Fast Neuromimetic Object Recognition using FPGA Outperforms GPU Implementations

TL;DR

This paper demonstrates that a modified HMAX model for visual object recognition can be efficiently implemented on FPGA hardware, achieving high processing speeds with minimal accuracy loss, outperforming GPU implementations.

Contribution

The authors adapt the biologically-inspired HMAX model for FPGA deployment, enabling real-time object recognition at high speeds with minimal accuracy compromise.

Findings

Recognition rate of 190 images/sec on FPGA

Less than 1% accuracy loss compared to traditional HMAX

Outperforms GPU implementations in speed

Abstract

Recognition of objects in still images has traditionally been regarded as a difficult computational problem. Although modern automated methods for visual object recognition have achieved steadily increasing recognition accuracy, even the most advanced computational vision approaches are unable to obtain performance equal to that of humans. This has led to the creation of many biologically-inspired models of visual object recognition, among them the HMAX model. HMAX is traditionally known to achieve high accuracy in visual object recognition tasks at the expense of significant computational complexity. Increasing complexity, in turn, increases computation time, reducing the number of images that can be processed per unit time. In this paper we describe how the computationally intensive, biologically inspired HMAX model for visual object recognition can be modified for implementation on a commercial Field Programmable Gate Array, specifically the Xilinx Virtex 6 ML605 evaluation board with XC6VLX240T FPGA. We show that with minor modifications to the traditional HMAX model we can perform recognition on images of size 128x128 pixels at a rate of 190 images per second with a less than 1% loss in recognition accuracy in both binary and multi-class visual object recognition tasks.