【摘要】：隨著計(jì)算機(jī)技術(shù)和人工智能的不斷普及,圖像的應(yīng)用領(lǐng)域非常廣泛,其中圖像特征提取占據(jù)重要的主導(dǎo)地位,也是當(dāng)前計(jì)算機(jī)視覺(jué)領(lǐng)域中熱門(mén)的研究課題之一。在過(guò)去的研究中,局部特征的深入研究推動(dòng)了整個(gè)計(jì)算機(jī)視覺(jué)領(lǐng)域的快速發(fā)展,其中最著名的局部二值模式(LBP)是局部特征中一種非常簡(jiǎn)單高效的局部描述子。自L(fǎng)BP提出來(lái)之后,受到眾多研究者的追崇,改良的算法被應(yīng)用于各種計(jì)算機(jī)視覺(jué)和模式識(shí)別領(lǐng)域中,包括紋理分類(lèi)、人臉識(shí)別、目標(biāo)檢測(cè)等。但是各種LBP算法仍會(huì)存在一定的缺陷和瓶頸,如LBP構(gòu)造的直方圖向量長(zhǎng)度過(guò)長(zhǎng),旋轉(zhuǎn)不變能力不夠突出,噪聲魯棒性還不夠強(qiáng)等問(wèn)題。為了增強(qiáng)LBP的鑒別能力,提升抗噪聲的魯棒性,本文對(duì)紋理分類(lèi)中所用到的關(guān)鍵技術(shù)進(jìn)行了深入研究后,提出了一些新算法,并應(yīng)用到特定的紋理數(shù)據(jù)庫(kù)進(jìn)行驗(yàn)證。另外,Contourlet變換繼承了Curvlet變換的各向異性的多尺度關(guān)系,能夠提取圖像的內(nèi)在幾何特征,因此本文也提出了基于Contourlet變換的紋理分類(lèi)方法,并應(yīng)用于紙幣識(shí)別中。本文的主要工作和貢獻(xiàn)如下:1、系統(tǒng)研究了紋理分類(lèi)中較著名的紋理特征提取算法,如LBP、CLBP、DLBP、SCLBP等局部二值模式描述子,詳細(xì)陳述了它們的工作實(shí)現(xiàn)原理,分析它們的優(yōu)勢(shì)和需要改進(jìn)的地方,并介紹它們所應(yīng)用的典型領(lǐng)域。2、研究了局部二值模式的改進(jìn)算法。針對(duì)LBP的鑒別能力和抗噪能力較弱,本文在前人研究的基礎(chǔ)上,對(duì)BRINT的提取識(shí)別算法進(jìn)行改進(jìn),提出一種新的基于BRINT的尺度不變特征提取方法,通過(guò)BRINT的尺度不變空間分析,可以得到最優(yōu)的尺度不變特征,并用不同的紋理數(shù)據(jù)庫(kù)進(jìn)行驗(yàn)證,得到較好的效果。首先,LBP描述子解決了旋轉(zhuǎn)不變和灰度不變特性,但在尺度不變特性方面沒(méi)有得到很好解決。我們提出的方法正好解決了這個(gè)瓶頸。其次,不同于其他傳統(tǒng)的局部尺度不變特征,我們不需要估計(jì)局部的尺度,而僅僅使用了全局描述子去實(shí)現(xiàn)尺度不變特性。最后,我們將直方圖橫跨不同尺度空間,最終取每個(gè)分量最大值,并整合成一個(gè)最優(yōu)直方圖,實(shí)現(xiàn)尺度不變特性。這種新的方案在紋理數(shù)據(jù)庫(kù)中能得到一定的提升效果。3、研究了基于Contourlet變換和統(tǒng)計(jì)特性的紙幣紋理分類(lèi)。首先介紹紙幣識(shí)別的基本現(xiàn)狀,詳細(xì)介紹contourlet變換的工作原理以及相關(guān)的變種,隨后利用contourlet變換分解出來(lái)的頻率子帶進(jìn)行模式統(tǒng)計(jì)特征提取,結(jié)合灰度共生矩陣方法,采用基于支持向量機(jī)(SVM)方法實(shí)現(xiàn)了紙幣紋理分類(lèi)。最后與相關(guān)的方法比較,驗(yàn)證本文算法的可行性。
[Abstract]:With the popularization of computer technology and artificial intelligence, the application of image is very extensive. Image feature extraction plays an important role in the field of computer vision, and it is also one of the hot research topics in the field of computer vision. In the past, the in-depth study of local features has promoted the rapid development of the whole field of computer vision. The most famous local binary pattern (LBP) is a very simple and efficient local descriptor in local features. Since LBP was proposed by many researchers, the improved algorithm has been applied to various fields of computer vision and pattern recognition, including texture classification, face recognition, target detection and so on. However, there are still some defects and bottlenecks in various LBP algorithms, such as long histogram vector length constructed by LBP, insufficient rotation invariant ability, and insufficient noise robustness. In order to enhance the discriminative ability of LBP and enhance the robustness of anti-noise, the key techniques used in texture classification are deeply studied in this paper, and some new algorithms are proposed, which are applied to a specific texture database for verification. In addition, Contourlet transform inherits the anisotropic multi-scale relation of Curvlet transform and can extract the intrinsic geometric feature of image. Therefore, a texture classification method based on Contourlet transform is proposed and applied to paper currency recognition. The main work and contributions of this paper are as follows: 1. The famous texture feature extraction algorithms in texture classification, such as local binary pattern descriptors such as LBP,CLBP,DLBP,SCLBP, are systematically studied, and their implementation principles are described in detail. This paper analyzes their advantages and needs to be improved, and introduces the typical field. 2, and studies the improved algorithm of local binary pattern. Aiming at the weak discriminant ability and anti-noise ability of LBP, this paper improves the extraction and recognition algorithm of BRINT on the basis of previous research, and proposes a new scale-invariant feature extraction method based on BRINT, which is analyzed by scale invariant space of BRINT. The optimal scale invariant features can be obtained and verified by different texture databases, and good results can be obtained. First, the LBP descriptor solves the rotation invariance and gray invariance, but it is not well solved in the scale invariance. The method we put forward just solves this bottleneck. Secondly, unlike other traditional local scale invariants, we do not need to estimate local scales, but only use global descriptors to realize scale invariants. Finally, we take the maximum value of each component across different scale spaces, and integrate the histogram into an optimal histogram to realize the scale-invariant property. This new scheme can get a certain improvement effect in texture database. The paper studies the paper currency texture classification based on Contourlet transform and statistical characteristics. This paper first introduces the basic status of banknote recognition, introduces in detail the working principle of contourlet transform and its related variants, then extracts the statistical features of patterns by using the frequency subbands decomposed by contourlet transform, and combines with the method of gray level co-occurrence matrix. The paper currency texture classification is realized based on support vector machine (SVM) (SVM) method. Finally, compared with the related methods, the feasibility of the algorithm is verified.
【學(xué)位授予單位】：廣東工業(yè)大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類(lèi)號(hào)】：TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前7條

