Efficient Implementation of a Recognition System Using the Cortex Ventral Stream Model

TL;DR

This paper presents an optimized implementation of the HMAX visual recognition model that improves accuracy and reduces computational complexity through targeted enhancements at multiple processing layers.

Contribution

It introduces specific optimizations for the HMAX model layers, including illumination removal, Gabor filter convolution, and efficient prototype generation, enhancing performance on visual recognition tasks.

Findings

Over 10% accuracy improvement at S1 layer

Reduced computational complexity overall

Slight accuracy increases at C1 and S2 layers

Abstract

In this paper, an efficient implementation for a recognition system based on the original HMAX model of the visual cortex is proposed. Various optimizations targeted to increase accuracy at the so-called layers S1, C1, and S2 of the HMAX model are proposed. At layer S1, all unimportant information such as illumination and expression variations are eliminated from the images. Each image is then convolved with 64 separable Gabor filters in the spatial domain. At layer C1, the minimum scales values are exploited to be embedded into the maximum ones using the additive embedding space. At layer S2, the prototypes are generated in a more efficient way using Partitioning Around Medoid (PAM) clustering algorithm. The impact of these optimizations in terms of accuracy and computational complexity was evaluated on the Caltech101 database, and compared with the baseline performance using support vector machine (SVM) and nearest neighbor (NN) classifiers. The results show that our model provides significant improvement in accuracy at the S1 layer by more than 10% where the computational complexity is also reduced. The accuracy is slightly increased for both approximations at the C1 and S2 layers.