吉首大学学报（自然科学版）2016，Vol.37Issue(3)：28-33,6.DOI:10.3969/j.cnki.jdxb.2016.03.007
一种分区BP人工神经网络图像差值算法
Regional Image Interpolation Algorithms with Back-Propagation Artificial Neural Network
摘要
Abstract
In order to improve the quality of image interpolation,back-propagation artificial neural net-work (BP-ANN)with self-learning,adaptive and generalization ability has been used to carry out the re-gional image interpolation research.Missing pixel in image is divided into smooth region and edge region, each region corresponding to a BP-ANN interpolation operation.To identify the topology structure,sam-pling mode and the interpolation process of regional BP-ANN,three experiments were performed.The experimental results show that best balance between CPU-time consumption and visual quality lies in 8-1 6-1 topology of BP-ANN;compared with the classical LA interpolation algorithm,our proposed algo-rithm provides 0.593 8 dB higher PSNR while performed better visual quality.关键词
插值/前向反馈人工神经网络/线性均值插值/峰值性噪比/网络拓扑Key words
interpolation/back propagation artificial neural network/linear average interpolation/peak sig-nal to noise radio/network topology分类
信息技术与安全科学引用本文复制引用
钱育蓉,于炯,英昌甜,杨兴耀..一种分区BP人工神经网络图像差值算法[J].吉首大学学报（自然科学版）,2016,37(3):28-33,6.基金项目
国家自然科学基金资助项目（61462079，61363083，61262088）；新疆维吾尔自治区青年博士科技人才创新项目（2013731004）；新疆维吾尔自治区高校科研计划项目（XJEDU2012I10）；新疆维吾尔自治区自然科学基金资助项目 （）
