无监督深度学习彩色图像识别方法  

Unsupervised deep learning method for color image recognition

作　　者：康晓东[1] 王昊[2] 郭军[1] 于文勇[1] 

机构地区：[1]天津医科大学医学影像学院,天津300070 [2]河北大学附属医院介入科,河北保定071000

出　　处：《计算机应用》2015年第9期2636-2639,共4页journal of Computer Applications

摘　　要：针对彩色图像分类识别的重要性,提出了一种结合图像特征数据和深度信任网络(DBN)的彩色图像识别方法。首先,构造符合人类视觉特性的图像色彩数据场;其次,以小波变换描述图像的多尺度特征;最后,通过无监督训练深度信任网络实现对图像的识别。实验结果表明,所提方法与Adaboost、支持向量机(SVM)方法比较,分类准确率分别提高约3.7%和2.8%,可有效提高图像识别效果。In view of significance of color image recognition, the method of color image recognition based on data of image features and Deep Belief Network （DBN） was presented. Firstly, data field of color image was constructed in accord with human visual characteristics; secondly, wavelet transforms was applied to describe multi-scale feature of image; finally, image recognition could be made by training unsupervised DBN. The experimental results show that compared with the methods of Adaboost and Support Vector Machine（ SVM）, classification accuracy is improved by 3.7% and 2.8% respectively and better image recognition is achieved by the proposed method.

关 键 词：图像识别 深度信任网络 受限玻尔兹曼机 计算机视觉 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]