Conference
Brazilian Symposium on Computer Graphics and Image Processing
About: Brazilian Symposium on Computer Graphics and Image Processing is an academic conference. The conference publishes majorly in the area(s): Image segmentation & Feature extraction. Over the lifetime, 1331 publications have been published by the conference receiving 16730 citations.
Topics: Image segmentation, Feature extraction, Rendering (computer graphics), Image processing, Segmentation
Papers published on a yearly basis
Papers
More filters
••
11 Oct 2009TL;DR: The experimental results demonstrate that the use of an enriched feature set analyzed by PLS reduces the ambiguity among different appearances and provides higher recognition rates when compared to other machine learning techniques.
Abstract: Appearance information is essential for applications such as tracking and people recognition. One of the main problems of using appearance-based discriminative models is the ambiguities among classes when the number of persons being considered increases. To reduce the amount of ambiguity, we propose the use of a rich set of feature descriptors based on color, textures and edges. Another issue regarding appearance modeling is the limited number of training samples available for each appearance. The discriminative models are created using a powerful statistical tool called Partial Least Squares (PLS), responsible for weighting the features according to their discriminative power for each different appearance. The experimental results, based on appearance-based person recognition, demonstrate that the use of an enriched feature set analyzed by PLS reduces the ambiguity among different appearances and provides higher recognition rates when compared to other machine learning techniques.
389 citations
••
01 Oct 2018TL;DR: The survey provides a clear, structured presentation of the principal, state-of-the-art (SOTA) face recognition techniques appearing within the past five years in top computer vision venues with some open issues currently overlooked by the community.
Abstract: Face recognition made tremendous leaps in the last five years with a myriad of systems proposing novel techniques substantially backed by deep convolutional neural networks (DCNN). Although face recognition performance sky-rocketed using deep-learning in classic datasets like LFW, leading to the belief that this technique reached human performance, it still remains an open problem in unconstrained environments as demonstrated by the newly released IJB datasets. This survey aims to summarize the main advances in deep face recognition and, more in general, in learning face representations for verification and identification. The survey provides a clear, structured presentation of the principal, state-of-the-art (SOTA) face recognition techniques appearing within the past five years in top computer vision venues. The survey is broken down into multiple parts that follow a standard face recognition pipeline: (a) how SOTA systems are trained and which public data sets have they used; (b) face preprocessing part (detection, alignment, etc.); (c) architecture and loss functions used for transfer learning (d) face recognition for verification and identification. The survey concludes with an overview of the SOTA results at a glance along with some open issues currently overlooked by the community.
347 citations
••
22 Aug 2012TL;DR: The wrapper approach combines the power of exploration of the bats together with the speed of the Optimum-Path Forest classifier to find the set of features that maximizes the accuracy in a validating set.
Abstract: Feature selection aims to find the most important information from a given set of features. As this task can be seen as an optimization problem, the combinatorial growth of the possible solutions may be in-viable for a exhaustive search. In this paper we propose a new nature-inspired feature selection technique based on the bats behaviour, which has never been applied to this context so far. The wrapper approach combines the power of exploration of the bats together with the speed of the Optimum-Path Forest classifier to find the set of features that maximizes the accuracy in a validating set. Experiments conducted in five public datasets have demonstrated that the proposed approach can outperform some well-known swarm-based techniques.
339 citations
••
22 Aug 2012TL;DR: This paper evaluated SFTA for the tasks of content-based image retrieval (CBIR) and image classification, comparing its performance to that of other widely employed feature extraction methods such as Haralick and Gabor filter banks and found that SFTA achieved higher precision and accuracy for CBIR and image Classification.
Abstract: In this paper we propose a new and efficient texture feature extraction method: the Segmentation-based Fractal Texture Analysis, or SFTA. The extraction algorithm consists in decomposing the input image into a set of binary images from which the fractal dimensions of the resulting regions are computed in order to describe segmented texture patterns. The decomposition of the input image is achieved by the Two-Threshold Binary Decomposition (TTBD) algorithm, which we also propose in this work. We evaluated SFTA for the tasks of content-based image retrieval (CBIR) and image classification, comparing its performance to that of other widely employed feature extraction methods such as Haralick and Gabor filter banks. SFTA achieved higher precision and accuracy for CBIR and image classification. Additionally, SFTA was at least 3.7 times faster than Gabor and 1.6 times faster than Haralick with respect to feature extraction time.
271 citations
••
22 Aug 2012TL;DR: The basic principles to begin developing applications using Kinect are shown, and some projects developed at the VISGRAF Lab are presented, and the new possibilities, challenges and trends raised by Kinect are discussed.
Abstract: Kinect is a device introduced in November 2010 as an accessory of Xbox 360. The acquired data has different and complementary natures, combining geometry with visual attributes. For this reason, Kinect is a flexible tool that can be used in applications from several areas such as: Computer Graphics, Image Processing, Computer Vision and Human-Machine Interaction. In this way, the Kinect is a widely used device in industry (games, robotics, theater performers, natural interfaces, etc.) and in research. We will initially present some concepts about the device: the architecture and the sensor. We then will discuss about the data acquisition process: capturing, representation and filtering. Capturing process consists of obtaining a colored image (RGB) and performing a depth measurement (D), with structured light technique. This data is represented by a structure called RGBD Image. We will also talk about the main tools available for developing applications on various platforms. Furthermore, we will discuss some recent projects based on RGBD Images. In particular, those related to Object Recognition, 3D Reconstruction, Augmented Reality, Image Processing, Robotic, and Interaction. In this survey, we will show some research developed by the academic community and some projects developed for the industry. We intend to show the basic principles to begin developing applications using Kinect, and present some projects developed at the VISGRAF Lab. And finally, we intend to discuss the new possibilities, challenges and trends raised by Kinect.
234 citations