检索结果-内蒙古大学图书馆

9th indian conference on computer vision, graphics and image processing, ICVGIP 2014

作者： Acharya, Aniruddha Babu, R. Venkatesh Video Analytics Laboratory Supercomputer Education Research Center Indian Institute of Science Bangalore India

ISBN: (纸本)1595930361

Secret sharing is a well known problem of cryptography. A secret has to be shared among a group of N people, in such a way that only when at least K of them use their shares, the secret is revealed. A special case of this problem is secret image sharing, where the secret is an image. Prior work on image sharing has predominantly been visual secret sharing on binary images, where decoding is done by stacking the shares and viewing them. Some of the works address gray scale and color image sharing too. We target secret image sharing for gray scale images and propose a novel solution based on fractal encoding and decoding. The main advantage of our method as compared to the other schemes is that the space complexity of the shares is O(1). That is the sum total of space required for all the shares is independent of N. We have not seen this property in any of the previous works of image sharing. We achieve this by avoiding the use of images as shares, and using partial and modified fractal codes instead. Moreover, our method implicitly does compression along with image sharing. The proposed algorithm has decoding time complexity O(N), which is the state of the art. Experiments have shown that the proposed method is robust to security attacks. Copyright 2014 ACM.

关键词： Binary images

来源：评论

学校读者我要写书评

暂无评论

Removing structural noise in handwriting images using deep learning 14

Removing structural noise in handwriting images using deep l...

引用

9th indian conference on computer vision, graphics and image processing, ICVGIP 2014

作者： Chen, Gang Srihari, Sargur N. Dept. of Computer Science and Engineering University at Buffalo State of University of New York BuffaloNY14260 United States

ISBN: (纸本)1595930361

Since handwriting recognition is very sensitive to structural noise, like superimposed objects such as straight lines and other marks, it is necessary to remove noise in a preprocessing stage before recognition. Although numerous denoising approaches have been proposed, it remains a challenge. The difficulties are due to non-locality of structural noise and hard discernment between spurious and the meaningful regions. We propose a supervised approach using deep learning to remove structural noise. Specifically, we generalize the deep autoencoder into the deep denoising autoencoder (DDAE), which consists in training a neural network with noisy and clean pairs to minimize cross-entropy error. Inspired by recurrent neural networks, we introduce feedback loop from the output to enhance the "repaired" image well in the reconstruction stage in our framework. We test the DDAE model on three handwritten image data sets, and show advantages over Wiener filter, robust Boltzmann machines and deep autoencoder. Copyright 2014 ACM.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Recognizing facial expressions in the orthogonal complement of principal subspace 14

Recognizing facial expressions in the orthogonal complement ...

引用

9th indian conference on computer vision, graphics and image processing, ICVGIP 2014

作者： Agarwal, Swapna Mazumder, Sanjoy Mukherjee, Dipti Prasad Indian Statistical Institute Kolkata700108 India

ISBN: (纸本)1595930361

We present a novel framework for recognition of facial expressions from a given face image. The framework is based on the assumption that expression information lies in the subspace orthogonal to the subspace representing expressionneutral faces. For deriving the principal subspace of the face images showing no expression, PCA is used as a tool. Then we derive a method to find the orthogonal complement (OC) of the subspace defined by the principal components. It is shown using different tools such as dendrogram and Davies-Bouldin cluster index that the OC of the principal subspace better represents the expressions as compared to the principal subspace in PCA analysis. We have done extensive experiments to validate the recognition capability of the proposed OC space. Two well known publicly available facial expression databases are used for the experiments. We also compare the expression discrimination capability of the OC subspace with some well known features for expression representation. The proposed framework exhibits higher (9:66% on average) recognition capability as compared to the present state-of-the-art works. Copyright 2014 ACM.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

3D face recognition using kinect 14

3D face recognition using kinect

引用

9th indian conference on computer vision, graphics and image processing, ICVGIP 2014

作者： Ajmera, Rahul Nigam, Aditya Gupta, Phalguni Department of Computer Science and Engineering Indian Institute of Technology Kanpur India School of Computing and Electrical Engineering Indian Institute of Technology Mandi India

