Font Size: a A A

Researches On Face Recognition Method Based On GLBC And Its Application In The Criminal Information Acquisition And Exchange System

Posted on:2017-11-20Degree:MasterType:Thesis
Country:ChinaCandidate:J F WangFull Text:PDF
GTID:2348330542461867Subject:Software engineering
Abstract/Summary:PDF Full Text Request
With the development of Internet and information technology,the criminal technique has become more and more hidden and advanced,which make the solving case more difficultly.It also brings new challenges to face recognition,how to improve recognition in a complex environment is one of the hot researches.According to the shortcoming of Gabor features,a improved feature extraction algorithm is proposed in this paper.Then,the new feature extraction algorithm is applied to the criminal investigation information system.The main work is given as following:1.Gabor transform can extract multi-scale and multi-dimensional spatial frequency characteristics of specific area of the image,and it is robust to the changes of face.However,the dimension of characteristic describe operator constructed in the traditional Gabor algorithm is too high,which will affect the matching efficiency of the algorithm.According to the shortcoming of Gabor features,a improved feature extraction algorithm GLBC is proposed in this paper.The GLBC combines the Gabor and LBC features for reducing the feature dimensionality.The chi-square distance are applied to evaluate the similarity of two feature vectors and the decision level fusion method is used to obtain the final recognition result of the whole test images.The effectiveness of the proposed method is verified by experiments on CAS-PEAL-R1,AR and FERET databases.The experimental results show that our method has better recognition performance than other classical face recognition methods.And it is well robust to variations in expression,light conditions,occlusion and facial pose,especially in occlusion.2.The criminal investigation information system architecture design,the system uses C/S three layer structure,including the presentation layer,logic layer,data layer.The presentation layer provides the user friendly interface of face dating system,the business logic layer provides the business processing combination and the service processing service,the data layer provides the data access interface and the data,and uses the MySQL to carry on the database development.This system enables exchange of information between the police integrated platform and the criminal investigation system,and efficiently avoid the consumption of valuable information.
Keywords/Search Tags:Face recognition, Feature extraction, Gabor features, LBC
PDF Full Text Request
Related items