A Handcrafted Normalized-Convolution Network for Texture Classification

Abstract

In this paper, we propose a Handcrafted NormalizedConvolution Network (NmzNet) for efficient texture classification. NmzNet is implemented by a three-layer normalized convolution network, which computes successive normalized convolution with a predefined filter bank (Gabor filter bank) and modulus non-linearities. Coefficients from different layers are aggregated by Fisher Vector aggregation to form the final discriminative features. The results of experimental evaluation on three texture datasets UIUC, KTH-TIPS-2a, and KTH-TIPS-2b indicate that our proposed approach achieves the good classification rate compared with other handcrafted methods. The results additionally indicate that only a marginal difference exists between the best classification rate of recent frontiers CNN and that of the proposed method on the experimented datasets.

Boosting Texture-Based Classification by Describing Statistical Information of Gray-Levels Differences

“…To the best of our knowledge, the best result has been yielded by by LFV+FC-CNN [ 52 ], an approach where deep features are extracted. The second and third positions are obtained by another deep features approach NmzNet [ 53 ], followed by a handcrafted one, IFV [ 54 ].…”