Open AccessThe Method of Cutting Image of Vehicle Face based on Haar Feature and Improved Cascade Classifier
Author(s) -
Tong Zhang,
Li Mao
Publication year - 2019
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1335/1/012018
Subject(s) - haar like features , artificial intelligence , classifier (uml) , pattern recognition (psychology) , computer science , cascade , cascading classifiers , segmentation , haar , computer vision , facial recognition system , feature extraction , face detection , engineering , random subspace method , wavelet , chemical engineering
A method of car face image segmentation based on haar-like features and improved cascade classifier was proposed to solve the problems of insufficient classification recognition performance and too long training time of the current classifier. First, the haar-like features of the image are calculated based on integral graph. Then the extracted feature values are input into the cascade classifier for training. Finally, the trained classifier was used to detect the vehicle face and segment the image of the vehicle face. In this paper an adaptive threshold setting method is proposed. The experimental results show that the method has the better performance than the traditional methods, and has better application prospects.