检索结果-内蒙古大学图书馆

FWLBP: A scale invariant descriptor for texture classification

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Roy, Swalpa Kumar Bhattacharya, Nilavra Chanda, Bhabatosh Chaudhuri, Bidyut B. Ghosh, Dipak Kumar Optical Character Recognition Laboratory Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata700108 India School of Information University of Texas AustinTX78712 United States Image Processing Laboratory Electronics and Communication Sciences Unit Indian Statistical Institute Kolkata700108 India Department of Electronics and Communication Engineering National Institute of Technology Rourkela Rourkela769008 India

In this paper we propose a novel texture descriptor called Fractal Weighted Local Binary pattern (FWLBP). The fractal dimension (FD) measure is relatively invariant to scale-changes, and presents a good correlation with human viewpoint of surface roughness. We have utilized this property to construct a scale-invariant descriptor. Here, the input image is sampled using an augmented form of the local binary pattern (LBP) over three different radii, and then used an indexing operation to assign FD weights to the collected samples. The final histogram of the descriptor has its features calculated using LBP, and its weights computed from the FD image. The proposed descriptor is scale invariant, and is also robust in rotation or reflection, and partially tolerant to noise and illumination changes. In addition, the local fractal dimension is relatively insensitive to the bi-Lipschitz transformations, whereas its extension is adequate to precisely discriminate the fundamental of texture primitives. Experiment results carried out on standard texture databases show that the proposed descriptor achieved better classification rates compared to the state-of-the-art descriptors. Copyright © 2018, The Authors. All rights reserved.

关键词： Fractal dimension

SigNet: Convolutional siamese network for writer independent offline signature verification

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Dey, Sounak Dutta, Anjan Ignacio Toledo, J. Ghosh, Suman K. Lladós, Josep Pal, Umapada Computer Vision Center Computer Science Dept. Universitat Autònoma de Barcelona Edifici O Campus Uab Bellaterra08193 Spain Computer Vision and Pattern Recognition Unit Indian Statistical Institute 203 B. T. Road Kolkata700108 India

Offline signature verification is one of the most challenging tasks in biometrics and document foren-sics. Unlike other verification problems, it needs to model minute but critical details between genuine and forged signatures, because a skilled falsification might only differ from a real signature by some specific kinds of deformation. This verification task is even harder in writer independent scenarios which is undeniably fiscal for realistic cases. In this paper, we model an offline writer independent signature verification task with a convolutional Siamese network. Siamese networks are twin networks with shared weights, which can be trained to learn a feature space where similar observations are placed in proximity. This is achieved by exposing the network to a pair of similar and dissimilar observations and minimizing the Euclidean distance between similar pairs while simultaneously maximizing it between dissimilar pairs. Experiments conducted on cross-domain datasets emphasize the capability of our network to handle forgery in different languages (scripts) and handwriting styles. Moreover, our designed Siamese network, named SigNet, provided better results than the state-of-the-art results on most of the benchmark signature datasets. Copyright © 2017, The Authors. All rights reserved.

关键词： Convolution

Edgy salient local binary patterns in inter-plane relationship for image retrieval in Diabetic Retinopathy

学校读者我要写书评

暂无评论

Procedia computer Science 2017年 115卷 440-447页

作者： Gajanan M. Galshetwar Laxman M. Waghmare Anil B. Gonde Subrahmanyam Murala Center of Excellence in Signal and Image Processing (COESIP) Department of ECE SGGSIET Nanded Maharashtra 431606 India Computer Vision and Pattern Recognition Laboratory Department of Electrical Engineering IIT Ropar Rupnagar 140001 India

In this paper, a novel approach for content based image retrieval (CBIR) in diabetic retinopathy (DR) is proposed. The concept of salient point selection and inter-plane relationship technique is used. Salient points are selected from edgy image and later using inter-planer relationship, Local Binary patterns (LBPs) are calculated using the salient point as a center pixel. Our approach enhanced the results as we used color features in combination with LBP features. Experimentation is carried out on MESSIDOR database of 1200 retinal images, proposed approach has average precision of 57.82% as compared to the earlier approach whose average precision is 53.70%.

关键词： Content-Based image retrieval (CBIR) Diabetic Retinopathy (DR) Edgy Salient points Local Binary patterns (LBPs)

Data-driven Study of Mouse Sleep-stages using Restricted Boltzmann Machines

学校读者我要写书评

暂无评论

Data-driven Study of Mouse Sleep-stages using Restricted Bol...

