HOG feature extraction

Status
Not open for further replies.

emerson_11

Member level 2
Joined
Jan 23, 2016
Messages
44
Helped
1
Reputation
2
Reaction score
1
Trophy points
8
Activity points
355
I want to train my support vector machine to classify human vs non human using matlab. In training phase am getting a large feature vector matrix around 1*335214 for a single human image. Is there a way to reduce the feature vector size or to select the location of human alone?
 

Status
Not open for further replies.
Cookies are required to use this site. You must accept them to continue using the site. Learn more…