检索结果-内蒙古大学图书馆

arXiv 2019年

作者： Chaturvedi, Akshay Garain, Utpal Computer Vision and Pattern Recognition Unit Indian Statistical Institute India

At present, adversarial attacks are designed in a task-specific fashion. However, for downstream computer vision tasks such as image captioning, image segmentation etc., the current deep learning systems use an image classifier like VGG16, ResNet50, Inception-v3 etc. as a feature extractor. Keeping this in mind, we propose Mimic and Fool, a task agnostic adversarial attack. Given a feature extractor, the proposed attack finds an adversarial image which can mimic the image feature of the original image. This ensures that the two images give the same (or similar) output regardless of the task. We randomly select 1000 MSCOCO validation images for experimentation. We perform experiments on two image captioning models, Show and Tell, Show Attend and Tell and one VQA model, namely, end-to-end neural module network (N2NMN). The proposed attack achieves success rate of 74.0%, 81.0% and 89.6% for Show and Tell, Show Attend and Tell and N2NMN respectively. We also propose a slight modification to our attack to generate natural-looking adversarial images. In addition, it is shown that the proposed attack also works for invertible architecture. Since Mimic and Fool only requires information about the feature extractor of the model, it can be considered as a gray-box attack. Copyright © 2019, The Authors. All rights reserved.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Cryptanalysis of optimal differential energy watermarking (DEW) and a modified robust scheme 3rd

Cryptanalysis of optimal differential energy watermarking (D...

引用

3rd International Conference on Cryptology in India, INDOCRYPT 2002

作者： Das, Tanmoy Kanti Maitra, Subhamoy Computer Vision and Pattern Recognition Unit Indian Statistical Institute 203 B T Road Calcutta700 108 India Applied Statistics Unit Indian Statistical Institute 203 B T Road Calcutta700 108 India

ISBN: (纸本)9783540362319

In this paper we provide a cryptanalysis of the well known "Optimal Differential Energy Watermarking (DEW)" scheme. The DEW scheme divides the image into some disjoint regions (each region containing two subregions). The watermark is basically a secret binary string where each individual bit information is inserted in one of the regions by modifying the high frequency DCT (Discrete Cosine Transform) coefficients. This modification creates required energy difference between two subregions. We here modify the high frequency components so that this energy difference vanishes and in turn extraction of watermark signal becomes impossible, making the cryptanalysis successful. Moreover, we modify the DEW scheme by inserting the bit information in low frequency components instead of high frequency components and propose an oblivious robust watermarking strategy which can trace the buyer too. © Springer-Verlag Berlin Heidelberg 2002.

关键词： Discrete cosine transforms

来源：评论

学校读者我要写书评

暂无评论

An approach to a rough set decision system for classification of different heart diseases

An approach to a rough set decision system for classificatio...

引用

AMSE International Conference on Modelling and Simulation, MS'2004

作者： Mitra, S. Mitra, M. Chattopadhya, S. Chaudhuri, B.B. Department of Applied Physics Faculty of Technology University of Calcutta India Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata India JIS College of Engineering Kalyani India

In this paper a rule based rough set decision system for development of a disease inference engine is described. For this purpose an off-line data acquisition system of paper electrocardiogram (ECG) records are developed using image processing techniques. A QRS detector is developed for detection of R-R interval from ECG waves. After detection of this R-R interval the P and T waves are detected based on syntactic approaches and different time-plane features are extracted from every ECG signals. From a knowledgebase which is developed from the feedback of different reputed cardiologists and consultation of different medical books the essential time plane features for ECG interpretation have been selected. Finally, a rule-based roughest decision system is generated for the development of an inference engine for disease identification from these time-plane features.

关键词： Inference engines

来源：评论

学校读者我要写书评

暂无评论

Offline handwritten Devanagari word recognition: Information fusion at feature and classifier levels

Offline handwritten Devanagari word recognition: Information...

