Face Image Recognition Algorithm based on Singular Value Decomposition

Tang, Jiakang; Chen, Lin; Pan, Zhenggao; Tan, Cheng-Fang; Li, Shanshan; Wang, Weijie

doi:10.1109/dsa56465.2022.00098

Cited by 1 publication

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This paper is further extended and modified from our paper Face Image Recognition Algorithm based on Singular Value Decomposition [1] presented at the DSA National Conference. Face recognition is the use of computer processing problems to compare different face images to find the same image, a process that requires matching externally acquired data with known data.…”

Section: Introductionmentioning

confidence: 99%

Face Image Recognition Algorithm Based on Label Complementation

Jiakang Tang,

Lin Cui

2023

Journal of Internet Technology

View full text Add to dashboard Cite

<p>In face image recognition, labels play a fairly important role in recognition and classification, and rich and perfect labels can greatly improve the accuracy rate. However, it is almost impossible for the labels in the image to be recognized to describe the image completely and accurately. At the same time, the data obtained when feature extraction is performed on an image inevitably extracts a large amount of redundant and useless information at the same time, which affects the generalization performance of the model. Accordingly, we propose a face image recognition algorithm based on label completion in multi label learning. First, the SVD algorithm is used to remove redundant and useless information from the features of the original data by dimensionality reduction operation to obtain simplified sample attribute information, and the label completion algorithm is used to supplement the labels of the images using the extracted feature information. Finally the obtained label data as complete as possible is put into the extreme learning machine to construct the face recognition model and give the prediction results of the images. Experiments on the ORL dataset demonstrate that the algorithm can achieve good recognition results.</p> <p> </p>

show abstract

Section: Introductionmentioning

confidence: 99%