基于尺度空間理論的圖像特征提取技術(shù)研究
發(fā)布時(shí)間：2018-07-29 08:29
【摘要】：隨著圖像特征提取技術(shù)在計(jì)算機(jī)視覺(jué)領(lǐng)域的應(yīng)用越來(lái)越重要,對(duì)能夠提取魯棒性更好,更能反映圖像內(nèi)容屬性的圖像特征的要求越來(lái)越高。與全局特征相比,圖像局部特征對(duì)圖像的幾何與光學(xué)變換(如旋轉(zhuǎn)、尺度、仿射、光照變換等)更魯棒,除此之外,局部特征還具有很高的重復(fù)性,并且不容易受到目標(biāo)遮擋的影響,所以對(duì)圖像局部特征提取技術(shù)的研究越來(lái)越受到重視。在圖像匹配應(yīng)用中,為了提高圖像特征的綜合性能(尺度、仿射不變性、實(shí)時(shí)性),本論文對(duì)圖像局部特征提取技術(shù)做了詳細(xì)的研究和深入分析。本文首先深入研究了尺度空間,在此基礎(chǔ)上詳細(xì)研究了基于尺度空間的圖像特征檢測(cè)算法的基本原理,包括:基于高斯差分算子(Difference of Gaussian,Do G)的SIFT檢測(cè)器,基于高斯尺度空間的Harris-Laplace尺度不變檢測(cè)器以及能夠應(yīng)用于存在仿射變換情況的擴(kuò)展算法Harris-Affine和Hessian-Affine仿射不變特征檢測(cè)器。尺度空間在特征檢測(cè)中的應(yīng)用保證了檢測(cè)到的特征具有尺度不變性以及更好的穩(wěn)定性。并且通過(guò)仿真實(shí)驗(yàn)對(duì)比了各種檢測(cè)算法的性能,基于實(shí)驗(yàn)結(jié)果我們選擇魯棒性最優(yōu)的Hessian-Affine檢測(cè)器作為后續(xù)特征描述的預(yù)處理算法。其次,本文從圖像匹配的角度,深入研究了圖像特征描述算法,包括MROGH,FRDOH和LIOP算法,通過(guò)對(duì)算法原理的研究,得出通過(guò)引入多支撐域思想或者雙梯度直方圖思想能夠提高特征描述符的魯棒性和可區(qū)別力的結(jié)論。但是引入多支撐域構(gòu)造描述符會(huì)增加構(gòu)造過(guò)程所消耗的計(jì)算時(shí)間,降低實(shí)時(shí)性。最后我們提出了一種基于雙梯度方向直方圖的特征描述新方法(DGOH),并且通過(guò)實(shí)驗(yàn)對(duì)DGOH算法與其他算法進(jìn)行比較可以得出,DGOH算法的魯棒性優(yōu)于FRDOH,并且與其他算法相比DGOH具有最優(yōu)的實(shí)時(shí)性能。
[Abstract]:With the application of image feature extraction technology in the field of computer vision, the requirements of image features which can extract better robustness and more reflect the image content attributes are becoming more and more important. Compared with global features, image local features are more robust to geometric and optical transformations (such as rotation, scale, affine, illumination transformation, etc.). In addition, local features are highly reproducible. And it is not easy to be affected by object occlusion, so more and more attention has been paid to local feature extraction. In the application of image matching, in order to improve the comprehensive performance of image features (scale, affine invariance, real-time), this paper makes a detailed study and in-depth analysis of image local feature extraction technology. In this paper, the basic principle of image feature detection algorithm based on scale space is studied in detail, including: SIFT detector based on Gao Si differential operator (Difference of Gaussian do G). Harris-Laplace scale invariant detector based on Gao Si scale space and extended algorithm Harris-Affine and Hessian-Affine affine invariant feature detector which can be applied to the existence of affine transformation. The application of scale space in feature detection ensures that the detected features are scale-invariant and more stable. The performance of various detection algorithms is compared by simulation experiments. Based on the experimental results, we choose the robust Hessian-Affine detector as the preprocessing algorithm for the subsequent feature description. Secondly, from the point of view of image matching, this paper deeply studies image feature description algorithm, including MROGH FRDOH and LIOP algorithm. It is concluded that the robustness and distinguishing force of feature descriptors can be improved by introducing the idea of multi-support domain or double-gradient histogram. But the introduction of multi-support domain construction descriptor will increase the computation time and reduce the real-time performance. Finally, we propose a new feature description method based on double gradient histogram (DGOH),). By comparing the DGOH algorithm with other algorithms, we can conclude that the robustness of DGOH algorithm is better than that of other algorithms, and compared with other algorithms. DGOH has optimal real-time performance.
