本文为美国罗切斯特理工学院（作者：Anshuman Vikram Singh）的硕士论文，共44页。

基于内容的图像检索（CBIR）系统是针对用户输入查询图像的低层次视觉特征而设计的，这使得用户很难进行查询，也无法给出令人满意的检索结果。在过去，图像标注被认为是CBIR的最佳可能系统，其工作原理是自动为图像分配关键字，以帮助图像检索用户根据这些关键字查询图像。图像标注通常被视为图像分类问题，其中图像由一些低级特征表示，低级特征与高级概念（类标签）之间的映射是由监督学习算法完成的。在CBIR系统中，学习有效的特征表示和相似性度量对于检索性能非常重要。语义鸿沟一直是这个问题的关键挑战。机器捕获的低级图像像素与人类感知的高级语义之间存在较大的语义鸿沟。最近在解决计算机视觉应用中的深度学习技术，特别是卷积神经网络（CNN）的成功，启发了我在这篇论文中的工作，以解决使用标注图像数据集的CBIR问题。

A content-based image retrieval (CBIR)system works on the low-level visual features of a user input query image,which makes it difficult for the users to formulate the query and also does notgive satisfactory retrieval results. In the past image annotation was proposedas the best possible system for CBIR which works on the principle of automaticallyassigning keywords to images that help image retrieval users to query imagesbased on these keywords. Image annotation is often regarded as the problem ofimage classification where images are represented by some low-level featuresand the mapping between low-level features and high-level concepts (classlabels) is done by supervised learning algorithms. In a CBIR system learning ofeffective feature representations and similarity measures is very important forthe retrieval performance. Semantic gap has been the key challenge for thisproblem. A semantic gap exists between low-level image pixels captured bymachines and the high-level semantics perceived by humans. The recent successesof deep learning techniques especially Convolutional Neural Networks (CNN) insolving computer vision applications has inspired me to work on this thesis soas to solve the problem of CBIR using a dataset of annotated images.

1 引言

2 项目背景

2.1 项目相关工作

3 已有方法回顾

3.1 词袋

3.2 假设

3.3 方法评估

4 算法结构概述

4.1 卷积神经网络

4.2 数据集

4.3 训练神经网络

4.4 系统设计

5 算法分析

5.1 实验

5.2 评估

6 结论

6.1 未来工作

附录A 检索结果展示

下载英文原文地址：

http://page2.dfpan.com/fs/elcj8221c29146c3812/  

更多精彩文章请关注微信号：