MomentsNet: a simple learning-free method for binary image recognition

by   Jiasong Wu, et al.

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.



page 1

page 2

page 3

page 4


A Framework for Moment Invariants

For more than half a century, moments have attracted lot ot interest in ...

On Higher-order Moments in Adam

In this paper, we investigate the popular deep learning optimization rou...

Hyperbolic quadrature method of moments for the one-dimensional kinetic equation

A solution is proposed to a longstanding open problem in kinetic theory,...

Assessment of the Local Tchebichef Moments Method for Texture Classification by Fine Tuning Extraction Parameters

In this paper we use machine learning to study the application of Local ...

Precise Calculation of Electrical Capacitance by means of Quadruple Integrals in Method of Moments Technique

In this paper, the capacitance of a parallel plate air-gap rectangular c...

Using the discrete radon transformation for grayscale image moments

Image moments are weighted sums over pixel values in a given image and a...

Rotation Invariant Descriptors for Galaxy Morphological Classification

The detection of objects that are multi-oriented is a difficult pattern ...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.