【學(xué)位授予單位】：哈爾濱工業(yè)大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TP391.41
本文編號(hào)：2152094
[Abstract]:With the application of image feature extraction technology in the field of computer vision, the requirements of image features which can extract better robustness and more reflect the image content attributes are becoming more and more important. Compared with global features, image local features are more robust to geometric and optical transformations (such as rotation, scale, affine, illumination transformation, etc.). In addition, local features are highly reproducible. And it is not easy to be affected by object occlusion, so more and more attention has been paid to local feature extraction. In the application of image matching, in order to improve the comprehensive performance of image features (scale, affine invariance, real-time), this paper makes a detailed study and in-depth analysis of image local feature extraction technology. In this paper, the basic principle of image feature detection algorithm based on scale space is studied in detail, including: SIFT detector based on Gao Si differential operator (Difference of Gaussian do G). Harris-Laplace scale invariant detector based on Gao Si scale space and extended algorithm Harris-Affine and Hessian-Affine affine invariant feature detector which can be applied to the existence of affine transformation. The application of scale space in feature detection ensures that the detected features are scale-invariant and more stable. The performance of various detection algorithms is compared by simulation experiments. Based on the experimental results, we choose the robust Hessian-Affine detector as the preprocessing algorithm for the subsequent feature description. Secondly, from the point of view of image matching, this paper deeply studies image feature description algorithm, including MROGH FRDOH and LIOP algorithm. It is concluded that the robustness and distinguishing force of feature descriptors can be improved by introducing the idea of multi-support domain or double-gradient histogram. But the introduction of multi-support domain construction descriptor will increase the computation time and reduce the real-time performance. Finally, we propose a new feature description method based on double gradient histogram (DGOH),). By comparing the DGOH algorithm with other algorithms, we can conclude that the robustness of DGOH algorithm is better than that of other algorithms, and compared with other algorithms. DGOH has optimal real-time performance.
【學(xué)位授予單位】：哈爾濱工業(yè)大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TP391.41
【參考文獻(xiàn)】
相關(guān)期刊論文 前1條
1 劉美玲;高虎明;;基于Harris-Laplace特征點(diǎn)檢測(cè)抗幾何攻擊的數(shù)字水印算法[J];科學(xué)技術(shù)與工程;2014年10期
相關(guān)博士學(xué)位論文 前3條
1 劉景能;圖像局部不變特征提取技術(shù)及其應(yīng)用研究[D];上海交通大學(xué);2012年
2 高彥彥;基于特征的圖像檢索技術(shù)研究[D];北京郵電大學(xué);2012年
3 胡俊華;圖象局部不變特征及其應(yīng)用研究[D];中國(guó)科學(xué)技術(shù)大學(xué);2009年
相關(guān)碩士學(xué)位論文 前2條
1 劉美玲;基于Harris-Laplace特征點(diǎn)檢測(cè)抗幾何攻擊的數(shù)字水印算法研究[D];天津財(cái)經(jīng)大學(xué);2014年
2 侯毅;圖像局部不變特征提取及應(yīng)用研究[D];國(guó)防科學(xué)技術(shù)大學(xué);2012年
，本文編號(hào)：2152094
本文鏈接：http://sikaile.net/kejilunwen/ruanjiangongchenglunwen/2152094.html
最近更新
教材專著
