本文選題：經(jīng)驗(yàn)?zāi)B(tài)分解 + 表情識別��； 參考：《長春工業(yè)大學(xué)》2017年碩士論文

【摘要】：現(xiàn)今,黃鍔和他的團(tuán)隊所提出的希爾伯特黃變換(HHT)成為了各大領(lǐng)域的研究熱點(diǎn),HHT方法在1998年提出以來,經(jīng)過國內(nèi)外學(xué)者們的深入研究,取得了一系列的研究成效。經(jīng)驗(yàn)?zāi)B(tài)分解EMD方法是希爾伯特黃變換中最重要的且具有創(chuàng)新性的數(shù)據(jù)處理算法。自適應(yīng)性是EMD算法最主要的特性之一,它主要是將非線性、非平穩(wěn)數(shù)據(jù)序列或信號的進(jìn)行平穩(wěn)化。由于EMD方法的提出以及廣大學(xué)者的廣泛關(guān)注,該算法已經(jīng)快速有效的應(yīng)用在各種的工程領(lǐng)域,并取得一定的研究成果。自適應(yīng)性是EMD算法最主要的特性之一,它主要是將非線性、非平穩(wěn)數(shù)據(jù)序列或信號的進(jìn)行平穩(wěn)化。EMD可把復(fù)雜的數(shù)據(jù)分解成有限的本征模函數(shù)(IMF)和一個趨勢項(xiàng),從而使得瞬時頻率這一概念具有了實(shí)際的物理意義。但是EMD算法存在著模態(tài)混疊的問題。為了克服了這一缺點(diǎn),提出了一種改進(jìn)算法——整體經(jīng)驗(yàn)?zāi)B(tài)分解(EEMD)方法,它是針對EMD方法的缺點(diǎn)而提出的一種噪聲輔助數(shù)據(jù)分析方法。為了將該算法應(yīng)用在圖像處理方面,本文提出了一種基于小波函數(shù)的二維整體經(jīng)驗(yàn)?zāi)B(tài)分解的方法,主要采用小波函數(shù)為二維EEMD算法中的基函數(shù),利用最小二乘法原理實(shí)現(xiàn)自適應(yīng)數(shù)據(jù)擬合。本文以人臉表情圖像為研究對象,證明所提出的算法是可行的并且有效的。本文針以人臉面部表情作為研究對象進(jìn)行研究分析,所研究的人臉表情來源于日本JAFFE人連表情數(shù)據(jù)庫,其中的213個表情來自10個不同的女性。本文利用圖像的尺度歸一化和直方圖均衡化對表情圖像進(jìn)行預(yù)處理,對于處理的結(jié)果,首先進(jìn)行Radon變換,再利用一維經(jīng)驗(yàn)?zāi)B(tài)分解對人臉圖像作進(jìn)一步處理;其次,將預(yù)處理的結(jié)果再進(jìn)行二維經(jīng)驗(yàn)?zāi)B(tài)分解;最后,分別對一維和二維經(jīng)驗(yàn)?zāi)B(tài)分解的結(jié)果采用支持向量機(jī)的方法,將表情特征屬性數(shù)據(jù)進(jìn)行訓(xùn)練分類,對比其分類結(jié)果并進(jìn)行分析,找到更加有效的人臉面部表情都識別的方法。其分析結(jié)果對未來的圖像處理方面,特別是人臉表情識別將會有重要的參考價值。
[Abstract]:Nowadays, HHT proposed by Huang E and his team has become a research hotspot in various fields. Since 1998, the HHT method has been studied deeply by scholars at home and abroad, and a series of research results have been achieved. Empirical mode decomposition (EMD) EMD method is the most important and innovative data processing algorithm in Hilbert-Huang transform. Self-adaptability is one of the most important features of EMD algorithm. It mainly stabilizes nonlinear, non-stationary data sequences or signals. Due to the development of EMD method and the wide attention of many scholars, the algorithm has been applied in various engineering fields quickly and effectively, and some research results have been obtained. Self-adaptability is one of the most important features of EMD algorithm. It can decompose complex data into finite eigenmode function and a trend term by stabilizing nonlinear, non-stationary data sequences or signals. Thus, the concept of instantaneous frequency has practical physical significance. But the EMD algorithm has the problem of modal aliasing. In order to overcome this shortcoming, an improved algorithm, Global empirical Mode decomposition (EMD) method, is proposed, which is a noise-aided data analysis method aiming at the shortcomings of EMD method. In order to apply this algorithm to image processing, this paper presents a method of two-dimensional global empirical mode decomposition based on wavelet function. The wavelet function is used as the basis function of two-dimensional EEMD algorithm. The principle of least square method is used to realize adaptive data fitting. This paper takes facial expression image as the research object, and proves that the proposed algorithm is feasible and effective. In this paper, facial expressions are studied and analyzed. The facial expressions are derived from the JAFFE Human expression Database in Japan, and 213 of them come from 10 different women. In this paper, the scale normalization and histogram equalization of the image are used to preprocess the facial expression image. First, the Radon transform is carried out, then the one-dimensional empirical mode decomposition is used to further process the face image. Finally, the results of one-dimensional and two-dimensional empirical mode decomposition are analyzed by support vector machine (SVM), and the facial expression attribute data are trained and classified. The classification results are compared and analyzed to find a more effective method for facial expression recognition. The analysis results will have important reference value for future image processing, especially for facial expression recognition.
【學(xué)位授予單位】：長春工業(yè)大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 蘆偉東;楊省偉;周平;;EMD算法和Hilbert算法混合的語音信號降噪和提取[J];科技通報;2015年03期

2 艾延廷;馮研研;周海侖;;小波變換和EEMD-馬氏距離的軸承故障診斷[J];噪聲與振動控制;2015年01期

3 茆美琴;龔文劍;張榴晨;曹雨;徐海波;;基于EEMD-SVM方法的光伏電站短期出力預(yù)測[J];中國電機(jī)工程學(xué)報;2013年34期

4 石冶郝;余玉峰;程小紅;;CT掃描中的數(shù)學(xué)——拉東(Radon)變換[J];首都師范大學(xué)學(xué)報(自然科學(xué)版);2013年04期

5 劉海飛;李心丹;;基于EMD方法的股票價格預(yù)測與實(shí)證研究[J];統(tǒng)計與決策;2010年23期

6 萬建;許高鳳;趙春暉;;基于二維EMD的人臉圖像去光照方法研究[J];哈爾濱工程大學(xué)學(xué)報;2009年12期

7 柏春嵐;;基于小波函數(shù)的航空遙感圖像壓縮研究[J];科技廣場;2009年07期

8 秦宇;;應(yīng)用經(jīng)驗(yàn)?zāi)B(tài)分解的上海股票市場價格趨勢分解及周期性分析[J];中國管理科學(xué);2008年S1期

9 任艷斐;;直方圖均衡化在圖像處理中的應(yīng)用[J];科技信息;2007年04期

10 李艷雙,曾珍香,張閩,于樹江;主成分分析法在多指標(biāo)綜合評價方法中的應(yīng)用[J];河北工業(yè)大學(xué)學(xué)報;1999年01期

相關(guān)碩士學(xué)位論文 前2條

1 汪婷;生物醫(yī)學(xué)圖像歸一化及配準(zhǔn)方法研究[D];廣東工業(yè)大學(xué);2013年

2 周振國;二維EMD方法及其在圖像處理中的應(yīng)用研究[D];哈爾濱工程大學(xué);2012年

，

本文編號：1829196