24图像哈希模块.docVIP

中图法分类号：TP391 文献标识码：A 文章编号：1006-8961(2016 ) - - 论文引用格式： 目标提取与哈希机制的多标签图像 陈飞，吕绍和，李军，王晓东，窦勇 国防科学技术大学并行与分布处理重点实验室,长沙 410073 摘 要哈希是大规模图像检索的有效方法。为提高检索精度，哈希码应保留语义信息之间越相似，其哈希码也应越接近。现有方法首先提取描述整体的特征，然后生成哈希码。这种方法不能精确地描述包含的多个目标，限制了多标签图像检索的精度。提出一种基于目标提取哈希生成方法首先提取中可能包含目标的一系列区域，然后用深度卷积神经网络提取每个区域的特征并进行融合，生成一组来刻画图中的每个目标。采用Triplet Loss的训练方法，使得哈希码尽可能保留语义信息。在VOC2012Flickr25K和NUSWIDE数据集normalized discounted cumulative gain ）性能指标上，当返回图像数量为 1 000时，对于VOC2012，本文方法相对于DSRH方法提高2~4个百分点，相对于ITQ-CCAIterative quantization-canonical correlation analysis）方法能提高3~6个百分点方法比DSRH能提高2个左右的百分点方法能以更细粒度来精确地描述，显著提高多标签图像检索的性能。 关键词 ：图像检索；卷积神经网络；哈希；多标签 Multi-label Image Retrieval by Hashing with Object Proposal Chen Fei, Lv Shaohe, Li Jun, Wang Xiaodong, Dou Yong National Laboratory for Parallel and Distributed Processing, National University of Defense Technology, Changsha 410073 Abstract: Objective Hashing is an effective means for large-scale image retrieval. Preserving the semantic similarity in hash codes (i.e., the distance between the hash codes of two images) should be small when the images are similar to improve the retrieval performance. Conventional methods first extract the overall image feature and then generate a single hash code. Such methods cannot characterize the image content for multiple objects, which results in a low accuracy of multi-label image retrieval. This study proposes a new hash generation method with object proposals. Method We propose a new deep-network-based framework to construct hash functions that learn directly from images that contain multiple labels. The model first derives a series of interesting regions that may contain objects and then generates the features of each region through deep convolutional neural networks. It finally generates a group of hash codes to describe all the objects in an image. The compact hash code will be generated to represent the entire image. A novel triplet-loss based training method is adopted to preserve the semantic ord