圖像特征表示的學(xué)習(xí)算法研究
[Abstract]:In many computer vision tasks, one of the intrinsic difficulties is to generate well-discriminatory image representation, i.e. high-performance image features. Since image features are robust enough to deal with intra-class variations and discriminant enough to deal with inter-class variations, designing excellent image features is a challenging task. Image features are generally divided into image block hierarchical features and image level features (i.e. local features and global features), the former is used to describe an image block and the latter is used to describe a complete image. The main research results are summarized as follows: (1) Firstly, a new image layer feature representation is proposed for image classification. The traditional Bag-of-Words model completely discards the spatial distribution information of features and loses some discriminant power. Spatial Correlogram (SCR) is a feature representation method, which describes the spatial distribution of local features by capturing the frequency of common occurrence of visual word pairs in the spatial range, thus improving the discriminant ability of image recognition. In addition, we combine the correlation graph features with the spatial pyramid model to generate a hybrid feature. Detailed experiments on the scene/object database show that the proposed correlation graph features and hybrid features can achieve higher image classification accuracy than the traditional word packet model. (2) Secondly, this paper proposes a new image classification method. Efficient Kernel Descriptor (EKD) is a new feature representation of image blocks. The design of image block features also belongs to the basic research content in the field of computer vision. Excellent image block feature representation can effectively improve the performance of image classification, object recognition and other related algorithms, but artificially designed images. Kernel Descriptor (KD) method provides a new way to generate image block features. Kernel Principal Component Analysis (KPCA) method is applied to feature representation based on matching kernel functions between image blocks. However, this method needs all joint basis vectors to generate kernel descriptor features, which results in high time complexity. Therefore, we design an efficient kernel descriptor algorithm. The algorithm is based on the incomplete Cholesky decomposition and automatically selects a small number of Pivot associations. The experimental results show that the efficient kernel descriptor (EKD) achieves better performance than the original kernel descriptor (KD) in image / scene classification applications. (3) Thirdly, on the basis of constructing an efficient kernel descriptor (EKD), we propose a new image layer feature representation, which is efficient. Efficient Hierarchical Kernel Descriptor (EHKD). Primitive Kernel Descriptor (KD) features can only be used to describe image blocks, so Bo et al. proposed Hierarchical Kernel Descriptor (HI KD) to describe the whole image in the framework of kernel descriptor (KD) algorithm. The construction process is similar to that of the kernel descriptor (KD), so the generation hierarchical kernel descriptor (HKD) algorithm will also encounter the computational efficiency problem in the generation kernel descriptor (KD) algorithm. To overcome this problem, we design an efficient hierarchical kernel descriptor algorithm. The experimental results show that the efficient hierarchical kernel descriptor (EHKD) has advantages over the hierarchical kernel descriptor (HKD) in computational efficiency and feature representation ability. (4) Finally, a supervised image block feature representation is proposed. Supervised Efficient Kernel Descriptor (SEKD). The previously mentioned kernel descriptor (KD) methods and efficient kernel descriptor (EKD) methods belong to the category of unsupervised learning. They design block-level features through similarity between image blocks and display them. Compared with the hand-designed image block features, these two methods give the interpretation of gradient-oriented histogram from the point of view of kernel, and use the information of pixels to "grow" the image block hierarchical features. Considering the label information of the image block itself, it is necessary to design a feature learning method which integrates the label information of the image in supervised mode. For this reason, we propose an efficient kernel descriptor algorithm based on supervised learning. The algorithm is based on the incomplete Cholesky decomposition algorithm which integrates the label information of the image class. Supervised Learning Efficient Kernel Descriptor (SEKD) has the advantage of shorter representation dimension and stronger discriminant ability than unsupervised learning.
