Performance evaluation of wavelet scattering network in image texture classification in various color spaces

07/24/2014
by   Jiasong Wu, et al.
0

Texture plays an important role in many image analysis applications. In this paper, we give a performance evaluation of color texture classification by performing wavelet scattering network in various color spaces. Experimental results on the KTH_TIPS_COL database show that opponent RGB based wavelet scattering network outperforms other color spaces. Therefore, when dealing with the problem of color texture classification, opponent RGB based wavelet scattering network is recommended.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset