臺灣博碩士論文加值系統

本文主要探考兩個以生物特徵為主的問題─語者辨識和人臉辨別。在處理第一個問題即語者辨識方面，以小波轉換將語音訊號分解成高低頻係數，加上傳統特徵抽取方法，如主成份分析(PCA)、線性預測編碼導出的倒頻譜係數(LPCC)、碎形幾何(Fractal)和小波特徵抽取(WTFT)[1]得到聲紋特徵，最後結合機率式神經網路(PNN)分類器進行聲紋比對，本文所提出方法可以有效改善辨識率同時提高辨識效率。第二個問題是人臉識別，我們首先將二維的人臉影像作水平投影，得到一維的累計灰階剖面曲線。再利用離散小波轉換抽取低頻小波成份當作特徵向量。針對人臉識別和人臉比對應用模式，我們進行了一系列的實驗，實驗的影像樣本來自ORL人臉影像資料庫，實驗顯示，我們的方法有最好的辨識性能和效率。此一方法將十分適合用來實現硬體化和資源有限的嵌入式人臉辨識系統。

This paper will study two problem in biometrics ─ speaker and face recognition. Firstly, to speaker recognition problem, we use wavelet transform to decompose speech signal into high and low frequency coefficients, then we apply difference traditional methods include PCA, LPCC, Fractal, and WTFT to extract low or high frequency as feature, which combined probabilistic neural network classifier to match voiceprint. This shows the proposed method will improve recognition rate and efficiency. Besides, to face recognition, we will obtain cumulative gray curve after 2D face image projected in horizon. Using discrete wavelet transform extracts low frequency coefficients as feature. For face identification and face matching application modes, we precede a set of experiments. The facial images are sampled from ORL database.Our experiments reveal that the proposed method possesses excellent recognition performance and efficiency. It is advantageous to realize a facial recognition system in a hardware-friendly, resource-constrained embedded environment.

目錄
中文摘要………………………………………………………………………i
英文摘要………………………………………………………………………………ii
目錄……………………………………………………………………………iv
圖目錄…………………………………………………………………………vi
表目錄………………………………………………………………………vii
第1章 前言………………………………………………………………1
1-1 研究動機…………………………………………………………………1
1-2 研究方法…………………………………………………………………2
1-3 論文架構…………………………………………………………………4
第2章 語音訊號前處理與特徵抽取……………………………………6
2-1 語音訊號原理與前處理…………………………………………………6
2-2 主成份分析………………………………………………………………8
2-3線性預測編碼導出的倒頻譜係數…………………………………………9
2-4 碎形理論…………………………………………………………………12
第3章 人臉特徵抽取……………………………………………………15
3-1 特徵臉……………………………………………………………………15
3-2 線性鑑定式分析…………………………………………………………16
3-3 人臉影像的維度縮減……………………………………………………18
第4章 一維小波轉換在生物辨識的應用………………………………20
4-1 離散小波轉換原理………………………………………………………20
4-2 離散小波轉換原理與語音特徵抽取……………………………………23
4-3 離散小波轉換原理與人臉特徵抽取……………………………………25
第5章 機率式神經網路…………………………………………………27
5-1 機率式神經網路原理……………………………………………………27
5-2 機率式神經網路與分類問題……………………………………………29
5-3 機率式神經網路與比對問題……………………………………………31
第6章 語者辨識實驗……………………………………………………33
6-1 實驗平台與驗證方法……………………………………………………33
6-2 語者辨識實驗……………………………………………………………33
6-3 語者比對實驗……………………………………………………………38
第7章 人臉辨識實驗……………………………………………………42
7-1 實驗平台與驗證方法……………………………………………………42
7-2 人臉辨識實驗……………………………………………………………42
7-3 人臉比對實驗……………………………………………………………44
第8章 結論與未來研究…………………………………………………47
參考文獻………………………………………………………………………48

參考文獻
[1] John Holmes and Wendy Holmes,”Speech synthesis and Recogition” 2001
[2] Francis Phan, Evangelia Micheli-Tzanakou, and Samuel Sideman.”Speaker Identification Using Neural Networks and Wavelets” IEEE Engineering in Medicine and Biology,pp92-101,January/February 2000
[3] Erik L.J. Bohez*,T.R. Senevirathne “Speech Recognition using Fractals” Pattern Recognition,pp2227-2243,19 July 2000
[4] Li Liu, Jialong He, and Gunther Palm “Signal Modeling for Speaker Identification” 1996 IEEE
[5] Olivier Rioul and Martin Vetterli “Wavelets and signal Processing” IEEE sp magazine , pp14-38,October 1991
[6] C.Sidney Burrus,Ramesh A.Gopinath,Haitao GUO “Wavelets and wavelet transforms” 1998
[7] Jaideva C.Goswami and Andrew K.Chan,“Fundaments of Wavelets” 1999
[8] C. Sidney Burrus Ramesh A.Gopinath Hai ta Guo “Introduction to Wavelets and Wavelet Transforms A Primer” 1998
[9] B.S. Everitt and G. Dunn “Applied Multivariate Data Analysis” 1991.
[10] Paul Geladi and Hans Grahn “Multivariate Image Analysis” 1996.
[11] 陳慶瀚,陳高斌 “應用SOM-PNN混合神經網路在於語者識別”義守大學電機碩士論文2002
[12] R. Chellappa, C. L.Wilson, and S. Sirohey, “Human and machine recognitionof faces: A survey,” Proc. IEEE, vol. 83, pp. 705—740, 1995.
[13] 吳佳珍 “以鑑別性小波參數為主人臉辨識系統”，成功大學資訊工程研所，碩士論文，2000。
[14] M.A. Turk and A.P.Pentland, “Eigenfaces for recognition,” J.Cognitive Necurosci., vol.3,pp.71 86,1991.
[15] T.Phiasai,S. Arunrungrusmi,and K. Chamnongthai,”Face recognition system with PCA and moment invariant method,” in Proc. IEEE Int. Symp. Circuits Syst., 2001,pp. III 65 III 68..
[16] B.-L. Zhang and Y.Guo, “Face Recognition by wavelet domain associative memory,” in Proc. Int. Symp. Intel. Multimedia. Video. Speech Processing, 2001, pp. 481-485.
[17] R. Brunelli and T. Poggio, ”Face recognition: Features versus templates,” IEEE Trans. Pattern Anal. Machine Intell., vol. 15, pp.1042-1053,1993.
[18] Bai Li*, Yihui Liu “When eigenfaces are combined with wavelets” Knowledge-Based Systems 15 (2002), pp 343-347.
[19] 劍橋大學ORL人臉資料庫. http://www.uk.research.att.com:pub/data/att_faces.zip.
[20] A. Averbuch ,D. Lazar ,and M. Israeli , ”Image Compression Using Wavelet Transform and Multiresolution Decomposition”, IEEE Trans. Image Proecessing, Vol. 5.1 ,Jan. 1996,pp.4-15
[21] Maio, D.; Maltoni, D.; Cappelli, R.; Wayman, J.L.; Jain, A.K ., “FVC2000: fingerprint verification competition“, IEEE Transactions on Pattern Analysis and Machine Intelligence, , Volume: 24 Issue: 3 , Mar 2002 Page(s): 402 —412.