Toward Optimal FPGA Implementation of Deep Convolutional Neural Networks for Handwritten Hangul Character Recognition

Hanwool Park; Yechan Yoo; Yoonjin Park; Changdae Lee; Hakkyung Lee; Injung Kim; Kang Yi

doi:10.5626/JCSE.2018.12.1.24

주제분류

...

저널정보

한국정보과학회
Journal of Computing Science and Engineering 학술저널
Journal of Computing Science and Engineering Vol.12 No.1
2018.3 24 - 35 (12page)
DOI : 10.5626/JCSE.2018.12.1.24

저자정보

Hanwool Park (Handong Global University)
Yechan Yoo (Handong Global University)
Yoonjin Park (Handong Global University)
Changdae Lee (Handong Global University)
Hakkyung Lee (Handong Global University)

이용수
내서재: 1

내서재에 추가
되었습니다. 내서재에서
삭제되었습니다.

초록·키워드

오류제보하기

Deep convolutional neural network (DCNN) is an advanced technology in image recognition. Because of extreme computing resource requirements, DCNN implementation with software alone cannot achieve real-time requirement. Therefore, the need to implement DCNN accelerator hardware is increasing. In this paper, we present a field programmable gate array (FPGA)-based hardware accelerator design of DCNN targeting handwritten Hangul character recognition application. Also, we present design optimization techniques in SDAccel environments for searching the optimal FPGA design space. The techniques we used include memory access optimization and computing unit parallelism, and data conversion. We achieved about 11.19 ms recognition time per character with Xilinx FPGA accelerator. Our design optimization was performed with Xilinx HLS and SDAccel environment targeting Kintex XCKU115 FPGA from Xilinx. Our design outperforms CPU in terms of energy efficiency (the number of samples per unit energy) by 5.88 times, and GPGPU in terms of energy efficiency by 5 times. We expect the research results will be an alternative to GPGPU solution for real-time applications, especially in data centers or server farms where energy consumption is a critical problem.

#Deep convolutional neural networks #Deep learning accelerator #FPGA optimal design #Hangul character recognition