Two Dimensional Clipping Based Segmentation Algorithm for Grayscale Fingerprint Images

Krishna Prasad K., P. S. Aithal
2017 International journal of applied engineering and management letters  
One of the huge methods in Automated Fingerprint Identification System (AFIS) is the segment or separation of the fingerprint. The process of decomposing an image into exclusive components is referred as segmentation. Fingerprint segmentation is the one of the predominant process involved in fingerprint pre-processing and it refers to the method of dividing or separating the image into disjoint areas as the foreground and the background region. The foreground also called as Region of Interest
more » ... OI) due to the fact only the region which contains ridge and valley structure is used for processing, whilst the background carries noisy and irrelevant content material and so that it will be discarded in later enhancement or orientation or classification method. The challenge proper right here is to decide which a part of the image belongs to the foreground, retrieved as an input from the fingerprint sensor device or from benchmark datasets and which part belongs to the background. A 100% correct segmentation is continually very tough, specifically inside the very poor quality image or partial image together with the presence of latent. In this paper, we discuss a modified clipped based segmentation algorithm by adopting threshold value and canny edge detection techniques. We segment the background image is x and y dimensions or in other words left the edge, right edge, top edge and bottom edge of the image. For the purpose of analyzing the algorithm FVC ongoing 2002 benchmark dataset is considered. The entire algorithm is implemented using MATLAB 2015a. The algorithm is able to find affectively ROI of the fingerprint image or separates the foreground region from the background area of the fingerprint image very effectively. In high configuration system proposed algorithm achieves execution time of 1.75 seconds.
doi:10.47992/ijaeml.2581.7000.0012 fatcat:fl4ql7ly3veafokn7zuj2daviu