Fingerprint Segmentation Algorithm Based on Fourier Transform

Summary Objectives : Many pathological conditions of the cardiovascular system cause murmurs and aberrations in heart sounds. Phonocardiography provides the clinician with a complementary tool to record the heart sounds heard during auscultation. The advancement of intracardiac phonocardiography combined with modern digital signal processing techniques has strongly renewed researchers' interest in studying heart sounds and murmurs.The aim of this work is to investigate the applicability of different spectral analysis methods to heart sound signals and explore their suitability for PDA-based implementation. Methods : Fourier transform (FT), short-time Fourier transform (STFT) and wavelet transform (WT) are used to perform spectral analysis on heart sounds. A segmentation algorithm based on Shannon energy is used to differentiate between first and second heartsounds. Then wavelet transform is deployed again to extract 64 features of heart sounds. Results : The FT provides valuable frequency information but the timing information is lost during the transformation process. The STFT or spectrogram provides valuable time-frequency information but there is a trade-off between time and frequency resolution. Waveletanalysis, however, does not suffer from limitations of the STFT and provides adequate time and frequency resolution to accurately characterize the normal and pathological heartsounds. Conclusions : The results show that the wavelet-based segmentation algorithm is quite effective in localizing the important components of both normal and abnormal heart sounds. They also demonstrate that wavelet-based feature extraction provides suitable feature vectors which are clearly differentiable and useful for automatic classification of heart sounds.

Download Full-text

A novel approach of K-means based fingerprint segmentation algorithm

2012 International Symposium on Instrumentation & Measurement, Sensor Network and Automation (IMSNA) ◽

10.1109/msna.2012.6324553 ◽

2012 ◽

Cited By ~ 1

Author(s):

Huina Li ◽

Yuan Ping

Keyword(s):

Segmentation Algorithm ◽

Novel Approach ◽

Fingerprint Segmentation

Download Full-text

A corner strength based Fingerprint segmentation algorithm with dynamic thresholding

2008 19th International Conference on Pattern Recognition ◽

10.1109/icpr.2008.4761871 ◽

2008 ◽

Cited By ~ 3

Author(s):

A. Baig ◽

A. Bouridane ◽

F. Kurugollu

Keyword(s):

Segmentation Algorithm ◽

Strength Based ◽

Fingerprint Segmentation

Download Full-text

Robust Point-Based Feature Fingerprint Segmentation Algorithm

Advances in Biometrics - Lecture Notes in Computer Science ◽

10.1007/978-3-540-74549-5_114 ◽

2007 ◽

pp. 1095-1103 ◽

Cited By ~ 18

Author(s):

Chaohong Wu ◽

Sergey Tulyakov ◽

Venu Govindaraju

Keyword(s):

Segmentation Algorithm ◽

Fingerprint Segmentation

Download Full-text

Analyses and System Implement to Fingerprint Image Segmentation Algorithm Based on Field

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.159.291 ◽

2010 ◽

Vol 159 ◽

pp. 291-296

Author(s):

Yan Bai Wang ◽

Lu Tan ◽

Nian Feng Li ◽

Wei Liu

Keyword(s):

Image Segmentation ◽

Separation Zone ◽

Experimental System ◽

Segmentation Algorithm ◽

Experimental Results ◽

Gradient Field ◽

Fingerprint Image ◽

Fingerprint Segmentation ◽

Image Segmentation Algorithm

Introduced the fingerprint segmentation algorithm based on strength field and gradient field and designed the experimental system for the algorithm. The method is used to carry on the massive tests with fingerprint images by APC fingerprint gathering. The experimental results show that this method achieved a good fingerprint image foreground and background separation zone.

Download Full-text

GLCM Inspired Fingerprints Segmentation Algorithm with Adaptive Block Size

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.239-240.1456 ◽

2012 ◽

Vol 239-240 ◽

pp. 1456-1461

Author(s):

Hui Na Li ◽

Jun Li Luo

Keyword(s):

Block Size ◽

Segmentation Algorithm ◽

Experimental Results ◽

Gray Level ◽

Fingerprint Image ◽

Pixel Pair ◽

Fingerprint Segmentation ◽

The Mean ◽

Occurrence Matrix ◽

Self Adaptive

In order to reduce the dependence on the images' sizes, resolutions and qualities, a self-adaptive block size fingerprint segmentation algorithm based on the gray level co-occurrence matrix (GLCM) is proposed. Firstly, the image is divided into a number of non-overlapped rectangular blocks whose size is automatically determined by the mean of the ridge distance from the spectrogram. Then the contrasts of the GLCM of each block in different directions of pixel-pair could be calculated. Since the variances of these contrasts are different for the foreground and the background, finally, the fingerprint image can be segmented correctly. Experimental results show that the proposed algorithm performs effectively in processing images gathered by various fingerprint sensors in diverse environments.

Download Full-text