Skip to Main Content
The zero-crossing rates (ZCRs) of the wavelet frame representation of texture images are proposed as features for texture classification. Results indicate that ZCR features lower the probability of error (PE) by 40% over energy (EN) and correlation coefficient features. Augmenting ZCR features with EN features improves the PE by 70% over ZCR features alone.
Date of Publication: 24 Oct 2002