|
|
Patricia Suarez, Dario Carpio, & Angel Sappa. (2021). Non-homogeneous Haze Removal Through a Multiple Attention Module Architecture. In 16th International Symposium on Visual Computing (Vol. 13018, 178–190). LNCS.
Abstract: This paper presents a novel attention based architecture to remove non-homogeneous haze. The proposed model is focused on obtaining the most representative characteristics of the image, at each learning cycle, by means of adaptive attention modules coupled with a residual learning convolutional network. The latter is based on the Res2Net model. The proposed architecture is trained with just a few set of images. Its performance is evaluated on a public benchmark—images from the non-homogeneous haze NTIRE 2021 challenge—and compared with state of the art approaches reaching the best result.
|
|
|
|
Esmitt Ramirez, Carles Sanchez, Agnes Borras, Marta Diez-Ferrer, Antoni Rosell, & Debora Gil. (2018). BronchoX: bronchoscopy exploration software for biopsy intervention planning. HTL - Healthcare Technology Letters, 177–182.
Abstract: Virtual bronchoscopy (VB) is a non-invasive exploration tool for intervention planning and navigation of possible pulmonary lesions (PLs). A VB software involves the location of a PL and the calculation of a route, starting from the trachea, to reach it. The selection of a VB software might be a complex process, and there is no consensus in the community of medical software developers in which is the best-suited system to use or framework to choose. The authors present Bronchoscopy Exploration (BronchoX), a VB software to plan biopsy interventions that generate physician-readable instructions to reach the PLs. The authors’ solution is open source, multiplatform, and extensible for future functionalities, designed by their multidisciplinary research and development group. BronchoX is a compound of different algorithms for segmentation, visualisation, and navigation of the respiratory tract. Performed results are a focus on the test the effectiveness of their proposal as an exploration software, also to measure its accuracy as a guiding system to reach PLs. Then, 40 different virtual planning paths were created to guide physicians until distal bronchioles. These results provide a functional software for BronchoX and demonstrate how following simple instructions is possible to reach distal lesions from the trachea.
|
|
|
|
Thanh Ha Do, Oriol Ramos Terrades, & Salvatore Tabbone. (2019). DSD: document sparse-based denoising algorithm. PAA - Pattern Analysis and Applications, 22(1), 177–186.
Abstract: In this paper, we present a sparse-based denoising algorithm for scanned documents. This method can be applied to any kind of scanned documents with satisfactory results. Unlike other approaches, the proposed approach encodes noise documents through sparse representation and visual dictionary learning techniques without any prior noise model. Moreover, we propose a precision parameter estimator. Experiments on several datasets demonstrate the robustness of the proposed approach compared to the state-of-the-art methods on document denoising.
Keywords: Document denoising; Sparse representations; Sparse dictionary learning; Document degradation models
|
|
|
|
Isabelle Guyon, Lisheng Sun Hosoya, Marc Boulle, Hugo Jair Escalante, Sergio Escalera, Zhengying Liu, et al. (2019). Analysis of the AutoML Challenge Series 2015-2018. In Automated Machine Learning (pp. 177–219). SSCML. Springer.
Abstract: The ChaLearn AutoML Challenge (The authors are in alphabetical order of last name, except the first author who did most of the writing and the second author who produced most of the numerical analyses and plots.) (NIPS 2015 – ICML 2016) consisted of six rounds of a machine learning competition of progressive difficulty, subject to limited computational resources. It was followed bya one-round AutoML challenge (PAKDD 2018). The AutoML setting differs from former model selection/hyper-parameter selection challenges, such as the one we previously organized for NIPS 2006: the participants aim to develop fully automated and computationally efficient systems, capable of being trained and tested without human intervention, with code submission. This chapter analyzes the results of these competitions and provides details about the datasets, which were not revealed to the participants. The solutions of the winners are systematically benchmarked over all datasets of all rounds and compared with canonical machine learning algorithms available in scikit-learn. All materials discussed in this chapter (data and code) have been made publicly available at http://automl.chalearn.org/.
|
|
|
|
Joan Mas, J.A. Jorge, Gemma Sanchez, & Josep Llados. (2008). Representing and Parsing Sketched Symbols using Adjacency Grammars and a Grid-Directed Parser. In J.M. Ogier J. L. W. Liu (Ed.), Graphics Recognition: Recent Advances and New Opportunities, (Vol. 5046, 176–187). LNCS.
|
|
|
|
Petia Radeva, Michal Drozdzal, Santiago Segui, Laura Igual, Carolina Malagelada, Fernando Azpiroz, et al. (2012). Active labeling: Application to wireless endoscopy analysis. In High Performance Computing and Simulation, International Conference on (pp. 174–181).
