基于区分深度置信网络的病害图像识别模型-计算机工程与应用.pdfVIP

32 2017 ，53（21 ） Computer Engineering and Applications 计算机工程与应用 基于区分深度置信网络的病害图像识别模型 用 宋丽娟 应 SONG Lijuan 与 1. 西北大学 信息科学与技术学院，西安 710127 程 2. 宁夏大学 信息工程学院，银川 750021 g r 1.School of Information Science and Technology, Northwest University, Xi ’an 710127, China 工 o 2.School of Information Engineering, Ningxia University, Yinchuan 750021, China . 机 j a SONG Lijuan. Recognition model of disease image based on discriminative deep belief networks. Computer 算 e Engineering and Applications, 2017, 53 （21 ）：32-36. c 计 w. Abstract: To detect and identify the disease of Chinese Wolfberry in time and accurately is very important on the disease monitor, prediction, early warning ，treatment and the construction of agricultural information and intelligence. The deep w architecture of disease image classification and identification is proposed based on discriminative deep belief networks. w First of all, this paper automatically crops the leaf disease image of Chinese Wolfberry into the sub- image containing typical spots, and then researches segmentation under complex background and the image feature extraction, the features is a total of 147 on color feature, texture feature and shape feature. Disease recognition model is established with discrimi- native deep belief networks and exponential loss function. Experimental results show that, the method has good effect on image recognition. Compared with the suppo