2019-03-13

Histogram of Oriented Gradient Based Gist Feature for Building Recognition

This paper introduced a new method which is named the histogram of oriented gradient based gist (HOG-gist). 

The traditional one uses the Gabor filters with four angles and four different scales to extract orientation gist feature vectors from an image.

However, the new method uses the normalized histogram of oriented gradient as orientation gist feature vectors of the same image. These HOG-based orientation gist vectors, combined with intensity and color gist feature vectors, are the proposed HOG-gist vectors.

The writer used four methods to compare the results of the old and new way which includes LLP, NPE, PCA, MFA. All of the test ways show that the proposed way is better than the old one.