引用

Asian Conference on pattern recognition (ACPR)

作者： Bikash Shaw Ujjwal Bhattacharya Swapan Kumar Parui Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata

ISBN: (纸本)9781479961016

This article presents our recent study on fusion of information at feature and classifier output levels for improved performance of offline handwritten Devanagari word recognition. We consider here two state-of-the-art features, viz., Directional Distance Distribution (DDD) and Gradient-Structural-Concavity (GSC) features along with multi-class SVM classifiers. Here, we study various combinations of DDD features along with one or more features from the GSC feature set. We experiment by presenting different combined feature vectors as input to SVM classifiers. Also, the output vectors of different SVM classifiers fed with different feature vectors are combined by another SVM classifier. The combination of the outputs of two SVMs each being fed with a different feature vector provides superior performance to the performance of a single SVM classifier fed with the combined feature vector. Experimental results are obtained on a large handwritten Devanagari word sample image database of 100 indian town names. The recognition results on its test samples show that SVM recognition output of DDD features combined with the SVM output of GSC features improves the final recognition accuracy significantly.

关键词： Handwriting recognition Support vector machines Feature extraction Shape Databases Automation

来源：评论

学校读者我要写书评

暂无评论

Multi-gradient-direction based deep learning model for arecanut disease identification

引用

CAAI Transactions on Intelligence Technology 2022年第2期7卷 156-166页

作者： S.B.Mallikarjuna Palaiahnakote Shivakumara Vijeta Khare M.Basavanna Umapada Pal B.Poornima Department of Computer Science and Engineering Bapuji Institute of Engineering and TechnologyDavanagereAffiliated to Visvesvaraya Theological UniversityBelagaviKarnatakaIndia Faculty of Computer Science and Information Technology University of MalayaKuala LumpurMalaysia Adani Institute of Infrastructure Engineering AhmedabadIndia Department of Computer Science Davanagere UniversityDavanagereKarnatakaIndia Computer Vision and Pattern Recognition Unit Indian Statistical InstituteKolkataWest BengalIndia

Arecanut disease identification is a challenging problem in the field of image *** this work,we present a new combination of multi-gradient-direction and deep con-volutional neural networks for arecanut disease identification,namely,rot,split and *** to the effect of the disease,there are chances of losing vital details in the *** enhance the fine details in the images affected by diseases,we explore multi-Sobel directional masks for convolving with the input image,which results in enhanced *** proposed method extracts arecanut as foreground from the enhanced images using Otsu ***,the features are extracted for foreground information for disease identification by exploring the ResNet *** advantage of the proposed approach is that it identifies the diseased images from the healthy arecanut *** results on the dataset of four classes(healthy,rot,split and rot-split)show that the proposed model is superior in terms of classification rate.

关键词： deep learning image analysis pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Machine authentication of security documents

Machine authentication of security documents

引用

ICDAR2009 - 10th International Conference on Document Analysis and recognition

作者： Garain, Utpal Halder, Biswajit Computer Vision and Pattern Recognition Unit India Statistical Institute 203 B.T. Road Kolkata 700108 India WB India

ISBN: (纸本)9780769537252

This paper presents a pioneering effort towards machine authentication of security documents like bank cheques, legal deeds, certificates, etc. that fall under the same class as far as security is concerned. The proposed method first computationally extracts the security features from the document images and then the notion of 'genuine' vs. 'duplicate' is defined in the feature space. Bank cheques are taken as a reference for conducting the present experiment. Support Vector Machines (SVMs) and Neural Networks (NN) are involved to verify authenticity of these cheques. Results on a test dataset of 200 samples show that the proposed approach achieves about 98% accuracy for discriminating duplicate cheques from genuine ones. This strongly attests the viability of involving machine in authenticating security documents. © 2009 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Script identification - A Han & Roman script perspective

Script identification - A Han & Roman script perspective

引用

2010 20th International Conference on pattern recognition, ICPR 2010

作者： Chanda, Sukalpa Pal, Umapada Franke, Katrin Kimura, Fumitaka Department of Computer Science and Media Tech. Gjøvik University College Norway Computer Vision and Pattern Recognition Unit Indian Statistical Institute India Graduate School of Engineering Mie University Japan

ISBN: (纸本)9780769541099

All Han-based scripts (Chinese, Japanese, and Korean) possess similar visual characteristics. Hence system development for identification of Chinese, Japanese and Korean scripts from a single document page is quite challenging. It is noted that a Han-based document page might also have Roman script in them. A multi-script OCR system dealing with Chinese, Japanese, Korean, and Roman scripts, demands identification of scripts before execution of respective OCR modules. We propose a system to address this problem using directional features along with a Gaussian Kernel-based Support Vector Machine. We got promising results of 98.39% script identification accuracy at character level and 99.85% at block level, when no rejection was considered. © 2010 IEEE.

