Synthesis of Pulsed-Coupled Neural Networks in FPGAs for Real-Time Image Segmentation

Abstract

This paper describes the implementation of a system based on Pulse Coupled Neural Networks (PCNNs) and Field Programmable Gate Arrays (FPGAs). The PCNN implemented is oriented to the industrial application of segmentation in sequences of images. The work went through several real physical stages of implementation and optimization to achieve the needed performance. The greatest performance achieved by the digital system was of 250M pixels per second, enough to process a sequence of images in real time. Details of these stages about the neuron implementation with different Altera's FPGAs families are presented. Furthermore, the implementation is compared with previous implemented schemes based on floating point DSP microprocessor.

The Content-Based Image Retrieval using the Pulse Coupled Neural Network

“…However, the method using PCNN has the advantage that the hardware implementation [20] or calculation using GPGPU is effectively because of its simple configuration and highly parallelism.…”

“…Because of these characteristics of the PCNN, it is effective to implement to the hardware such as a FPGA. The hardware implementation of the PCNN using the FPGA had been studied and shown its validity in [15] preceding study [20].…”

Review of pulse-coupled neural networks

“…Vega-Pineda et al design a system of the PCNN based on the platform of FPGAs. This system can implement real-time image segmentation [133].…”

Hardware implementation of IC-PCNN for the color image segmentation

“…Add to that, in the practical use, it is also expected to implement them to an embedded system. The hardware implementation of the PCNN had been shown in the conventional studies, and recently the FPGA implementation is well studied [13] [14]. The FPGA is a reconfigurable hardware that consists of programmable logic cells and interconnections, and it is well known as a very effective tool for the circuit implementation.…”