%0 Journal Article
%T 基于深度学习编码模型的图像分类方法
%A 赵永威
%A 李婷
%A 蔺博宇
%J 工程科学与技术
%D 2017
%R 10.15961/j.jsuese.2017.01.028
%X 中文摘要: 针对矢量量化编码的量化误差严重，而稀疏编码只是一种浅层学习模型，容易导致视觉词典对图像特征缺乏选择性的问题，提出了一种基于深度学习特征编码模型的图像分类方法。首先，采用深度学习网络监督的受限玻尔兹曼机（RBM）代替传统的 K-Means聚类及稀疏编码等方法对SIFT特征库进行编码学习，生成视觉词典；其次，对RBM编码添加正则化项分解组合每个特征的稀疏表示，使得生成的视觉单词兼具稀疏性和选择性；然后，利用训练数据的类别标签信息有监督地自上而下对得到的初始视觉词典进行微调，得到图像深度学习表示向量，以此训练SVM分类器并完成图像分类。实验结果表明，本文方法能有效克服传统矢量量化编码及稀疏编码等方法的缺点，有效地提升图像分类性能。</br>Abstract:For the serious quantization error in vector quantitation coding,the sparse coding is only a shallow learning model which caused the codeword lack selectivity for image features.In this paper,an image classification method based on deep learning coding model was proposed.Firstly,the deep learning network unsupervised RBM was used to encode SIFT features and generate visual dictionary instead of the traditional K-means clustering.Then,the unsupervised RBM learning was steered by using a regularization scheme,which decomposes into a combined prior for the sparsity of each feature's representation as well as the selectivity for each codeword.Finally,the initial dictionary was fine-tuned to be discriminative through the supervised learning from top-down labels.To train SVM classifier and complete image classification,the representation features based on image deep learning were obtained.The experimental results demonstrated that the proposed method can overcome the disadvantage of vector quantization coding and sparse coding.Moreover,the classification performance can be boosted effectively.
%K 图像分类 视觉词典模型 深度学习 稀疏编码 受限玻尔兹曼机&lt
%K /br&gt
%K image classification bag of visual words model deep learning coding model sparse coding restricted Boltzmann machine
%U http://jsuese.ijournals.cn/jsuese_cn/ch/reader/view_abstract.aspx?file_no=201600210&flag=1