基于弱监督E2LSH和显著图加权的目标分类方法

在目标分类领域，当前主流的目标分类方法是基于视觉词典模型，而时间效率低、视觉单词同义性和歧义性及单词空间信息的缺失等问题严重制约了其分类性能。针对这些问题，该文提出一种基于弱监督的精确位置敏感哈希(E2LSH)和显著图加权的目标分类方法。首先，引入E2LSH算法对训练图像集的特征点聚类生成一组视觉词典，并提出一种弱监督策略对E2LSH中哈希函数的选取进行监督，以降低其随机性，提高视觉词典的区分性。然后，利用GBVS(Graph-Based Visual Saliency)显著度检测算法对图像进行显著度检测，并依据单词所处区域的显著度值为其分配权重；最后，利用显著图加权的视觉语言模型完成目标分类。在数据集Caltech-256和Pascal VOC 2007上的实验结果表明，所提方法能够较好地提高词典生成效率，提高目标表达的分辨能力，其目标分类性能优于当前主流方法。

Object Classification Method Based on Weakly Supervised E2LSH and Saliency Map Weighting

The most popular approach in object classification is based on the bag of visual-words model. However, there are several fundamental problems that restricts the performance of this method, such as low time efficiency, the synonym and polysemy of visual words, and the lack of spatial information between visual words. In view of this, an object classification method based on weakly supervised Exact Euclidean Locality Sensitive Hashing (E2LSH) and saliency map weighting is proposed. Firstly, E2LSH is employed to generate a group of visual dictionary by clustering SIFT features of the training dataset, and the selecting process of hash functions is effectively supervised inspired by the random forest ideas to reduce the randomcity of E2LSH. Secondly, Graph-Based Visual Saliency (GBVS) algorithm is applied to detect the saliency map of different images and visual words are weighted according to the saliency prior. Finally, saliency map weighted visual language model is carried out to accomplish object classification. Experimental results on datasets of Caltech-256 and Pascal 2007 indicate that the distinguishability of objects is effectively improved and the proposed method is superior to the state- of-the-art object classification methods.