FPGA Implementation of Complex-Valued Neural Network for Polar-Represented Image Classification

This proposed research explores a novel approach to image classification by deploying a complex-valued neural network (CVNN) on a Field-Programmable Gate Array (FPGA), specifically for classifying 2D images transformed into polar form. The aim of this research is to address the limitations of existi...

Full description

Bibliographic Details
Main Authors: Maruf Ahmad, Lei Zhang, Muhammad E. H. Chowdhury
Format: Article
Language:English
Published: MDPI AG 2024-01-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/24/3/897
_version_ 1797318156771917824
author Maruf Ahmad
Lei Zhang
Muhammad E. H. Chowdhury
author_facet Maruf Ahmad
Lei Zhang
Muhammad E. H. Chowdhury
author_sort Maruf Ahmad
collection DOAJ
description This proposed research explores a novel approach to image classification by deploying a complex-valued neural network (CVNN) on a Field-Programmable Gate Array (FPGA), specifically for classifying 2D images transformed into polar form. The aim of this research is to address the limitations of existing neural network models in terms of energy and resource efficiency, by exploring the potential of FPGA-based hardware acceleration in conjunction with advanced neural network architectures like CVNNs. The methodological innovation of this research lies in the Cartesian to polar transformation of 2D images, effectively reducing the input data volume required for neural network processing. Subsequent efforts focused on constructing a CVNN model optimized for FPGA implementation, emphasizing the enhancement of computational efficiency and overall performance. The experimental findings provide empirical evidence supporting the efficacy of the image classification system developed in this study. One of the developed models, CVNN_128, achieves an accuracy of 88.3% with an inference time of just 1.6 ms and a power consumption of 4.66 mW for the classification of the MNIST test dataset, which consists of 10,000 frames. While there is a slight concession in accuracy compared to recent FPGA implementations that achieve 94.43%, our model significantly excels in classification speed and power efficiency—surpassing existing models by more than a factor of 100. In conclusion, this paper demonstrates the substantial advantages of the FPGA implementation of CVNNs for image classification tasks, particularly in scenarios where speed, resource, and power consumption are critical.
first_indexed 2024-03-08T03:48:25Z
format Article
id doaj.art-0085f28cb6cd4c3898314c1fc042f41a
institution Directory Open Access Journal
issn 1424-8220
language English
last_indexed 2024-03-08T03:48:25Z
publishDate 2024-01-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj.art-0085f28cb6cd4c3898314c1fc042f41a2024-02-09T15:22:11ZengMDPI AGSensors1424-82202024-01-0124389710.3390/s24030897FPGA Implementation of Complex-Valued Neural Network for Polar-Represented Image ClassificationMaruf Ahmad0Lei Zhang1Muhammad E. H. Chowdhury2Faculty of Engineering and Applied Science, University of Regina, Regina, SK S4S 0A2, CanadaFaculty of Engineering and Applied Science, University of Regina, Regina, SK S4S 0A2, CanadaDepartment of Electrical Engineering, Qatar University, Doha 2713, QatarThis proposed research explores a novel approach to image classification by deploying a complex-valued neural network (CVNN) on a Field-Programmable Gate Array (FPGA), specifically for classifying 2D images transformed into polar form. The aim of this research is to address the limitations of existing neural network models in terms of energy and resource efficiency, by exploring the potential of FPGA-based hardware acceleration in conjunction with advanced neural network architectures like CVNNs. The methodological innovation of this research lies in the Cartesian to polar transformation of 2D images, effectively reducing the input data volume required for neural network processing. Subsequent efforts focused on constructing a CVNN model optimized for FPGA implementation, emphasizing the enhancement of computational efficiency and overall performance. The experimental findings provide empirical evidence supporting the efficacy of the image classification system developed in this study. One of the developed models, CVNN_128, achieves an accuracy of 88.3% with an inference time of just 1.6 ms and a power consumption of 4.66 mW for the classification of the MNIST test dataset, which consists of 10,000 frames. While there is a slight concession in accuracy compared to recent FPGA implementations that achieve 94.43%, our model significantly excels in classification speed and power efficiency—surpassing existing models by more than a factor of 100. In conclusion, this paper demonstrates the substantial advantages of the FPGA implementation of CVNNs for image classification tasks, particularly in scenarios where speed, resource, and power consumption are critical.https://www.mdpi.com/1424-8220/24/3/897image classificationcomplex-valued neural networkFPGA implementationCVNN on FPGA
spellingShingle Maruf Ahmad
Lei Zhang
Muhammad E. H. Chowdhury
FPGA Implementation of Complex-Valued Neural Network for Polar-Represented Image Classification
Sensors
image classification
complex-valued neural network
FPGA implementation
CVNN on FPGA
title FPGA Implementation of Complex-Valued Neural Network for Polar-Represented Image Classification
title_full FPGA Implementation of Complex-Valued Neural Network for Polar-Represented Image Classification
title_fullStr FPGA Implementation of Complex-Valued Neural Network for Polar-Represented Image Classification
title_full_unstemmed FPGA Implementation of Complex-Valued Neural Network for Polar-Represented Image Classification
title_short FPGA Implementation of Complex-Valued Neural Network for Polar-Represented Image Classification
title_sort fpga implementation of complex valued neural network for polar represented image classification
topic image classification
complex-valued neural network
FPGA implementation
CVNN on FPGA
url https://www.mdpi.com/1424-8220/24/3/897
work_keys_str_mv AT marufahmad fpgaimplementationofcomplexvaluedneuralnetworkforpolarrepresentedimageclassification
AT leizhang fpgaimplementationofcomplexvaluedneuralnetworkforpolarrepresentedimageclassification
AT muhammadehchowdhury fpgaimplementationofcomplexvaluedneuralnetworkforpolarrepresentedimageclassification