Human eye inspired log-polar pre-processing for neural networks
This addresses the need for more efficient and robust image processing in CNNs, though it is incremental as it builds on existing pre-processing techniques.
The paper tackles the problem of achieving rotation and scale robustness in convolutional neural networks (CNNs) by introducing a bio-inspired log-polar pre-processing step, which reduces image size to ~20% of the original without significantly compromising classification accuracy.
In this paper we draw inspiration from the human visual system, and present a bio-inspired pre-processing stage for neural networks. We implement this by applying a log-polar transformation as a pre-processing step, and to demonstrate, we have used a naive convolutional neural network (CNN). We demonstrate that a bio-inspired pre-processing stage can achieve rotation and scale robustness in CNNs. A key point in this paper is that the CNN does not need to be trained to identify rotation or scaling permutations; rather it is the log-polar pre-processing step that converts the image into a format that allows the CNN to handle rotation and scaling permutations. In addition we demonstrate how adding a log-polar transformation as a pre-processing step can reduce the image size to ~20\% of the Euclidean image size, without significantly compromising classification accuracy of the CNN. The pre-processing stage presented in this paper is modelled after the retina and therefore is only tested against an image dataset. Note: This paper has been submitted for SAUPEC/RobMech/PRASA 2020.