Sparse representation scheme with enhanced medium pixel intensity for face recognition

作     者：Xuexue Zhang Yongjun Zhang Zewei Wang Wei Long Weihao Gao Bob Zhang 

作者机构：State Key Laboratory of Public Big DataInstitute for Artificial IntelligenceCollege of Computer Science and TechnologyGuizhou UniversityGuiyangGuizhouChina Department of Computer and Information ScienceUniversity of MacaoAvenida da UniversidadeTaipaMacaoChina 

出 版 物：《CAAI Transactions on Intelligence Technology》 (智能技术学报（英文）)

年 卷 期：2024年第9卷第1期

页      面：116-127页

核心收录：

学科分类：08[工学] 080203[工学-机械设计及理论] 0802[工学-机械工程] 

基　　金：Guizhou University  GZU 

主　　题：computer vision face recognition image classification image representation 

摘      要：Sparse representation is an effective data classification algorithm that depends on the known training samples to categorise the test *** has been widely used in various image classification *** in sparse representation means that only a few of instances selected from all training samples can effectively convey the essential class-specific information of the test sample,which is very important for *** deformable images such as human faces,pixels at the same location of different images of the same subject usually have different ***,extracting features and correctly classifying such deformable objects is very ***,the lighting,attitude and occlusion cause more *** the problems and challenges listed above,a novel image representation and classification algorithm is ***,the authors’algorithm generates virtual samples by a non-linear variation *** method can effectively extract the low-frequency information of space-domain features of the original image,which is very useful for representing deformable *** combination of the original and virtual samples is more beneficial to improve the clas-sification performance and robustness of the ***,the authors’algorithm calculates the expression coefficients of the original and virtual samples separately using the sparse representation principle and obtains the final score by a designed efficient score fusion *** weighting coefficients in the score fusion scheme are set entirely ***,the algorithm classifies the samples based on the final *** experimental results show that our method performs better classification than conventional sparse representation algorithms.