【學(xué)位授予單位】:北京交通大學(xué)
【學(xué)位級別】:博士
【學(xué)位授予年份】:2016
【分類號】:TP391.41
【相似文獻】
相關(guān)期刊論文 前10條
1 陳芳;一種基于錯切原理的圖像旋轉(zhuǎn)方法[J];淮陰師范學(xué)院學(xué)報(自然科學(xué)版);2004年04期
2 李少芳;陳德禮;;數(shù)字圖像旋轉(zhuǎn)實現(xiàn)的探討[J];計算機與現(xiàn)代化;2007年09期
3 李峰;;交互式、可控制圖像旋轉(zhuǎn)[J];電腦編程技巧與維護;2008年09期
4 趙琰;魏為民;;用于圖像認證和竄改檢測的穩(wěn)健圖像摘要[J];計算機應(yīng)用研究;2011年05期
5 王濱海;許正飛;陳西廣;張海龍;邵瑞雪;;圖像旋轉(zhuǎn)算法的分析與對比[J];光學(xué)與光電技術(shù);2011年02期
6 陶德元,李舒平,周激流;消除圖像旋轉(zhuǎn)失真的方法[J];數(shù)據(jù)采集與處理;1991年04期
7 李偉青;圖像旋轉(zhuǎn)的快速顯示技術(shù)[J];計算機應(yīng)用研究;1994年03期
8 沈定剛,,戚飛虎;任意圖像的主方向定位[J];上海交通大學(xué)學(xué)報;1995年04期
9 曹建;變換圖像及與其它圖像程序的結(jié)合使用技術(shù)[J];軟件世界;1996年06期
10 丁宏慶;數(shù)字圖像旋轉(zhuǎn)的硬件實現(xiàn)[J];電子技術(shù);1998年12期
相關(guān)會議論文 前4條
1 魯傳運;黃言平;季托;;圖像旋轉(zhuǎn)不變特征特性研究[A];第九屆全國光電技術(shù)學(xué)術(shù)交流會論文集(下冊)[C];2010年
2 唐振軍;王朔中;魏為民;張新鵬;;利用分塊相似系數(shù)構(gòu)造感知圖像Hash[A];第八屆全國信息隱藏與多媒體安全學(xué)術(shù)大會湖南省計算機學(xué)會第十一屆學(xué)術(shù)年會論文集[C];2009年
3 王彥錕;劉方;;一種快速穩(wěn)健的圖像旋轉(zhuǎn)角度估計算法[A];計算機技術(shù)與應(yīng)用進展·2007——全國第18屆計算機技術(shù)與應(yīng)用(CACIS)學(xué)術(shù)會議論文集[C];2007年
4 王炳健;樓紅斌;盧剛;劉上乾;;多模光電圖像配準(zhǔn)算法性能評估[A];2011西部光子學(xué)學(xué)術(shù)會議論文摘要集[C];2011年
相關(guān)重要報紙文章 前3條
1 奇妙天堂;PowerPoint XP玩轉(zhuǎn)圖象輕松做[N];中國電腦教育報;2003年
2 曉峰;EPC圖像轉(zhuǎn)換專家:批量轉(zhuǎn)換的得力助手[N];中國攝影報;2005年
3 小鴨;掃描一點通[N];電腦報;2001年
相關(guān)博士學(xué)位論文 前4條
1 謝博捚;圖像特征表示的學(xué)習(xí)算法研究[D];北京交通大學(xué);2016年
2 林春雨;圖像/視頻的多描述編碼及傳輸[D];北京交通大學(xué);2010年
3 高光勇;基于混沌和圖像矩的魯棒零水印技術(shù)研究[D];南京郵電大學(xué);2012年
4 李長松;空間太陽望遠鏡穩(wěn)像系統(tǒng)中圖像相關(guān)器的研究[D];中國科學(xué)院研究生院(國家天文臺);2008年
相關(guān)碩士學(xué)位論文 前10條
1 劉霞;基于尺度不變與視覺顯著特征的圖像感知哈希技術(shù)研究[D];西南大學(xué);2015年
2 史力如;圖像與思維及重疊圖像式繪畫的探索[D];天津美術(shù)學(xué)院;2015年
3 王開芳;照片/素描及跨年齡階段異質(zhì)人臉的識別研究[D];山東大學(xué);2015年
4 董愛萍;小尺度圖像旋轉(zhuǎn)失真分析與矯正方法研究[D];大連海事大學(xué);2015年
5 袁征帆;基于安卓的火車客票管理系統(tǒng)的設(shè)計與實現(xiàn)[D];南京大學(xué);2014年
6 黃韻;基于詞袋模型和詞匯樹的圖像檢索技術(shù)研究[D];西安電子科技大學(xué);2014年
7 王東旭;基于快速檢索的圖像溯源軟件平臺[D];西安電子科技大學(xué);2014年
8 孫潔;基于隱支持向量機模型的個性化圖像推薦和檢索[D];北京交通大學(xué);2014年
9 宋寶林;基于圖像特征的圖像哈希算法及實現(xiàn)[D];山東師范大學(xué);2014年
10 石晟;普通光照下葉片圖像特征信息抽取[D];北京林業(yè)大學(xué);2014年
本文編號:2183454
本文鏈接:http://sikaile.net/shoufeilunwen/xxkjbs/2183454.html