ISBN: (纸本)1595930361

2D Face recognition systems bound to fail on images with varying pose angles and occlusions. Many pose invariant methods are proposed in recent years but they are still not able to achieve very good accuracies. So in order to achieve a better accuracy we need to extend algorithms over 3D faces. Due to the high cost involved in acquisition of 3D faces we developed our approach for low-cost and low-quality Microsoft Kinect Sensor and propose an algorithm to produce better results than existing 2D Face recognition techniques even after compromising on the quality of the images from the sensor. Our proposed algorithm is based on modified SURF descriptors on RGB images combined with various enhancements on automatically generated training images using Depth and Color images. We compare our results obtained with State Of The Art Techniques obtained on publicly available RGB-D Face databases. Our System obtained recognition rate of 98.07% on 30° CurtinFace Database, 89.28% on EURECOM Database, 98.00% on 15° Internal Database and 81.00% on 30° Internal Database.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Wavelet based rotation invariant texture feature for lung tissue classification and retrieval

Wavelet based rotation invariant texture feature for lung ti...

引用

conference on Medical Imaging - computer-Aided Diagnosis

作者： Dash, Jatindra Kumar Mukhopadhyay, Sudipta Das Gupta, Rahul Garg, Mandeep Kumar Prabhakar, Nidhi Khandelwal, Niranjan Post Grad Inst Med Educ & Res Dept Elect & Elect Commun Engn Chandigarh India Post Grad Inst Med Educ & Res Ctr Educ Technol Chandigarh India Indian Inst Technol Kharagpur W Bengal India Post Grad Inst Med Educ & Res Dept Radio Diagnos & Imaging Chandigarh India

ISBN: (纸本)9780819498281

This paper evaluates the performance of recently proposed rotation invariant texture feature extraction method for the classification and retrieval of lung tissues affected with Interstitial Lung Diseases (ILDs). The method makes use of principle texture direction as the reference direction and extracts texture features using Discrete Wavelet Transform (DWT). A private database containing high resolution computed tomography (HRCT) images belonging to five category of lung tissue is used for the experiment. The experimental result shows that the texture appearances of lung tissues are anisotropic in nature and hence rotation invariant features achieve better retrieval as well as classification accuracy.

关键词： Interstitial Lung Disease classification image retrieval texture principle texture direction

来源：评论

学校读者我要写书评

暂无评论

Total cluster: A person agnostic clustering method for broadcast videos 14

Total cluster: A person agnostic clustering method for broad...

引用

9th indian conference on computer vision, graphics and image processing, ICVGIP 2014

作者： Tapaswi, Makarand Parkhi, Omkar M. Rahtu, Esa Sommerlade, Eric Stiefelhagen, Rainer Zisserman, Andrew Computer Vision for Human Computer Interaction Karlsruhe Institute of Technology Germany Visual Geometry Group Department of Engineering Science University of Oxford United Kingdom Center for Machine Vision Research University of Oulu Finland

ISBN: (纸本)1595930361

The goal of this paper is unsupervised face clustering in edited video material - where face tracks arising from different people are assigned to separate clusters, with one cluster for each person. In particular we explore the extent to which faces can be clustered automatically without making an error. This is a very challenging problem given the variation in pose, lighting and expressions that can occur, and the similarities between different people. The novelty we bring is three fold: first, we show that a form of weak supervision is available from the editing structure of the material - the shots, threads and scenes that are standard in edited video;second, we show that by first clustering within scenes the number of face tracks can be significantly reduced with almost no errors;third, we propose an extension of the clustering method to entire episodes using exemplar SVMs based on the negative training data automatically harvested from the editing structure. The method is demonstrated on multiple episodes from two very different TV series, Scrubs and Buffy. For both series it is shown that we move towards our goal, and also outperform a number of baselines from previous works. Copyright is held by the authors.

关键词： Cluster analysis

来源：评论

学校读者我要写书评

暂无评论

Temporal stationarity based prediction method for lossless video coding 14

Temporal stationarity based prediction method for lossless v...

引用

9th indian conference on computer vision, graphics and image processing, ICVGIP 2014

作者： Vaishnav, Mohit Chobey, Dinesh Kumar Tiwari, Anil Kumar LNM Institute of Information Technology India Indian Institute of Technology Jodhpur India

ISBN: (纸本)1595930361

This paper aims to propose a noble method to estimate the auto-regressive(AR) coefficients used by least-square(LS) based predictors. Estimation of this LS based predictors is computationally most complex process. This process requires a covariance matrix comprised of chosen causal pixels and also the inverse elements of the same matrix. Computational requirements of this process depends on the number of pixels for which the predictor is trained and also on the order of the predictor. Due to this high complexity, the predictor is not used practically although it provides a high compression ratio. Thus, an alternative algorithm, popularly known as LOPT-3D, was proposed in literature. However, the number of pixels required for the estimation of AR parameters are still large, and thereby, making it impracticable for real-time implementations. The proposed method overcomes this limitation by effectively making use of previously estimated AR parameters. Copyright 2014 ACM.

