一種DCT和ELBP融合的人臉特征提取方法
發(fā)布時間：2019-06-21 02:25
【摘要】：僅使用單一算法提取人臉圖像的特征不足以捕捉人臉多方面的信息,為了更好地獲取人臉面部特征,針對離散余弦變換(Discrete Cosine Transform,DCT)只能提取人臉面部圖像的頻域特征,而未考慮近鄰像素之間的關(guān)系、不能提取紋理特質(zhì)信息等問題進(jìn)行了研究,提出一種融合DCT特征和伸長的局部二值模式(Elongated Local Binary Pattern,ELBP)的特征提取方法。該方法首先考慮將人臉圖像經(jīng)DCT變換后的少量低頻系數(shù)作為人臉的頻域特征,然后對人臉圖像中貢獻(xiàn)相對較大的眼部和嘴部區(qū)域進(jìn)行ELBP特征提取,將該ELBP特征作為人臉的空域特征,并采用PCA方法對所提取的空頻域特征進(jìn)行有效融合,得到更有效的人臉特征,最后用最近鄰分類器進(jìn)行識別。在ORL人臉庫和Yale人臉庫上的實(shí)驗(yàn)結(jié)果表明:所提方法比單獨(dú)采用DCT、ELBP方法或采用DCT和LBP相結(jié)合的方法提取的特征更有利于識別,提高了識別的準(zhǔn)確性。
[Abstract]:Using a single algorithm to extract the features of face images is not enough to capture the information of face in many aspects. in order to better obtain face features, discrete cosine transform (Discrete Cosine Transform,DCT) can only extract the frequency domain features of face images, but can not extract texture feature information without considering the relationship between nearest neighbor pixels. A feature extraction method based on local binary pattern (Elongated Local Binary Pattern,ELBP) combining DCT features and extension is proposed. In this method, a small number of low frequency coefficients of face image transformed by DCT are considered as the frequency domain features of face, then the ELBP feature is extracted from the eye and mouth region, and the ELBP feature is regarded as the spatial feature of face. PCA method is used to effectively fuse the extracted space-frequency domain features to obtain more effective face features. Finally, the nearest neighbor classifiers are used for recognition. The experimental results on ORL face database and Yale face database show that the proposed method is more beneficial to recognition and improves the accuracy of recognition than the method of DCT,ELBP alone or the combination of DCT and LBP.
【作者單位】： 蘭州理工大學(xué)計算機(jī)與通信學(xué)院;
【基金】：國家自然科學(xué)基金(No.61263019) 甘肅省高等學(xué)�；究蒲许�(xiàng)目
【分類號】：TP391.41
[Abstract]:Using a single algorithm to extract the features of face images is not enough to capture the information of face in many aspects. in order to better obtain face features, discrete cosine transform (Discrete Cosine Transform,DCT) can only extract the frequency domain features of face images, but can not extract texture feature information without considering the relationship between nearest neighbor pixels. A feature extraction method based on local binary pattern (Elongated Local Binary Pattern,ELBP) combining DCT features and extension is proposed. In this method, a small number of low frequency coefficients of face image transformed by DCT are considered as the frequency domain features of face, then the ELBP feature is extracted from the eye and mouth region, and the ELBP feature is regarded as the spatial feature of face. PCA method is used to effectively fuse the extracted space-frequency domain features to obtain more effective face features. Finally, the nearest neighbor classifiers are used for recognition. The experimental results on ORL face database and Yale face database show that the proposed method is more beneficial to recognition and improves the accuracy of recognition than the method of DCT,ELBP alone or the combination of DCT and LBP.
【作者單位】： 蘭州理工大學(xué)計算機(jī)與通信學(xué)院;
【基金】：國家自然科學(xué)基金(No.61263019) 甘肅省高等學(xué)�；究蒲许�(xiàng)目
【分類號】：TP391.41
【相似文獻(xiàn)】
相關(guān)期刊論文 前10條
1 江宇聞;朱思銘;;基于Overcomplete ICA的人臉特征提取[J];計算機(jī)科學(xué);2005年07期
2 陳鵬;;人臉特征提取方法的研究[J];中國水運(yùn)(理論版);2006年12期
3 魏冬冬;諶海新;聶鐵鑄;;人臉特征提取與識別技術(shù)研究[J];計算機(jī)與現(xiàn)代化;2007年03期
4 王宏勇;王青青;;三維人臉特征提取方法綜述[J];電子科技;2012年12期
5 王fE;楊光;;改進(jìn)的脈沖耦合神經(jīng)網(wǎng)絡(luò)人臉特征提取方法[J];計算機(jī)工程與應(yīng)用;2013年01期
6 宋宇,周激流,何坤,劉智明,黎奎;多尺度人臉特征提取[J];計算機(jī)應(yīng)用研究;2005年04期
7 陶宇權(quán);程德福;李成榮;徐U，
本文編號：2503712
本文鏈接：http://sikaile.net/kejilunwen/ruanjiangongchenglunwen/2503712.html
最近更新
教材專著
