2019 International Conference on Communication and Signal Processing (ICCSP)最新文献

Latent Fingerprint Image Enhancement using Gabor Functions via Multi-Scale Patch based Sparse Representation and Matching based on Neural Networks 基于多尺度Patch稀疏表示和神经网络匹配的Gabor隐指纹图像增强

2019 International Conference on Communication and Signal Processing (ICCSP) Pub Date : 2019-04-04 DOI: 10.1109/ICCSP.2019.8697916

R. Jhansi rani, K. Vasanth

{"title":"Latent Fingerprint Image Enhancement using Gabor Functions via Multi-Scale Patch based Sparse Representation and Matching based on Neural Networks","authors":"R. Jhansi rani, K. Vasanth","doi":"10.1109/ICCSP.2019.8697916","DOIUrl":"https://doi.org/10.1109/ICCSP.2019.8697916","url":null,"abstract":"Fingerprint identification is one of the most trusted identification techniques acceptable by court of law. Latent fingerprint images are usually smudged, distorted, overlapped by other prints with less clarity and less content of poor quality. Hence it is challenging to achieve well definitive latent fingerprint feature extraction and recognition techniques. The proposed system is the combination of total variation model and sparse representation with multi-scale patching. TV model divides the image into two components: texture and cartoon components. The texture components are characterized as the informative structure of small patterns and the cartoon components are eliminated as non-fingerprint patterns. Initially we apply Gabor functions on a high quality fingerprint images to obtain the characteristics of ridge structures like ridge orientation and frequency. Then the dictionaries are created by repeated learning from a set of well defined fingerprint patterns. Using the knowledge of the dictionary, multi-scale patch based sparse representation is used to enhance and restore the ridge structures in latent fingerprint images. Finally Levenberg-Marquardt algorithm is used to train Neural Networks for fingerprint matching and identification. The proposed algorithm reduces the distortion and enhances the finger print pattern thereby increases the recognition rate.","PeriodicalId":194369,"journal":{"name":"2019 International Conference on Communication and Signal Processing (ICCSP)","volume":"29 6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116629920","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: 2

A Deep Learning RCNN Approach for Vehicle Recognition in Traffic Surveillance System 交通监控系统中车辆识别的深度学习RCNN方法

2019 International Conference on Communication and Signal Processing (ICCSP) Pub Date : 2019-04-04 DOI: 10.1109/ICCSP.2019.8698018

Murugan V, Vijaykumar V.R, N. A

引用次数: 21

Lane Datasets for Lane Detection 车道检测的车道数据集

2019 International Conference on Communication and Signal Processing (ICCSP) Pub Date : 2019-04-04 DOI: 10.1109/ICCSP.2019.8698065

S. Shirke, R. Udayakumar

引用次数: 15

Reseeding LFSR for Test Pattern Generation 重新播种LFSR以生成测试模式

2019 International Conference on Communication and Signal Processing (ICCSP) Pub Date : 2019-04-04 DOI: 10.1109/ICCSP.2019.8698025

Patare Snehal Dilip, Geethu Remadevi Somanathan, R. Bhakthavatchalu

{"title":"Reseeding LFSR for Test Pattern Generation","authors":"Patare Snehal Dilip, Geethu Remadevi Somanathan, R. Bhakthavatchalu","doi":"10.1109/ICCSP.2019.8698025","DOIUrl":"https://doi.org/10.1109/ICCSP.2019.8698025","url":null,"abstract":"Testing of circuits became difficult as the scale of integration is increasing as said in Moore’s Law. Conventional testing approach is not sufficient with the growth of device counts and density. Testing helps the developer to investigate faults and error present in developed circuit which helps to reduce time require to test and thus decreases chances of getting failed during operation. Test time is one of the most important parameters in digital circuit testing which effects the overall process of testing. Reducing the test time of the test pattern generation is one of the most effected solution for the process. Reseeding LFSR is one of the methods to generate the test patterns for testing. In this paper, pseudo-random test patterns are generated to test circuit using reseeding LFSR technique. This helps to reduce the test pattern required to be stored for testing. This technique can be applied with the principles which are required for low power as well as low test data volume. Fault coverage of proposed circuit is calculated using ISCAS’89 benchmark circuits. The technique is integrated with the benchmark circuits and comparison is done based on the performance and resource utilization. Proposed model reduces the need for memory to store seed value and the power utilization. Reseeding can mainly be applied for BIST which targets complete fault coverage and minimization of the test length. Data compression for reducing the test pattern required for testing will indirectly reduce the time required to check the circuits. Future work is to reduce time required for the test pattern generation. Hamming distance can be applied to calculate the number of bits changing during the test patterns transition. Hamming distance approach can be implemented to reduce the parameter.","PeriodicalId":194369,"journal":{"name":"2019 International Conference on Communication and Signal Processing (ICCSP)","volume":"76 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114335257","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: 20

Modified Cylindrical Shaped Dielectric Resonator Antenna for Multiple Applications 多用途改进型圆柱形介质谐振器天线

2019 International Conference on Communication and Signal Processing (ICCSP) Pub Date : 2019-04-04 DOI: 10.1109/ICCSP.2019.8698055

S. Anusuya, T. Shanmuganantham

引用次数: 2

Design of Smart Helmet for Accident Avoidance 面向事故规避的智能头盔设计

2019 International Conference on Communication and Signal Processing (ICCSP) Pub Date : 2019-04-04 DOI: 10.1109/ICCSP.2019.8698000

A. Jesudoss, R. Vybhavi, B. Anusha

引用次数: 37

Classification of Pitch Disguise Level with Artificial Neural Networks 基于人工神经网络的基音伪装等级分类

2019 International Conference on Communication and Signal Processing (ICCSP) Pub Date : 2019-04-04 DOI: 10.1109/ICCSP.2019.8697975

Thiramdas Narendra, Athulya M S, Sathidevi P S

引用次数: 4

Deep Learning based Automated Billing Cart 基于深度学习的自动计费车

2019 International Conference on Communication and Signal Processing (ICCSP) Pub Date : 2019-04-04 DOI: 10.1109/ICCSP.2019.8697995

N. Ragesh, B. Giridhar, D. Lingeshwaran, P. Siddharth, K. Peeyush

引用次数: 11

Performance Analysis of 6T SRAM Cell on Planar and FinFET Technology 基于平面和FinFET技术的6T SRAM单元性能分析

2019 International Conference on Communication and Signal Processing (ICCSP) Pub Date : 2019-04-04 DOI: 10.1109/ICCSP.2019.8697928

Aswathy A Kumar, Anu Chalil

引用次数: 9

A Printed Antenna with LTE/GSM/UMTS/WLAN and Wi-MAX Bands for Automotive Applications 用于汽车应用的LTE/GSM/UMTS/WLAN和Wi-MAX频段的印刷天线

2019 International Conference on Communication and Signal Processing (ICCSP) Pub Date : 2019-04-04 DOI: 10.1109/ICCSP.2019.8698042

S. Pradheepa, T. Shanmuganantham

引用次数: 1