Abstract: Today, robust learners trained in a real supervised machine learning application should count with a rich collection of positive and negative examples. Although in many applications, it is not difficult to obtain huge amount of data, labeling those data can be a very expensive process, especially when dealing with data of high variability and complexity. A good example of such cases are data from medical imaging applications where annotating anomalies like tumors, polyps, atherosclerotic plaque or informative frames in wireless endoscopy need highly trained experts. Building a representative set of training data from medical videos (e.g. Wireless Capsule Endoscopy) means that thousands of frames to be labeled by an expert. It is quite normal that data in new videos come different and thus are not represented by the training set. In this paper, we review the main approaches on active learning and illustrate how active learning can help to reduce expert effort in constructing the training sets. We show that applying active learning criteria, the number of human interventions can be significantly reduced. The proposed system allows the annotation of informative/non-informative frames of Wireless Capsule Endoscopy video containing more than 30000 frames each one with less than 100 expert ”clicks”.
|
|
|
|
Jaume Garcia, David Rotger, Francesc Carreras, R.Leta, & Petia Radeva. (2003). Contrast echography segmentation and tracking by trained deformable models. In Proc. Computers in Cardiology (Vol. 30, pp. 173–176). Centre de Visió per Computador – Dept. Informàtica, UAB Edifici O – Campus UAB, 08193 Bellater.
Abstract: The objective of this work is to segment the human left ventricle myocardium (LVM) in contrast echocardiography imaging and thus track it along a cardiac cycle in order to extract quantitative data about heart function. Ultrasound images are hard to work with due to their speckle appearance. To overcome this we report the combination of active contour models (ACM) or snakes and active shape models (ASM). The ability of ACM in giving closed and smooth curves in addition to the power of the ASM in producing shapes similar to the ones learned, evoke to a robust algorithm. Meanwhile the snake is attracted towards image main features, ASM acts as a correction factor. The algorithm was tested independently on 180 frames and satisfying results were obtained: in 95% the maximum difference between automatic and experts segmentation was less than 12 pixels.
|
|
|
|
Daniel Sanchez, Miguel Angel Bautista, & Sergio Escalera. (2015). HuPBA 8k+: Dataset and ECOC-GraphCut based Segmentation of Human Limbs. NEUCOM - Neurocomputing, 150(A), 173–188.
Abstract: Human multi-limb segmentation in RGB images has attracted a lot of interest in the research community because of the huge amount of possible applications in fields like Human-Computer Interaction, Surveillance, eHealth, or Gaming. Nevertheless, human multi-limb segmentation is a very hard task because of the changes in appearance produced by different points of view, clothing, lighting conditions, occlusions, and number of articulations of the human body. Furthermore, this huge pose variability makes the availability of large annotated datasets difficult. In this paper, we introduce the HuPBA8k+ dataset. The dataset contains more than 8000 labeled frames at pixel precision, including more than 120000 manually labeled samples of 14 different limbs. For completeness, the dataset is also labeled at frame-level with action annotations drawn from an 11 action dictionary which includes both single person actions and person-person interactive actions. Furthermore, we also propose a two-stage approach for the segmentation of human limbs. In a first stage, human limbs are trained using cascades of classifiers to be split in a tree-structure way, which is included in an Error-Correcting Output Codes (ECOC) framework to define a body-like probability map. This map is used to obtain a binary mask of the subject by means of GMM color modelling and GraphCuts theory. In a second stage, we embed a similar tree-structure in an ECOC framework to build a more accurate set of limb-like probability maps within the segmented user mask, that are fed to a multi-label GraphCut procedure to obtain final multi-limb segmentation. The methodology is tested on the novel HuPBA8k+ dataset, showing performance improvements in comparison to state-of-the-art approaches. In addition, a baseline of standard action recognition methods for the 11 actions categories of the novel dataset is also provided.