1 董健衛(wèi);陳艷美;;淺析多進(jìn)制小波及其應(yīng)用[J];科技視界;2015年04期

2 盛國(guó)瑞;高鐵杠;曹雁軍;高琳;范禮;;基于脊波變換的圖像篡改檢驗(yàn)算法[J];光電子.激光;2013年02期

3 孫君頂;馬媛媛;;紋理特征研究綜述[J];計(jì)算機(jī)系統(tǒng)應(yīng)用;2010年06期

4 劉麗;匡綱要;;圖像紋理特征提取方法綜述[J];中國(guó)圖象圖形學(xué)報(bào);2009年04期

5 劉曉民;;紋理研究及其應(yīng)用綜述[J];測(cè)控技術(shù);2008年05期

6 張志龍;李吉成;沈振康;;局部傅里葉變換系數(shù)各階矩的紋理鑒別性能分析[J];中國(guó)圖象圖形學(xué)報(bào);2006年01期

7 洪繼光;;灰度-梯度共生矩陣紋理分析方法[J];自動(dòng)化學(xué)報(bào);1984年01期

相關(guān)碩士學(xué)位論文 前2條

1 祝平平;離散余弦變換快速算法的研究[D];華中科技大學(xué);2008年

2 薛玉利;基于Gabor變換的特征提取及其應(yīng)用[D];山東大學(xué);2007年

，

本文編號(hào)：2238639