MomentsNet: a simple learning-free method for binary image recognition
This work addresses binary image recognition for computer vision applications, but it is incremental as it adapts existing moments into a network structure.
The authors tackled binary image recognition by proposing MomentsNet, a learning-free deep network using moments kernels, and found that ZernikeNet outperformed both traditional moments and the learning-based PCANet in recognition tasks.
In this paper, we propose a new simple and learning-free deep learning network named MomentsNet, whose convolution layer, nonlinear processing layer and pooling layer are constructed by Moments kernels, binary hashing and block-wise histogram, respectively. Twelve typical moments (including geometrical moment, Zernike moment, Tchebichef moment, etc.) are used to construct the MomentsNet whose recognition performance for binary image is studied. The results reveal that MomentsNet has better recognition performance than its corresponding moments in almost all cases and ZernikeNet achieves the best recognition performance among MomentsNet constructed by twelve moments. ZernikeNet also shows better recognition performance on binary image database than that of PCANet, which is a learning-based deep learning network.