Keywords: Human limb segmentation; ECOC; Graph-Cuts
|
|
|
|
Ivo Everts, Jan van Gemert, & Theo Gevers. (2012). Per-patch Descriptor Selection using Surface and Scene Properties. In 12th European Conference on Computer Vision (Vol. 7577, pp. 172–186). LNCS. Springer Berlin Heidelberg.
Abstract: Local image descriptors are generally designed for describing all possible image patches. Such patches may be subject to complex variations in appearance due to incidental object, scene and recording conditions. Because of this, a single-best descriptor for accurate image representation under all conditions does not exist. Therefore, we propose to automatically select from a pool of descriptors the one that is best suitable based on object surface and scene properties. These properties are measured on the fly from a single image patch through a set of attributes. Attributes are input to a classifier which selects the best descriptor. Our experiments on a large dataset of colored object patches show that the proposed selection method outperforms the best single descriptor and a-priori combinations of the descriptor pool.
|
|
|
|
Arnau Baro, Pau Riba, & Alicia Fornes. (2022). Musigraph: Optical Music Recognition Through Object Detection and Graph Neural Network. In Frontiers in Handwriting Recognition. International Conference on Frontiers in Handwriting Recognition (ICFHR2022) (Vol. 13639, pp. 171–184). LNCS.
Abstract: During the last decades, the performance of optical music recognition has been increasingly improving. However, and despite the 2-dimensional nature of music notation (e.g. notes have rhythm and pitch), most works treat musical scores as a sequence of symbols in one dimension, which make their recognition still a challenge. Thus, in this work we explore the use of graph neural networks for musical score recognition. First, because graphs are suited for n-dimensional representations, and second, because the combination of graphs with deep learning has shown a great performance in similar applications. Our methodology consists of: First, we will detect each isolated/atomic symbols (those that can not be decomposed in more graphical primitives) and the primitives that form a musical symbol. Then, we will build the graph taking as root node the notehead and as leaves those primitives or symbols that modify the note’s rhythm (stem, beam, flag) or pitch (flat, sharp, natural). Finally, the graph is translated into a human-readable character sequence for a final transcription and evaluation. Our method has been tested on more than five thousand measures, showing promising results.
Keywords: Object detection; Optical music recognition; Graph neural network
|
|
|
|
Muhammad Muzzamil Luqman, Thierry Brouard, Jean-Yves Ramel, & Josep Llados. (2010). Vers une approche foue of encapsulation de graphes: application a la reconnaissance de symboles. In Colloque International Francophone sur l'Écrit et le Document (pp. 169–184).
Abstract: We present a new methodology for symbol recognition, by employing a structural approach for representing visual associations in symbols and a statistical classifier for recognition. A graphic symbol is vectorized, its topological and geometrical details are encoded by an attributed relational graph and a signature is computed for it. Data adapted fuzzy intervals have been introduced for addressing the sensitivity of structural representations to noise. The joint probability distribution of signatures is encoded by a Bayesian network, which serves as a mechanism for pruning irrelevant features and choosing a subset of interesting features from structural signatures of underlying symbol set, and is deployed in a supervised learning scenario for recognizing query symbols. Experimental results on pre-segmented 2D linear architectural and electronic symbols from GREC databases are presented.
Keywords: Fuzzy interval; Graph embedding; Bayesian network; Symbol recognition
|
|
|
|
David Vazquez, Antonio Lopez, Daniel Ponsa, & David Geronimo. (2013). Interactive Training of Human Detectors. In Multiodal Interaction in Image and Video Applications (Vol. 48, pp. 169–182). Springer Berlin Heidelberg.
Abstract: Image based human detection remains as a challenging problem. Most promising detectors rely on classifiers trained with labelled samples. However, labelling is a manual labor intensive step. To overcome this problem we propose to collect images of pedestrians from a virtual city, i.e., with automatic labels, and train a pedestrian detector with them, which works fine when such virtual-world data are similar to testing one, i.e., real-world pedestrians in urban areas. When testing data is acquired in different conditions than training one, e.g., human detection in personal photo albums, dataset shift appears. In previous work, we cast this problem as one of domain adaptation and solve it with an active learning procedure. In this work, we focus on the same problem but evaluating a different set of faster to compute features, i.e., Haar, EOH and their combination. In particular, we train a classifier with virtual-world data, using such features and Real AdaBoost as learning machine. This classifier is applied to real-world training images. Then, a human oracle interactively corrects the wrong detections, i.e., few miss detections are manually annotated and some false ones are pointed out too. A low amount of manual annotation is fixed as restriction. Real- and virtual-world difficult samples are combined within what we call cool world and we retrain the classifier with this data. Our experiments show that this adapted classifier is equivalent to the one trained with only real-world data but requiring 90% less manual annotations.