International Joint Conference on Neural Networks

作者： Vasiliki-Maria Katsageorgiou Matteo Zanotto Valter Tucci Vittorio Murino Diego Sona Pattern Analysis and Computer Vision (PAVIS) Istituto Italiano di Tecnologia Genova Italy Neuroscience and Brain Technologies (NBT) Istituto Italiano di Tecnologia Genova Italy

ISBN: (纸本)9781509061839

Rodents play an important role in sleep studies since they are the most easily available low-cost animal species sharing most genes and gene functions with humans. The scoring of sleep stages in these studies is usually based on a manual analysis of long-lasting recordings of the brain electrical activity and the activity of skeletal muscles. Hence, there is a great need for tools automating the investigation over large experiments. In this paper we present a way of analyzing this huge amount of electrophysiological data using unsupervised learning models. We show how employing latent variable models, like Restricted Boltzmann Machines, we can define different sleep-wakefulness sub-stages reflected by regularities in the data, without any prior knowledge. Our analysis shows that we can effectively discover meaningful feature representations which characterize sleep stages at a finer level than those commonly used by the experts. These feature representations can be also used to further characterize different mouse genotypes, without incurring biases of experts like in a classical analysis setup where predefined rules limit the discovery of novel insights.

关键词： Brain modeling Sleep Mice Strain Data models Standards Muscles

Unsupervised Feature Learning for Writer Identification and Writer Retrieval

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Christlein, Vincent Gropp, Martin Fiel, Stefan Maier, Andreas Pattern Recognition Lab Friedrich-Alexander-Universität Erlangen-Nürnberg Erlangen91058 Germany Computer Vision Lab TU Wien Vienna1040 Austria

Deep Convolutional Neural Networks (CNN) have shown great success in supervised classification tasks such as character classification or dating. Deep learning methods typically need a lot of annotated training data, which is not available in many scenarios. In these cases, traditional methods are often better than or equivalent to deep learning methods. In this paper, we propose a simple, yet effective, way to learn CNN activation features in an unsupervised manner. Therefore, we train a deep residual network using surrogate classes. The surrogate classes are created by clustering the training dataset, where each cluster index represents one surrogate class. The activations from the penultimate CNN layer serve as features for subsequent classification tasks. We evaluate the feature representations on two publicly available datasets. The focus lies on the ICDAR17 competition dataset on historical document writer identification (Historical-WI). We show that the activation features trained without supervision are superior to descriptors of state-of-the-art writer identification methods. Additionally, we achieve comparable results in the case of handwriting classification using the ICFHR16 competition dataset on historical Latin script types (CLaMM16). Copyright © 2017, The Authors. All rights reserved.

关键词： Chemical activation

Sketch-based Facial Expression Recognition for Human Figure Drawing Psychological Test

学校读者我要写书评

暂无评论

Sketch-based Facial Expression Recognition for Human Figure ...

Frontiers of Information Technology (FIT)

作者： Momina Moetesum Tasneem Aslam Hassan Saeed Imran Siddiqi Uzma Masroor Bahria University Islamabad PK Center of Computer Vision and Pattern Recognition Bahria University Islamabad Pakistan Dept. of Professional Psychology Bahria University Islamabad Pakistan

Drawing tests have been long used by practitioners for early screening of a number of psychological and neurological impairments. These brain functioning tests are used by psychologists to understand feelings, personality and reactions of individuals to different circumstances. Among these, Human Figure Drawing Test (HFDT) is a popular instrument for the assessment of cognitive functioning of individuals. While the HFDT has various dimensions, the focus of this study lies on the face of the drawn figure. A computerized system that analyzes the hand-drawn facial images to extract the expressions from the image is proposed. Sketch of human face is drawn by the subject and then fed to the system, the image is then binarized and segmented into different facial components. Features (based on local binary patterns, gray level co-occurrence matrices and histogram of oriented gradients) computed from the facial components are used to train an SVM classifier to learn to distinguish between four expression classes, `happy', `sad', `angry' and `neutral'. The system evaluated on a custom developed database of sketches realized promising results. The developed system could serve as a useful module toward development of a complete automated system to score human figure drawing test.

