基于阈值分割法和卷积神经网络的图像识别算法  

Image Recognition Algorithm Based on Threshold Segmentation Method and Convolutional Neural Network

作　　者：李鹏松[1] 李俊达 吴良武 胡建平[1] LI Pengsong;LI Junda;WU Liangwu;HU Jianping(College of Sciences,Northeast Electric Power University,Jilin 132012,Jilin Province,China;Dalian Institute of Test and Control Technology,Dalian 116013,Liaoning Province,China)

机构地区：[1]东北电力大学理学院,吉林吉林132012 [2]大连测控技术研究所,辽宁大连116013

出　　处：《吉林大学学报（理学版）》2020年第6期1436-1442,共7页Journal of Jilin University:Science Edition

基　　金：国家自然科学基金(批准号:61672149)。

摘　　要：针对传统卷积神经网络严重依赖数据量的问题,提出一种基于均值迭代阈值分割法和卷积神经网络的图像识别算法,通过均值迭代阈值分割法过滤图像背景,并基于AlexNet构造新的卷积神经网络.与其他常用的卷积神经网络进行对比实验结果表明,在样本数量不足的图像识别任务中,该算法识别效果较理想,与其他卷积神经网络相比,具有更高的识别准确度、更低的识别误差和更快的收敛速度.Aiming at the problem that traditional convolutional neural network relied heavily on the amount of data,we proposed an image recognition algorithm based on mean iterative threshold segmentation method and convolutional neural network.The image background was filtered by means iterative threshold segmentation method,and a new convolutional neural network was constructed based on AlexNet.Compared with other commonly used convolutional neural networks,the experimental results show that the recognition effect of the proposed algorithm is ideal in image recognition tasks with insufficient samples,and it has higher recognition accuracy,lower recognition error and faster convergence rate than that of other convolutional neural networks.

关 键 词：图像识别 阈值分割法 卷积神经网络 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]