Keywords: Pedestrian Detection; Virtual World; AdaBoost; Domain Adaptation
|
|
|
|
Sebastien Mace, Herve Locteau, Ernest Valveny, & Salvatore Tabbone. (2010). A system to detect rooms in architectural floor plan images. In 9th IAPR International Workshop on Document Analysis Systems (167–174).
Abstract: In this article, a system to detect rooms in architectural floor plan images is described. We first present a primitive extraction algorithm for line detection. It is based on an original coupling of classical Hough transform with image vectorization in order to perform robust and efficient line detection. We show how the lines that satisfy some graphical arrangements are combined into walls. We also present the way we detect some door hypothesis thanks to the extraction of arcs. Walls and door hypothesis are then used by our room segmentation strategy; it 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 between regions can also be rough. We take advantage of knowledge associated to architectural floor plans in order to obtain mostly rectangular rooms. Qualitative and quantitative evaluations performed on a corpus of real documents show promising results.
|
|
|
|
Naila Murray, Sandra Skaff, Luca Marchesotti, & Florent Perronnin. (2011). Towards Automatic Concept Transfer. In Proceedings of the ACM SIGGRAPH/Eurographics Symposium on Non-Photorealistic Animation and Rendering (167.176). ACM Press.
Abstract: This paper introduces a novel approach to automatic concept transfer; examples of concepts are “romantic”, “earthy”, and “luscious”. The approach modifies the color content of an input image given only a concept specified by a user in natural language, thereby requiring minimal user input. This approach is particularly useful for users who are aware of the message they wish to convey in the transferred image while being unsure of the color combination needed to achieve the corresponding transfer. The user may adjust the intensity level of the concept transfer to his/her liking with a single parameter. The proposed approach uses a convex clustering algorithm, with a novel pruning mechanism, to automatically set the complexity of models of chromatic content. It also uses the Earth-Mover's Distance to compute a mapping between the models of the input image and the target chromatic concept. Results show that our approach yields transferred images which effectively represent concepts, as confirmed by a user study.
Keywords: chromatic modeling, color concepts, color transfer, concept transfer
|
|
|
|
Jordi Roca, A.Owen, G.Jordan, Y.Ling, C. Alejandro Parraga, & A.Hurlbert. (2011). Inter-individual Variations in Color Naming and the Structure of 3D Color Space. In Journal of Vision (Vol. 12, 166).
Abstract: 36.307
Many everyday behavioural uses of color vision depend on color naming ability, which is neither measured nor predicted by most standardized tests of color vision, for either normal or anomalous color vision. Here we demonstrate a new method to quantify color naming ability by deriving a compact computational description of individual 3D color spaces. Methods: Individual observers underwent standardized color vision diagnostic tests (including anomaloscope testing) and a series of custom-made color naming tasks using 500 distinct color samples, either CRT stimuli (“light”-based) or Munsell chips (“surface”-based), with both forced- and free-choice color naming paradigms. For each subject, we defined his/her color solid as the set of 3D convex hulls computed for each basic color category from the relevant collection of categorised points in perceptually uniform CIELAB space. From the parameters of the convex hulls, we derived several indices to characterise the 3D structure of the color solid and its inter-individual variations. Using a reference group of 25 normal trichromats (NT), we defined the degree of normality for the shape, location and overlap of each color region, and the extent of “light”-“surface” agreement. Results: Certain features of color perception emerge from analysis of the average NT color solid, e.g.: (1) the white category is slightly shifted towards blue; and (2) the variability in category border location across NT subjects is asymmetric across color space, with least variability in the blue/green region. Comparisons between individual and average NT indices reveal specific naming “deficits”, e.g.: (1) Category volumes for white, green, brown and grey are expanded for anomalous trichromats and dichromats; and (2) the focal structure of color space is disrupted more in protanopia than other forms of anomalous color vision. The indices both capture the structure of subjective color spaces and allow us to quantify inter-individual differences in color naming ability.
|
|