关键词： Covariance matrix

来源：评论

学校读者我要写书评

暂无评论

Emotion recognition from geometric facial features using self-organizing map

引用

PATTERN RECOGNITION 2014年第3期47卷 1282-1293页

作者： Majumder, Anima Behera, Laxmidhar Subramanian, Venkatesh K. Indian Inst Technol Dept Elect Engn Kanpur 208016 Uttar Pradesh India

This paper presents a novel emotion recognition model using the system identification approach. A comprehensive data driven model using an extended Kohonen self-organizing map (KSOM) has been developed whose input is a 26 dimensional facial geometric feature vector comprising eye, lip and eyebrow feature points. The analytical face model using this 26 dimensional geometric feature vector has been effectively used to describe the facial changes due to different expressions. This paper thus includes an automated generation scheme of this geometric facial feature vector. The proposed non-heuristic model has been developed using training data from MMI facial expression database. The emotion recognition accuracy of the proposed scheme has been compared with radial basis function network, multi-layered perceptron model and support vector machine based recognition schemes. The experimental results show that the proposed model is very efficient in recognizing six basic emotions while ensuring significant increase in average classification accuracy over radial basis function and multilayered perceptron. It also shows that the average recognition rate of the proposed method is comparatively better than multi-class support vector machine. (C) 2013 Elsevier Ltd. All rights reserved.

关键词： Facial expression analysis Geometric facial features Self-organizing map Features extraction System identification Radial basis function Multi-layer perceptron Support vector machine

来源：评论

学校读者我要写书评

暂无评论

Particle coding for meshfree cutting of deformable assets 14

Particle coding for meshfree cutting of deformable assets

引用

9th indian conference on computer vision, graphics and image processing, ICVGIP 2014

作者： Shrivastava, Prateek Das, Sukhendu VPLab. CSE IIT Madras India

ISBN: (纸本)1595930361

In this paper we propose a novel algorithm for cutting deformable (soft) assets, modeled using the meshfree method of Smoothed Particle Hydrodynamics (SPH). The key idea of the algorithm is to label all particles during the virtual cut operation to obtain particle codes. Since the traditional SPH formulations ignore particle separation due to cuts, we had to account for the change in topology due to virtual cuts in the SPH formulation. Virtual cut causes disruption in internal forces between separated particles. To avoid separated particles (i.e., particles belonging to different regions) affecting each other's dynamics, the generated particle codes are used for filtering the neighbours before SPH dynamics are computed. Assignment of particle codes eliminates the need for an external grid like structure for detecting newly generated cut surfaces. We exploit the region information extracted from the particle codes to obtain a color field for surface generation. We show that our algorithm can easily be integrated with existing SPH techniques. Our proposed method generates minimum overhead in scenarios where multiple cutting operations are performed on a deformable asset. Particle coding is applied across all particles in parallel and is hence computationally efficient when implemented on a GPU. Copyright 2014 ACM.

关键词： graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Blind 3D video watermarking based on 3D-HEVC encoder using depth 14

Blind 3D video watermarking based on 3D-HEVC encoder using d...

引用

9th indian conference on computer vision, graphics and image processing, ICVGIP 2014

作者： Rana, Shuvendu Sur, Arijit Department of Computer Science and Engineering Indian Institute of Technology Guwahati Assam781039 India

ISBN: (纸本)1595930361

Due to enormous advancement of internet technology and display devices, 3D video becomes popular in recent times. To ensure secure media transmission, efficient authentication scheme for such 3D video sequence is a requirement. In recent past, watermarking is being regarded as a popular DRM tool for video authentication. It has been observed that video watermarking becomes a challenging task in the presence of advanced auto-stereoscopic display devices and MVD (Multi-view Video plus Depth) based encoding technique in case of 3D video. In this paper, depth image based rendering technique is proposed for blind 3D video watermarking. In this scheme, rendering technique is used to find the Z-axis of the stereo videos (left and right video). The connected regions of the Z-axis of a Group of Picture (GOP) have been filtered using the motion prediction of the video. Block DCT coefficients are used to embed the watermark signal with the selected Z-axis regions of the each video (left and right separately). A comprehensive set of experiments have been done to justify the robustness of the proposed scheme over existing schemes with respect to compression of the 3D-HEVC video codec. Copyright 2014 ACM.

关键词： Watermarking

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：