Rotation-Invariant Feature Learning via Convolutional Neural Network With Cyclic Polar Coordinates Convolutional Layer

Convolutional neural networks (CNNs) have been demonstrated to be powerful tools to automatically learn effective features from large datasets. Though features learned in CNNs are approximately scale-, translation-, and position-invariant, and their capacity in dealing with image rotations remains limited. In this article, a novel cyclic polar coordinate convolutional layer (CPCCL) is proposed for CNNs to handle the problem of rotation invariance for feature learning. First, the proposed CPCCL converts rotation variation into translation variation using polar coordinates transformation, which can easily be handled by CNNs. Moreover, cyclic convolution is designed to completely handle the translation variation converted from rotation variation by conducting convolution in a cyclic shift mode. Note that the proposed CPCCL is capable of generalization and can be used as a preprocessing layer for classification CNNs to learn the rotation-invariant feature. Extensive experiments over three benchmark datasets demonstrate that the proposed CPCCL can clearly handle the rotation-sensitive problem in traditional CNNs and outperforms several state-of-the-art rotation-invariant feature learning algorithms.

Automated summary

This article proposes a novel cyclic polar coordinate convolutional layer (CPCCL) for CNNs to handle the problem of rotation invariance. The CPCCL converts rotation variation into translation variation using polar coordinates transformation, and employs cyclic convolution to handle the translation variation. Experimental results demonstrate that the proposed CPCCL can effectively handle the rotation-sensitive problem in traditional CNNs and outperforms several state-of-the-art rotation-invariant feature learning algorithms.