彭腾飞,
干宗良
南京邮电大学通信与信息工程学院 南京 210003
基金项目:国家自然科学基金(61501260)，江苏省研究生科研与实践创新计划(KYCX17_0776)
详细信息
作者简介:陈昌红：女，1982年生，副教授，研究方向为智能视频分析、模式识别
彭腾飞：男，1994年生，硕士生，研究方向为图像处理与图像通信
干宗良：男，1978年生，副教授，研究方向为分布式视频编码、图像信号视频处理
通讯作者:陈昌红 chenchh@njupt.edu.cn
中图分类号:TN911.73计量
文章访问数:799
HTML全文浏览量:289
PDF下载量:78
被引次数:0
出版历程
收稿日期:2019-12-09
修回日期:2020-08-09
网络出版日期:2020-08-13
刊出日期:2020-12-08
Aurora Image Classification and Retrieval Method Based on Deep Hashing Algorithm
Changhong CHEN,,Tengfei PENG,
Zongliang GAN
College of Communication and Information Technology, Nanjing University of Posts and Telecommunications, Nanjing 210003, China
Funds:The National Natural Science Foundation of China (61501260), The Postgraduate Research & Practice Innovation Program of Jiangsu Province (KYCX17_0776)
摘要
摘要:面对形态万千、变化复杂的海量极光数据，对其进行分类与检索为进一步研究地球磁场物理机制和空间信息具有重要意义。该文基于卷积神经网络(CNN)对图像特征提取方面的良好表现，以及哈希编码可以满足大规模图像检索对检索时间的要求，提出一种端到端的深度哈希算法用于极光图像分类与检索。首先在CNN中嵌入空间金字塔池化(SPP)和幂均值变换(PMT)来提取图像中多种尺度的区域信息；其次在全连接层之间加入哈希层，将全连接层最能表现图像的高维语义信息映射为紧凑的二值哈希码，并在低维空间使用汉明距离对图像对之间的相似性进行度量；最后引入多任务学习机制，充分利用图像标签信息和图像对之间的相似度信息来设计损失函数，联合分类层和哈希层的损失作为优化目标，使哈希码之间可以保持更好的语义相似性，有效提升了检索性能。在极光数据集和 CIFAR-10 数据集上的实验结果表明，所提出方法检索性能优于其他现有检索方法，同时能够有效用于极光图像分类。
关键词:极光图像/
分类与检索/
卷积神经网络/
哈希编码/
多尺度特征融合
Abstract:It is of great significance to classify and retrieve the vast amount of aurora data with various forms and complex changes for the further study of the physical mechanism of the geomagnetic field and spatial information. In this paper, an end-to-end deep hashing algorithm for aurora image classification and retrieval is proposed based on the good performance of CNN in image feature extraction and the fact that hash coding can meet the retrieval time requirment of large-scale image retrieval. Firstly, Spatial Pyramidal Pooling(SPP) and Power Mean Transformtion(PMT) are embedded in Convolutional Neural Network (CNN) to extract multi-scale region information in the image. Secondly, a Hash layer is added between the fully connected layer to Mean Average Precision(MAP) the high-dimensional semantic information that can best represent the image into a compact binary Hash code, and the hamming distance is used to measure the similarity between the image pairs in the low-dimensional space. Finally, a multi-task learning mechanism is introduced to design the loss fuction by making full use of similarity informtion between the image label information and the image pairs. The loss of classification layer and Hash layer are combined as the optimization objective, so that a better semantic similarity between Hash code can be maintained, and the retrieval performance can be effectively improved. The results show that the proposed method outperforms the state-of-art retrieval algorithms on aurora dataset and CIFAR-10 datasets, and it can also be used in aurora image classification effectively.
Key words:Aurora image/
Classification and retrieval/
Convolutional Neural Network(CNN)/
Hash coding/
Multi-scale feature fusion
PDF全文下载地址:
https://jeit.ac.cn/article/exportPdf?id=4bff465b-05ca-41a4-a225-e922daf3e80d
