基于中层特征的精细图像分类-论文分解.doc

基于中层特征的精细图像分类 摘 要 现如今，图像处理中目标分类与检测越来越多的得到了人们的关注与研究。目标分类一般分为两种，一种是基础图像分类，另一种是越来越受到人们关注的精细图像分类。基础图像分类是为了区分具有不同形状以及视觉特征的物体（例如给出一个鸟的图片，基础图像分类就是为了要区分出这张图片是鸟的图片还是狗的图片）。精细图像分类则是要区分具有相似形状以及外貌特征的物体（例如给出一副鸟的图片，精细分类就是要判断出这只鸟究竟属于哪一类鸟）。在这篇文章中，我们主要研究了图像的精细分类问题，在现实生活中它比图像的基础分类更加具有实用性。我们所使用的数据库是目前比较有挑战性的CUB-200以及Stanford_Dogs数据库。 我们结合了高效匹配核函数（EMK）与带有权重的空间金字塔以达到最优的分类表现。实验用EMK与词包（BoW）作对比，其中，BoW也可以看做是一种核函数匹配方法，EMK是找出词表主要成分的相互关系，并且在核函数的框架中找到一种新的映射。EMK是通过映射，将局部特征映射到一个低维的特征空间并且将结果向量平均化以形成一个特征层集合。实验结果表明，这可以很好的改进系统的性能。 关键词：高效匹配核函数（EMK）；词包（BoW）；细粒度图像分类 ABSTRACT In recent days, object classification and detection in image processing are getting more and more attention and research. Object classification include two sides, one is basic classification, another is fine-grained classification which attract more and more people to study. basic classification is to classify the object which have the different shapes and visual appearance(e.g.: for a picture of bird,the basic classification is to identify the object in the picture is a bird or dog ). Fine-grained classification is to classification the object with the similar shapes and visual appearance(e.g.: for a picture of bird,the fine-grained classification is to identify which kind of birds it belongs to). In this paper, we study the problem of fine-grained image categorization, which is much more useful in real applications than basic image classification. Based on the most challenge dataset, CUB-200, Stanford_Dogs_Dataset. We combine Efficient match kernel (EMK) with the weighted spatial pyramid to achieve state-of-art performance. Comparison with BoW, which can also be viewed as kernel matching approach, EMK digs the relations among vocabulary bases and finds a new mapping in kernel framework. By it, local features are mapped to a low dimensional feature space and average the resulting vectors to form a set level feature in EMK. It is proved that it is helpful to improve the system performance. 第1章 绪论 1.1精细图像分类的研究背景及意义 伴随着网络和多媒体技术的飞速发展，越来