重庆理工大学学报（自然科学版）2018，Vol.32Issue(1)：188-194,7.DOI:10.3969/j.issn.1674-8425(z).2018.01.027
基于深度哈希的批量图像并行检索方法
Batch Images Parallel Retrieval Based on Deep Hashing
摘要
Abstract
In view of the accuracy and efficiency of image retrieval is the key problem in content-based image retrieval,a batch images distributed retrieval algorithm based on deep hashing is proposed.Firstly,the image features and hash code extraction model is built by training deep hashing model using the training data.Then,the features and hash codes of images are extracted by the model and stored in the distributed database HBase.Finally,a parallel retrieval method is implemented with Hadoopframework.The experiment on a large scale dataset CIFAR-10 shows that the method is effective.The mean average precision is 60.28%.The accuracy has increased by 12.63%comparing to SIFT,and the average retrieval of an image takes 0.73 s.It can not only solve the problem of massive images storage and fast retrieval,but also improve the accuracy.关键词
图像检索/Hadoop/卷积神经网络/深度哈希/并行检索Key words
image retrieval/Hadoop/convolutional neural network/deep hashing/parallel retrieval分类
信息技术与安全科学引用本文复制引用
熊舒羽,毛雷,刘畅..基于深度哈希的批量图像并行检索方法[J].重庆理工大学学报（自然科学版）,2018,32(1):188-194,7.基金项目
重庆市研究生科研创新项目(CYS16222) （CYS16222）
重庆理工大学研究生创新基金资助项目(YCX2016230) （YCX2016230）
