that the deployment of gaze is to be considered in the context of a general action-perception loop relying on two strictly intertwined processes: sensory processing, depending on current gaze position, identifies sources of information that are most valuable under the given task; motor processing links such information with the oculomotor act by sampling the next gaze position and thus performing the gaze shift. In such a framework, the choice of where to look next is task-dependent and oriented to classes of objects embedded within pictures of complex scenes. The dependence on task is taken into account by exploiting the value and the payoff of gazing at certain image patches or proto-objects that provide a sparse representation of the scene objects. The different levels of the action-perception loop are represented in probabilistic form and eventually give rise to a stochastic process that generates the gaze sequence. This way the model also accounts for statistical properties of gaze shifts such as individual scan path variability. Results of the simulations are compared either with experimental data derived from publicly available datasets and from our own experiments.
Keywords: Visual attention; Gaze guidance; Value; Payoff; Stochastic fixation prediction
|
|
|
Herve Locteau, Sebastien Mace, Ernest Valveny and Salvatore Tabbone. 2010. Extraction des pieces de un plan de habitation. Colloque Internacional Francophone de l´Ecrit et le Document.1–12.
Abstract: In this article, a method to extract the rooms of an architectural floor plan image is described. We first present a line detection algorithm to extract long lines in the image. Those lines are analyzed to identify the existing walls. From this point, room extraction can be seen as a classical segmentation task for which each region corresponds to a room. The chosen resolution strategy consists in recursively decomposing the image until getting nearly convex regions. The notion of convexity is difficult to quantify, and the selection of separation lines can also be rough. Thus, we take advantage of knowledge associated to architectural floor plans in order to obtain mainly rectangular rooms. Preliminary tests on a set of real documents show promising results.
|
|