상세정보
학술대회
Convolutional Neural Network for Implementing a 2D Median Filter
- 발행일
- 202110
- 출처
- International Conference on Information and Communication Technology Convergence (ICTC) 2021, pp.290-292
- 협약과제
- 21IH1200, 근현대 미술품들의 디지털 데이터 확보 및 과학 기반 미술품 신뢰도 분석 지원 시스템 개발, 김진서
- 초록
- While traditional neural networks could not solve the 'exclusive or' (XOR) problem, it is known that current ones took the place of the universal Turing machine with the same level of computational capability. However, there was not enough vigorous research on how to construct neural networks to solve specific computational problems. Median filter is a nonlinear local signal processing technique that reduces noise from the original signal. It conducts more complicated operations compared to solving an XOR problem. In this paper, we developed a new neural network that performs 2D median filtering and conducted experiments by applying it to a variety of image data sets. Experimental results showed that the proposed XOR neural network could conduct median filtering with more than 99% accuracy. We observed that the accuracy is improved as the sizes of input images increase and also found that the accuracy was better for artificially created random images than natural images.
- KSP 제안 키워드
- 2D Median Filter, Computational capability, Convolution neural network(CNN), Data sets, Image data, Local signal, Median Filtering, Processing technique, Signal Processing, Universal Turing machine, Xor problem