Open AccessFace Recognition with Frame size reduction and DCT compression using PCA algorithm
Author(s) -
Padmaja vijaykumar,
Jeevan K. Mani
Publication year - 2021
Publication title -
indonesian journal of electrical engineering and computer science
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.241
H-Index - 17
eISSN - 2502-4760
pISSN - 2502-4752
DOI - 10.11591/ijeecs.v22.i1.pp168-178
Subject(s) - discrete cosine transform , facial recognition system , classifier (uml) , computer science , salient , artificial intelligence , pattern recognition (psychology) , face (sociological concept) , raw data , data compression , reduction (mathematics) , computer vision , mathematics , image (mathematics) , social science , sociology , programming language , geometry
Face recognition has become a very important study of research because it has a variety of applications in research field such as human computer interaction, pattern recognition (PR). A successful face recognition procedure, be it mathematical or numerical, depends on the particular choice of the features used by the classifier. Feature selection in pattern recognition consists of the derivation of salient features present in the raw input data in order to reduce the amount of data used for classification. For the successful face recognition, the database images must have sufficient information so that when presented with the probe image, the recognition must be possible. Majority of times, there is always excess information present in the database images, leads higher storage, hence optimum size of the images needs to be stored in the database for good performance, are compressed with reduction in frame size and then compressed with that of the DCT.