|
Antonio Lopez, Ricardo Toledo, Joan Serrat, & Juan J. Villanueva. (1999). Extraction of vessel centerlines from 2D coronary angiographies.
|
Herve Locteau, Sebastien Mace, Ernest Valveny, & Salvatore Tabbone. (2010). Extraction des pieces de un plan de habitation. In 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.
|
|
J.R. Serra, & J.B. Subirana. (1996). Extraccion de estructuras interesantes en imagenes.
|
|
G. Tortajada. (2000). Extraccio interactiva de patrocinadors d’anuncis en revistes utilitzant tecniques de Visio per Computador.
|
Katerine Diaz, & Francesc J. Ferri. (2013). Extensiones del método de vectores comunes discriminantes Aplicadas a la clasificación de imágenes.
Abstract: Los métodos basados en subespacios son una herramienta muy utilizada en aplicaciones de visión por computador. Aquí se presentan y validan algunos algoritmos que hemos propuesto en este campo de investigación. El primer algoritmo está relacionado con una extensión del método de vectores comunes discriminantes con kernel, que reinterpreta el espacio nulo de la matriz de dispersión intra-clase del conjunto de entrenamiento para obtener las características discriminantes. Dentro de los métodos basados en subespacios existen diferentes tipos de entrenamiento. Uno de los más populares, pero no por ello uno de los más eficientes, es el aprendizaje por lotes. En este tipo de aprendizaje, todas las muestras del conjunto de entrenamiento tienen que estar disponibles desde el inicio. De este modo, cuando nuevas muestras se ponen a disposición del algoritmo, el sistema tiene que ser reentrenado de nuevo desde cero. Una alternativa a este tipo de entrenamiento es el aprendizaje incremental. Aquí se proponen diferentes algoritmos incrementales del método de vectores comunes discriminantes.
|
Debora Gil, & Petia Radeva. (2005). Extending anisotropic operators to recover smooth shapes. Computer Vision and Image Understanding, 99(1), 110–125.
Abstract: Anisotropic differential operators are widely used in image enhancement processes. Recently, their property of smoothly extending functions to the whole image domain has begun to be exploited. Strong ellipticity of differential operators is a requirement that ensures existence of a unique solution. This condition is too restrictive for operators designed to extend image level sets: their own functionality implies that they should restrict to some vector field. The diffusion tensor that defines the diffusion operator links anisotropic processes with Riemmanian manifolds. In this context, degeneracy implies restricting diffusion to the varieties generated by the vector fields of positive eigenvalues, provided that an integrability condition is satisfied. We will use that any smooth vector field fulfills this integrability requirement to design line connection algorithms for contour completion. As application we present a segmenting strategy that assures convergent snakes whatever the geometry of the object to be modelled is.
Keywords: Contour completion; Functional extension; Differential operators; Riemmanian manifolds; Snake segmentation
|
|
Maria Vanrell. (1997). Exploring the space of behaviour of a texture perception algorithm.
|
Ruben Perez Tito. (2023). Exploring the role of Text in Visual Question Answering on Natural Scenes and Documents (Ernest Valveny, Ed.). Ph.D. thesis, IMPRIMA, .
Abstract: Visual Question Answering (VQA) is the task where given an image and a natural language question, the objective is to generate a natural language answer. At the intersection between computer vision and natural language processing, this task can be seen as a measure of image understanding capabilities, as it requires to reason about objects, actions, colors, positions, the relations between the different elements as well as commonsense reasoning, world knowledge, arithmetic skills and natural language understanding. However, even though the text present in the images conveys important semantically rich information that is explicit and not available in any other form, most VQA methods remained illiterate, largely
ignoring the text despite its potential significance. In this thesis, we set out on a journey to bring reading capabilities to computer vision models applied to the VQA task, creating new datasets and methods that can read, reason and integrate the text with other visual cues in natural scene images and documents.
