A Handcrafted Normalized-Convolution Network for Texture Classification

Vu-Lam Nguyen (1) , Ngoc-Son Vu (1) , Philippe-Henri Gosselin (2, 1)

1 ETIS - UMR 8051 - Equipes Traitement de l'Information et Systèmes
2 MIDI - Multimedia Indexation and Data Integration

In this paper, we propose a Handcrafted Normalized-Convolution 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.

Domains: Computer Vision and Pattern Recognition [cs.CV]

Vu-Lam Nguyen, Ngoc-Son Vu, Philippe-Henri Gosselin. A Handcrafted Normalized-Convolution Network for Texture Classification. Compact and Efficient Feature Representation and Learning in Computer Vision, Oct 2017, Venice, Italy. ⟨hal-01681182⟩