关键词： Feature extraction Psychology Face recognition Face Databases Support vector machines Lips

An analysis of dropout for matrix factorization

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Cavazza, Jacopo Lane, Connor Haeffele, Benjamin D. Murino, Vittorio Vidal, René Pattern Analysis and Computer Vision Istituto Italiano di Tecnologia Genova16163 Italy Johns Hopkins University Center for Imaging Science BaltimoreMD21218 United States

Dropout is a simple yet effective algorithm for regularizing neural networks by randomly dropping out units through Bernoulli multiplicative noise, and for some restricted problem classes, such as linear or logistic regression, several theoretical studies have demonstrated the equivalence between dropout and a fully deterministic optimization problem with data-dependent Tikhonov regularization. This work presents a theoretical analysis of dropout for matrix factorization, where Bernoulli random variables are used to drop a factor, thereby attempting to control the size of the factorization. While recent work has demonstrated the empirical effectiveness of dropout for matrix factorization, a theoretical understanding of the regularization properties of dropout in this context remains elusive. This work demonstrates the equivalence between dropout and a fully deterministic model for matrix factorization in which the factors are regularized by the sum of the product of the norms of the columns. While the resulting regularizer is closely related to a variational form of the nuclear norm, suggesting that dropout may limit the size of the factorization, we show that it is possible to trivially lower the objective value by doubling the size of the factorization. We show that this problem is caused by the use of a fixed dropout rate, which motivates the use of a rate that increases with the size of the factorization. Synthetic experiments validate our theoretical findings. Copyright © 2017, The Authors. All rights reserved.

关键词： Optimization

Dropout as a low-rank regularizer for matrix factorization

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Cavazza, Jacopo Morerio, Pietro Haeffele, Benjamin Lane, Connor Murino, Vittorio Vidal, René Pattern Analysis and Computer Vision Istituto Italiano di Tecnologia Genova16163 Italy Johns Hopkins University Center for Imaging Science BaltimoreMD21218 United States

Regularization for matrix factorization (MF) and approximation problems has been carried out in many different ways. Due to its popularity in deep learning, dropout has been applied also for this class of problems. Despite its solid empirical performance, the theoretical properties of dropout as a regularizer remain quite elusive for this class of problems. In this paper, we present a theoretical analysis of dropout for MF, where Bernoulli random variables are used to drop columns of the factors. We demonstrate the equivalence between dropout and a fully deterministic model for MF in which the factors are regularized by the sum of the product of squared Euclidean norms of the columns. Additionally, we inspect the case of a variable sized factorization and we prove that dropout achieves the global minimum of a convex approximation problem with (squared) nuclear norm regularization. As a result, we conclude that dropout can be used as a low-rank regularizer with data dependent singular-value thresholding. Copyright © 2017, The Authors. All rights reserved.

关键词： Deep learning

SSERBC 2017: Sclera segmentation and eye recognition benchmarking competition

学校读者我要写书评

暂无评论

SSERBC 2017: Sclera segmentation and eye recognition benchma...

2017 IEEE International Joint Conference on Biometrics, IJCB 2017

作者： Das, Abhijit Pal, Umapada Ferrer, Miguel A. Blumenstein, Michael Štepec, Dejan Rot, Peter Emeršič, Žiga Peer, Peter Štruc, Vitomir Kumar, S.V. Aruna Harish, B.S. Institute for Integrated and Intelligent Systems Griffith University QLD Australia Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata India IDeTIC University of Las Palmas de Gran Canaria Las Palmas Spain School of Software University of Technology Sydney Australia Faculty of Computer and Information Science University of Ljubljana Ljubljana Slovenia Department of Information Science and Engineering Sri Jayachamrajendra College of Engineering Mysusru Karnataka India

ISBN: (纸本)9781538611241

This paper summarises the results of the Sclera Segmentation and Eye Recognition Benchmarking Competition (SSERBC 2017). It was organised in the context of the International Joint Conference on Biometrics (IJCB 2017). The aim of this competition was to record the recent developments in sclera segmentation and eye recognition in the visible spectrum (using iris, sclera and peri-ocular, and their fusion), and also to gain the attention of researchers on this subject. In this regard, we have used the Multi-Angle Sclera Dataset (MASD version 1). It is comprised of2624 images taken from both the eyes of 82 identities. Therefore, it consists of images of 164 (82×2) eyes. A manual segmentation mask of these images was created to baseline both tasks. Precision and recall based statistical measures were employed to evaluate the effectiveness of the segmentation and the ranks of the segmentation task. Recognition accuracy measure has been employed to measure the recognition task. Manually segmented sclera, iris and peri-ocular regions were used in the recognition task. Sixteen teams registered for the competition, and among them, six teams submitted their algorithms or systems for the segmentation task and two of them submitted their recognition algorithm or systems. The results produced by these algorithms or systems reflect current developments in the literature of sclera segmentation and eye recognition, employing cutting edge techniques. The MASD version 1 dataset with some of the ground truth will be freely available for research purposes. The success of the competition also demonstrates the recent interests of researchers from academia as well as industry on this subject. © 2017 IEEE.

关键词： Competition