Feeding Hand-Crafted Features for Enhancing the Performance of Convolutional Neural Networks

TL;DR

This paper demonstrates that incorporating hand-crafted Gabor filter features with CNN inputs can significantly improve performance in face-related tasks like age estimation, face detection, and emotion recognition.

Contribution

The study introduces a method of feeding Gabor filter responses alongside images into CNNs, showing improved results over traditional image-only inputs.

Findings

Enhanced accuracy in face-related tasks using combined features

Gabor filter responses improve CNN performance

Tuning Gabor parameters further boosts results

Abstract

Since the convolutional neural network (CNN) is be- lieved to find right features for a given problem, the study of hand-crafted features is somewhat neglected these days. In this paper, we show that finding an appropriate feature for the given problem may be still important as they can en- hance the performance of CNN-based algorithms. Specif- ically, we show that feeding an appropriate feature to the CNN enhances its performance in some face related works such as age/gender estimation, face detection and emotion recognition. We use Gabor filter bank responses for these tasks, feeding them to the CNN along with the input image. The stack of image and Gabor responses can be fed to the CNN as a tensor input, or as a fused image which is a weighted sum of image and Gabor responses. The Gabor filter parameters can also be tuned depending on the given problem, for increasing the performance. From the extensive experiments, it is shown that the proposed methods provide better performance than the conventional CNN-based methods that use only the input images.