关键词： Optical character recognition

来源：评论

学校读者我要写书评

暂无评论

NLP-IISERB@Simpletext2022: To Explore the Performance of BM25 and Transformer Based Frameworks for Automatic Simplification of Scientific Texts

NLP-IISERB@Simpletext2022: To Explore the Performance of BM2...

引用

2022 Conference and Labs of the Evaluation Forum, CLEF 2022

作者： Saha, Sourav Roy, Dwaipayan Goud, B. Yuvaraj Reddy, Chethan S. Basu, Tanmay Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata India Department of Computational and Data Sciences Indian Institute of Science Education and Research Kolkata India Department of Data Science and Engineering Indian Institute of Science Education and Research Bhopal India

CLEF SimpleText 2022 lab focuses on developing effective systems to identify relevant passages from a given set of scientific articles. The lab has organized three tasks this year. Task 1 is focused on passage retrieval from the given data for a query text. These passages can be complex and hence require further simplification to be carried out in tasks 2 and 3. The BioNLP research group at the indian institute of Science Education and Research Bhopal (IISERB) in collaboration with two different information retrieval research groups at IISER Kolkata and ISI Kolkata participated only in Task 1 of this challenge and submitted three runs using three different retrieval models. The paper explores the performance of these retrieval models for the given task. We used a standard BM25 model as our first run to identify 1000 relevant passages for each query. Moreover, the passages for each query were ranked based on their similarity scores generated by the BM25 model. For our second run, we used a BERT (Bidirectional Encoder Representations from Transformers) based re-ranking method, called as Mono-BERT to further rank the 1000 passages retrieved by our first run for each query. A pre-trained sequence to sequence model based re-ranking method, called MonoT5 was used as our third run to reorder the 1000 passages retrieved by the Mono-BERT model for each query. As the official results of this task are not yet announced, we cannot explore the performance of our submissions. However, we have manually checked the retrieved results of many queries for each run, which indicate that the performance improved from run 1 to run 2 and further to run 3. © 2022 Copyright for this paper by its authors.

关键词： Information retrieval

来源：评论

学校读者我要写书评

暂无评论

Proceedings of 2nd International Conference on computer vision & Image Processing 1

引用

丛书名： Advances in Intelligent Systems and Computing

1000年

作者： Bidyut B. Chaudhuri Mohan S. Kankanhalli Balasubramanian Raman

来源：评论

学校读者我要写书评

暂无评论

F-ratio based weighted feature extraction for similar shape character recognition

F-ratio based weighted feature extraction for similar shape ...

引用

ICDAR2009 - 10th International Conference on Document Analysis and recognition

作者： Wakabayashi, T. Pal, U. Kimura, F. Miyake, Y. Graduate School of Engineering Mie University TSU 1577 Kurimamachiya-cho Mie 514-8507 Japan Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata-108 India

ISBN: (纸本)9780769537252

recognition of handwritten similar shaped character is a difficult problem and in character recognition system most of the errors occur from similar shaped characters. In this paper we proposed a novel feature extraction technique to improve the recognition results of two similar shaped characters. The technique is based on F-ratio (Fisher Ratio), a statistical measure defined by the ratio to the between-class variance and within-class variance. F-ratio modifies the feature vector of two similar shape characters by weighting the feature elements. This weighting scheme enhances the feature elements that belongs to the distinguishable portions of the similar shaped characters and reduces the feature elements of the common portion of the characters, so that similar shaped characters can be identified easily. We considered pair of handwritten similar shape characters of different scripts like Arabic/Persian, Devnagari English, Bangla, Oriya, Tamil, Kannada, Telugu etc. and we noted that f-ratio based feature weighting shows better recognition results. © 2009 IEEE.

关键词： Character recognition

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：