In Chapter 3, we address the combination of scene text with visual information to fully understand all the nuances of natural scene images. To achieve this objective, we define a new sub-task of VQA that requires reading the text in the image, and highlight the limitations of the current methods. In addition, we propose a new architecture that integrates both modalities and jointly reasons about textual and visual features. In Chapter 5, we shift the domain of VQA with reading capabilities and apply it on scanned industry document images, providing a high-level end-purpose perspective to Document Understanding, which has been
primarily focused on digitizing the document’s contents and extracting key values without considering the ultimate purpose of the extracted information. For this, we create a dataset which requires methods to reason about the unique and challenging elements of documents, such as text, images, tables, graphs and complex layouts, to provide accurate answers in natural language. However, we observed that explicit visual features provide a slight contribution in the overall performance, since the main information is usually conveyed within the text and its position. In consequence, in Chapter 6, we propose VQA on infographic images, seeking for document images with more visually rich elements that require to fully exploit visual information in order to answer the questions. We show the performance gap of
different methods when used over industry scanned and infographic images, and propose a new method that integrates the visual features in early stages, which allows the transformer architecture to exploit the visual features during the self-attention operation. Instead, in Chapter 7, we apply VQA on a big collection of single-page documents, where the methods must find which documents are relevant to answer the question, and provide the answer itself. Finally, in Chapter 8, mimicking real-world application problems where systems must process documents with multiple pages, we address the multipage document visual question answering task. We demonstrate the limitations of existing methods, including models specifically designed to process long sequences. To overcome these limitations, we propose
a hierarchical architecture that can process long documents, answer questions, and provide the index of the page where the information to answer the question is located as an explainability measure.
|
Felipe Codevilla, Eder Santana, Antonio Lopez, & Adrien Gaidon. (2019). Exploring the Limitations of Behavior Cloning for Autonomous Driving. In 18th IEEE International Conference on Computer Vision (pp. 9328–9337).
Abstract: Driving requires reacting to a wide variety of complex environment conditions and agent behaviors. Explicitly modeling each possible scenario is unrealistic. In contrast, imitation learning can, in theory, leverage data from large fleets of human-driven cars. Behavior cloning in particular has been successfully used to learn simple visuomotor policies end-to-end, but scaling to the full spectrum of driving behaviors remains an unsolved problem. In this paper, we propose a new benchmark to experimentally investigate the scalability and limitations of behavior cloning. We show that behavior cloning leads to state-of-the-art results, executing complex lateral and longitudinal maneuvers, even in unseen environments, without being explicitly programmed to do so. However, we confirm some limitations of the behavior cloning approach: some well-known limitations (eg, dataset bias and overfitting), new generalization issues (eg, dynamic objects and the lack of a causal modeling), and training instabilities, all requiring further research before behavior cloning can graduate to real-world driving. The code, dataset, benchmark, and agent studied in this paper can be found at github.
|
Francesco Brughi, Debora Gil, Llorenç Badiella, Eva Jove Casabella, & Oriol Ramos Terrades. (2014). Exploring the impact of inter-query variability on the performance of retrieval systems. In 11th International Conference on Image Analysis and Recognition (Vol. 8814, 413–420). LNCS. Springer International Publishing.
Abstract: This paper introduces a framework for evaluating the performance of information retrieval systems. Current evaluation metrics provide an average score that does not consider performance variability across the query set. In this manner, conclusions lack of any statistical significance, yielding poor inference to cases outside the query set and possibly unfair comparisons. We propose to apply statistical methods in order to obtain a more informative measure for problems in which different query classes can be identified. In this context, we assess the performance variability on two levels: overall variability across the whole query set and specific query class-related variability. To this end, we estimate confidence bands for precision-recall curves, and we apply ANOVA in order to assess the significance of the performance across different query classes.
|
Ricard Balague. (2014). Exploring the combination of color cues for intrinsic image decomposition (Vol. 178). Master's thesis, , .
