基于BP神经网络的竹片正反面识别算法  

The Algorithm of Identifying the Front Side of Bamboo Based on BP Neural Network

作　　者：王冬旭[1] 宋树祥[1] 蒋品群[1] 

机构地区：[1]广西师范大学电子工程学院,广西桂林541004

出　　处：《广西师范大学学报（自然科学版）》2014年第2期14-19,共6页Journal of Guangxi Normal University:Natural Science Edition

基　　金：国家自然科学基金资助项目(61061006);广西区研究生创新计划项目(YCSW2012060)

摘　　要：针对竹片自动检测领域中竹片正反面识别率低的问题,提出基于BP神经网络的竹片正反面识别算法,构建并训练一个三层的3输入1输出的BP神经网络模型;提取竹片的2个纹理特征和灰度值特征值,输入经过训练的神经网络模型,计算预测的识别结果。实验结果表明:基于BP神经网络的竹片正反面识别算法在最小风险的原则下的反面识别率为97%;正面的识别率为98%;稳定性明显高于单一特征识别的稳定性。In order to improve the low rate of detecting the front side of a bamboo in chip in the bambooautomatic detection field, the paper present an algorithm of identifying the front side of the bamboo chipbased on BP neural network. A model of BP neural network wa built with three layers of three input andone output. The operation flow is as follow： extract the front and reverse side＇s textural features andcharacteristic value of gray value, then import these data into the trained model, and at last calculate thepredicting results. The experiment results show that the algorithm can identify 96% of the reverse sideand 95% of the front side under the principle of minimum risk. Therefore, the stability of the algorithmis stronger than any other method with signal feature.

关 键 词：竹片正反面 神经网络 纹理特征 灰度特征 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]