Effects of Gabor Filters on Classification Performance of CNNs Trained on a Limited Number of Conditions

TL;DR

This paper investigates how Gabor filters as a preprocessing step can enhance the generalization and reduce the size of CNNs trained on limited condition data, inspired by the visual nervous system.

Contribution

It introduces the use of Gabor filters as a preprocessor to improve CNN accuracy and compactness when trained on limited visual data for robot vision.

Findings

Gabor filters improve CNN generalization performance.

Preprocessing with Gabor filters reduces CNN size.

Enhanced robustness to limited condition variations.

Abstract

In this study, we propose a technique to improve the accuracy and reduce the size of convolutional neural networks (CNNs) running on edge devices for real-world robot vision applications. CNNs running on edge devices must have a small architecture, and CNNs for robot vision applications involving on-site object recognition must be able to be trained efficiently to identify specific visual targets from data obtained under a limited variation of conditions. The visual nervous system (VNS) is a good example that meets the above requirements because it learns from few visual experiences. Therefore, we used a Gabor filter, a model of the feature extractor of the VNS, as a preprocessor for CNNs to investigate the accuracy of the CNNs trained with small amounts of data. To evaluate how well CNNs trained on image data acquired under a limited variation of conditions generalize to data acquired under other conditions, we created an image dataset consisting of images acquired from different camera positions, and investigated the accuracy of the CNNs that trained using images acquired at a certain distance. The results were compared after training on multiple CNN architectures with and without Gabor filters as preprocessing. The results showed that preprocessing with Gabor filters improves the generalization performance of CNNs and contributes to reducing the size of CNNs.