基于深度卷积神经网络和二进制哈希学习的图像检索方法

Image Retrieval Based on Deep Convolutional Neural Networks and Binary Hashing Learning

随着图像数据的迅猛增长,当前主流的图像检索方法采用的视觉特征编码步骤固定,缺少学习能力,导致其图像表达能力不强,而且视觉特征维数较高,严重制约了其图像检索性能。针对这些问题,该文提出一种基于深度卷积神径网络学习二进制哈希编码的方法,用于大规模的图像检索。该文的基本思想是在深度学习框架中增加一个哈希层,同时学习图像特征和哈希函数,且哈希函数满足独立性和量化误差最小的约束。首先,利用卷积神经网络强大的学习能力挖掘训练图像的内在隐含关系,提取图像深层特征,增强图像特征的区分性和表达能力。然后,将图像特征输入到哈希层,学习哈希函数使得哈希层输出的二进制哈希码分类误差和量化误差最小,且满足独立性约束。最后,给定输入图像通过该框架的哈希层得到相应的哈希码,从而可以在低维汉明空间中完成对大规模图像数据的有效检索。在3个常用数据集上的实验结果表明,利用所提方法得到哈希码,其图像检索性能优于当前主流方法。

With the increasing amount of image data, the image retrieval methods have several drawbacks, such as the low expression ability of visual feature, high dimension of feature, low precision of image retrieval and so on. To solve these problems, a learning method of binary hashing based on deep convolutional neural networks is proposed, which can be used for large-scale image retrieval. The basic idea is to add a hash layer into the deep learning framework and to learn simultaneously image features and hash functions should satisfy independence and quantization error minimized. First, convolutional neural network is employed to learn the intrinsic implications of training images so as to improve the distinguish ability and expression ability of visual feature. Second, the visual feature is putted into the hash layer, in which hash functions are learned. And the learned hash functions should satisfy the classification error and quantization error minimized and the independence constraint. Finally, an input image is given, hash codes are generated by the output of the hash layer of the proposed framework and large scale image retrieval can be accomplished in low-dimensional hamming space. Experimental results on the three benchmark datasets show that the binary hash codes generated by the proposed method has superior performance gains over other state-of-the-art hashing methods.