2017 Tenth International Conference on Contemporary Computing (IC3)最新文献_第7页

Adversarial attacks on computer vision algorithms using natural perturbations 利用自然扰动对计算机视觉算法进行对抗性攻击

2017 Tenth International Conference on Contemporary Computing (IC3) Pub Date : 2017-08-01 DOI: 10.1109/IC3.2017.8284294

A. Ramanathan, L. Pullum, Zubir Husein, Sunny Raj, N. Torosdagli, S. Pattanaik, Sumit Kumar Jha

引用次数: 10

Image based search engine using deep learning 基于图像的深度学习搜索引擎

2017 Tenth International Conference on Contemporary Computing (IC3) Pub Date : 2017-08-01 DOI: 10.1109/IC3.2017.8284301

Surbhi Jain, J. Dhar

{"title":"Image based search engine using deep learning","authors":"Surbhi Jain, J. Dhar","doi":"10.1109/IC3.2017.8284301","DOIUrl":"https://doi.org/10.1109/IC3.2017.8284301","url":null,"abstract":"During previous couple of years, the World Wide Web (WWW) has become an extremely well-liked information source. To successfully utilize the vast quantity of information that the web provides, we want an effective way to explore it. Image data is much more voluminous than textual data, and visual information cannot be indexed by traditional strategies developed for indexing textual information. Therefore, Content-Based Image Retrieval (CBIR) has received an excellent deal of interest within the research community. A CBIR system operates on the visible features at low-level of a user's input image that makes it troublesome for the users to devise the input and additionally doesn't offer adequate retrieval results. In CBIR system, the study of the useful representation of features and appropriate similarity metrics is extremely necessary for improving the performance of retrieval task. Semantic gap has been the main issue which occurs between image pixels at low-level and semantics at high-level interpreted by humans. Among varied methods, machine learning (ML) has been explored as a feasible way to reduce the semantic gap. Inspired by the current success of deep learning methods for computer vision applications, in this paper, we aim to confront an advance deep learning method, known as Convolutional Neural Network (CNN), for studying feature representations and similarity measures. In this paper, we explored the applications of CNNs towards solving classification and retrieval problems. For retrieval of similar images, we agreed on using transfer learning to apply the GoogleNet deep architecture to our problem. Extracting the last-but-one fully connected layer from the retraining of GoogleNet CNN model served as the feature vectors for each image, computing Euclidean distances between these feature vectors and that of our query image to return the closest matches in the dataset.","PeriodicalId":147099,"journal":{"name":"2017 Tenth International Conference on Contemporary Computing (IC3)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125197250","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 23

Design of people counting system using MATLAB 用MATLAB设计人数统计系统

2017 Tenth International Conference on Contemporary Computing (IC3) Pub Date : 2017-08-01 DOI: 10.1109/IC3.2017.8284344

Surbhi Saxena, Dalpat Songara

引用次数: 6

Resolving identities on Facebook and Twitter 解决Facebook和Twitter上的身份问题

2017 Tenth International Conference on Contemporary Computing (IC3) Pub Date : 2017-08-01 DOI: 10.1109/IC3.2017.8284354

Suyash Somani, Somya Jain

引用次数: 3

An efficient algorithm for sampling of a single large graph 对单个大图进行采样的有效算法

2017 Tenth International Conference on Contemporary Computing (IC3) Pub Date : 2017-08-01 DOI: 10.1109/IC3.2017.8284290

Vandana Bhatia, Rinkle Rani

引用次数: 3

Approaches for information retrieval in legal documents 法律文书信息检索方法研究

2017 Tenth International Conference on Contemporary Computing (IC3) Pub Date : 2017-08-01 DOI: 10.1109/IC3.2017.8284324

Rachayita Giri, Yosha Porwal, Vaibhavi Shukla, Palak Chadha, Rishabh Kaushal

{"title":"Approaches for information retrieval in legal documents","authors":"Rachayita Giri, Yosha Porwal, Vaibhavi Shukla, Palak Chadha, Rishabh Kaushal","doi":"10.1109/IC3.2017.8284324","DOIUrl":"https://doi.org/10.1109/IC3.2017.8284324","url":null,"abstract":"With crimes increasing at an alarming rate, it becomes essential to impart justice to the victims readily. To come to a final decision, lawyers need to study several previous judgments for research purposes. Reducing the time spent on research can speed up the judicial process drastically. The time consumption mostly happens in two areas — searching for the right document and understanding that document. To start with, being able to get hold of the appropriate judgments or other legal documents is the most essential task for any legal professional, especially lawyers. Once a document is obtained, the next most integral and inevitable task is to read and re-read it, and come to necessary as well as needful conclusions after a comprehensive analysis. To resolve the first issue, there is a need for an efficient search system which can provide searching options based upon multiple views. This system is an effort at improving the search for users by providing them with search options based upon either the semantics of the word or based upon the IPC sections. It is important that laymen can access all the related judgments by entering just one keyword or phrase without bothering about the legal jargon. Post retrieval of documents, the lengthy texts have to be scrutinized for meaningful inferences. To reduce the time spent in reading texts, we intend to present the information in the judgments visually through semantic networks. Lawyers will be benefitted by this system because it will enable them to skip the complexity of the often verbose language of the legal documents. This IR System provides the features of semantic and IPC section based search to users, deriving information from semantic networks that are representative of the documents, so that a more efficient search system on legal documents can be put in place.","PeriodicalId":147099,"journal":{"name":"2017 Tenth International Conference on Contemporary Computing (IC3)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130059562","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 3

Impact analysis of rank attack with spoofed IP on routing in 6LoWPAN network IP欺骗等级攻击对6LoWPAN网络路由的影响分析

2017 Tenth International Conference on Contemporary Computing (IC3) Pub Date : 2017-08-01 DOI: 10.1109/IC3.2017.8284340

K. Rai, Krishna Asawa

引用次数: 13

Smart intersection control algorithms for automated vehicles 自动驾驶车辆的智能交叉口控制算法

2017 Tenth International Conference on Contemporary Computing (IC3) Pub Date : 2017-08-01 DOI: 10.1109/IC3.2017.8284361

Mahmoud Pourmehrab, L. Elefteriadou, S. Ranka

引用次数: 11

A fast and scalable crowd sensing based trajectory tracking system 一种快速、可扩展的基于人群传感的轨迹跟踪系统

2017 Tenth International Conference on Contemporary Computing (IC3) Pub Date : 2017-08-01 DOI: 10.1109/IC3.2017.8284303

R. Niyogi, Tarun Kulshrestha, Dhaval Patel

引用次数: 2

Fixed and dynamic threshold selection criteria in energy detection for cognitive radio communication systems 认知无线电通信系统能量检测的固定和动态阈值选择准则

2017 Tenth International Conference on Contemporary Computing (IC3) Pub Date : 2017-08-01 DOI: 10.1109/IC3.2017.8284302

Alok Kumar, P. Thakur, S. Pandit, G. Singh

引用次数: 12