Abstract: Intrinsic image decomposition is a challenging problem that consists in separating an image into its physical characteristics: reflectance and shading. This problem can be solved in different ways, but most methods have combined information from several visual cues. In this work we describe an extension of an existing method proposed by Serra et al. which considers two color descriptors and combines them by means of a Markov Random Field. We analyze in depth the weak points of the method and we explore more possibilities to use in both descriptors. The proposed extension depends on the combination of the cues considered to overcome some of the limitations of the original method. Our approach is tested on the MIT dataset and Beigpour et al. dataset, which contain images of real objects acquired under controlled conditions and synthetic images respectively, with their corresponding ground truth.
|
Gloria Fernandez Esparrach, Jorge Bernal, Maria Lopez Ceron, Henry Cordova, Cristina Sanchez Montes, Cristina Rodriguez de Miguel, et al. (2016). Exploring the clinical potential of an automatic colonic polyp detection method based on the creation of energy maps. END - Endoscopy, 48(9), 837–842.
Abstract: Background and aims: Polyp miss-rate is a drawback of colonoscopy that increases significantly in small polyps. We explored the efficacy of an automatic computer vision method for polyp detection.
Methods: Our method relies on a model that defines polyp boundaries as valleys of image intensity. Valley information is integrated into energy maps which represent the likelihood of polyp presence.
Results: In 24 videos containing polyps from routine colonoscopies, all polyps were detected in at least one frame. Mean values of the maximum of energy map were higher in frames with polyps than without (p<0.001). Performance improved in high quality frames (AUC= 0.79, 95%CI: 0.70-0.87 vs 0.75, 95%CI: 0.66-0.83). Using 3.75 as maximum threshold value, sensitivity and specificity for detection of polyps were 70.4% (95%CI: 60.3-80.8) and 72.4% (95%CI: 61.6-84.6), respectively.
Conclusion: Energy maps showed a good performance for colonic polyp detection. This indicates a potential applicability in clinical practice.
|
Roberto Morales, Juan Quispe, & Eduardo Aguilar. (2023). Exploring multi-food detection using deep learning-based algorithms. In 13th International Conference on Pattern Recognition Systems (pp. 1–7).
Abstract: People are becoming increasingly concerned about their diet, whether for disease prevention, medical treatment or other purposes. In meals served in restaurants, schools or public canteens, it is not easy to identify the ingredients and/or the nutritional information they contain. Currently, technological solutions based on deep learning models have facilitated the recording and tracking of food consumed based on the recognition of the main dish present in an image. Considering that sometimes there may be multiple foods served on the same plate, food analysis should be treated as a multi-class object detection problem. EfficientDet and YOLOv5 are object detection algorithms that have demonstrated high mAP and real-time performance on general domain data. However, these models have not been evaluated and compared on public food datasets. Unlike general domain objects, foods have more challenging features inherent in their nature that increase the complexity of detection. In this work, we performed a performance evaluation of Efficient-Det and YOLOv5 on three public food datasets: UNIMIB2016, UECFood256 and ChileanFood64. From the results obtained, it can be seen that YOLOv5 provides a significant difference in terms of both mAP and response time compared to EfficientDet in all datasets. Furthermore, YOLOv5 outperforms the state-of-the-art on UECFood256, achieving an improvement of more than 4% in terms of mAP@.50 over the best reported.
|
|
Ivet Rafegas. (2013). Exploring Low-Level Vision Models. Case Study: Saliency Prediction (Vol. 175). Master's thesis, , .
|
Raul Gomez, Jaume Gibert, Lluis Gomez, & Dimosthenis Karatzas. (2020). Exploring Hate Speech Detection in Multimodal Publications. In IEEE Winter Conference on Applications of Computer Vision.
Abstract: In this work we target the problem of hate speech detection in multimodal publications formed by a text and an image. We gather and annotate a large scale dataset from Twitter, MMHS150K, and propose different models that jointly analyze textual and visual information for hate speech detection, comparing them with unimodal detection. We provide quantitative and qualitative results and analyze the challenges of the proposed task. We find that, even though images are useful for the hate speech detection task, current multimodal models cannot outperform models analyzing only text. We discuss why and open the field and the dataset for further research.
|
