Classification of Human Ear by Extracting Hog Features and Support Vector Machine

Abstract

The approaches proposed by eminent researchers have been discussed in the previous sections. Survey on the researches says that, it defines the uniqueness of a given person. And it is possible in the biometric authentication to have collisions between two people who have completely biometric character. Gabor filter can represents the frequency and orientation of similar to those of the human visual System, and they have been found to be particularly appropriate for texture representation and as well as discrimination. There will be a great research on the HOG, it is purely gradient based and captured the object shape information; it can be used to extract the global feature. HOG compute edge gradient of whole image and find orientation of each pixel so it can generate histogram easily. Many of them used the Support vector machine for classification because it avoids the over fitting, and it can built kernel and also it is an approximation to a bound on the test error rate. The theory behind SVM suggests that it should a good idea.