DOI QR코드

DOI QR Code

Binary CNN Operation Algorithm using Bit-plane Image

비트평면 영상을 이용한 이진 CNN 연산 알고리즘

  • Choi, Jong-Ho (Department of IoT Electronic Engineering, Kangnam University)
  • Received : 2019.10.16
  • Accepted : 2019.11.20
  • Published : 2019.12.31

Abstract

In this paper, we propose an algorithm to perform convolution, pooling, and ReLU operations in CNN using binary image and binary kernel. It decomposes 256 gray-scale images into 8 bit planes and uses a binary kernel consisting of -1 and 1. The convolution operation of binary image and binary kernel is performed by addition and subtraction. Logically, it is a binary operation algorithm using the XNOR and comparator. ReLU and pooling operations are performed by using XNOR and OR logic operations, respectively. Through the experiments to verify the usefulness of the proposed algorithm, We confirm that the CNN operation can be performed by converting it to binary logic operation. It is an algorithm that can implement deep running even in a system with weak computing power. It can be applied to a variety of embedded systems such as smart phones, intelligent CCTV, IoT system, and autonomous car.

본 논문에서는 이진영상과 이진커널을 사용하여 컨볼루션, 풀링, ReLU 연산을 수행하는 이진 CNN 연산 알고리즘을 제안한다. 256 그레이스케일 영상을 8개의 비트평면으로 분해하고, -1과 1로 구성되는 이진커널을 사용하는 방법이다. 이진영상과 이진커널의 컨볼루션 연산은 가산과 감산으로 수행한다. 논리적으로는 XNOR 연산과 비교기로 구성되는 이진연산 알고리즘이다. ReLU와 풀링 연산은 각각 XNOR와 OR 논리연산으로 수행한다. 본 논문에서 제안한 알고리즘의 유용성을 증명하기 위한 실험을 통해, CNN 연산을 이진 논리연산으로 변환하여 수행할 수 있음을 확인한다. 이진 CNN 알고리즘은 컴퓨팅 파워가 약한 시스템에서도 딥러닝을 구현할 수 있는 알고리즘으로 스마트 폰, 지능형 CCTV, IoT 시스템, 자율주행 자동차 등의 임베디드 시스템에서 다양하게 적용될 수 있는 시스템이다.

Keywords

References

  1. Y. LeCun, K. Kavukcuoglu, and C. Farabet, "Convolutional networks and applications in vision," International Symposium in Circuits and Systems (ISCAS), IEEE, 2010.
  2. Alex Krizhevsky, Ilya Sutskever, and Geoffrey E. Hinton, "ImageNet Classification with Deep Convolutional Neural Networks," Advances in Neural Information processing Systems 25, NIPS, 2012.
  3. H. Lee, R. Grosse, R. Ranganath, and A.Y. Ng., "Convolutional deep belief networks for scalable unsupervised learning of hierarchical represent ations," Proceedings of the 26th Annual International Conference on Machine Learning, ACM, 2009.
  4. Jong-Ho Choi, "Algorithm of Morphological Multimode Binary Shape Decomposition," Journal of KITE, Vol. 36S, No. September, April, 1999.
  5. Jong-Ho Choi, "Parallel-Addition Con volution Algorithm in Grayscale Image," Journal of KIIECT, Vol. 10, No. 4, August, 2017.
  6. Rastegari, Mohammad, et al.,"Xnor-net: Imagenet classification using binary convolutional neural networks." European Conference on Computer Vision. Springer, Cham, 2016.
  7. HUBARA, Itay, et al. "Binarized neural networks: Training neural networks with weights and activations constrained to+ 1 or-1." arXiv preprint arXiv:1602.02830, 2016.

Cited by

  1. Concept Drift Based on CNN Probability Vector in Data Stream Environment vol.13, pp.4, 2019, https://doi.org/10.13160/ricns.2020.13.4.147