基于卷积神经网络的图像识别算法研究  

Research on image recognition algorithm based on convolutional neural networks

作　　者：张荣磊[1] 田爱奎[1] 谭浩[1] 郑睿 ZHANG Rong-Lei TIAN Ai-kui TAN Hao ZHENG Rui(School of Computer Science and Technology, Shandong University of Technology, Zibo 255049, Chin)

机构地区：[1]山东理工大学计算机科学与技术学院,山东淄博255049

出　　处：《山东理工大学学报（自然科学版）》2018年第1期48-50,共3页Journal of Shandong University of Technology:Natural Science Edition

摘　　要：针对卷积神经网络在自然图像识别上的局限性,提出一种适用于自然图像识别的卷积神经网络算法,使其在自然图像识别的准确率和速度上取得更好的效果.首先利用MAPREDUCE实现算法的并行化,并利用GPU技术对该算法进行加速;再次利用多区域的逻辑回归计算方法提高图像识别的准确率.在实验环境下验证了改进算法的正确性和有效性.According to the limitation of the convolutional neural network in natural image recog- nition, a convolution neural network algorithm for natural image recognition is proposed. So that the accuracy and speed can achieve better results. Firstly, the parallelism of the algorithm is a- chieved by using MAPREDUCE, and the algorithm is accelerated by using GPU technology~ Sec- ondly, the method of multi region logistic regression is used to improve the accuracy of image recognition; Finally, the correctness and effectiveness of the improved algorithm are verified in the experimental environment.

关 键 词：卷积神经网络 自然图像 逻辑回归 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]