APLIKASI METODE TEMPLATE MATCHING UNTUK KLASIFIKASI SIDIK JARI

Abstract

The development of image processing technologies now provide the possibility of human to create a system that can recognize a digital image. One method to recognize a digital image is the template matching. This method serves to find small parts of the image that matches the template image. Among the technologies to solve the problem of image processing is a system of classifying fingerprints into the form of software that is able to process the fingerprint image enhancement and match fingerprint images that have been recorded by the database system and classify fingerprints into a particular class. In this final project made an application that aims to classify the fingerprint image into a particular class using template matching method.Classification process is started with fingerprint image acquisition, images size distorting 256x256, grayscale(gray level), histeq (histogram equalization), binary (image distorting becomes two scales black and white), thinning, image gets to aim, and resize 32x32. The process will then be calculated percentage of similarity with the template fingerprint image file by using the calculation of NC (Normalized Cross Correlation). The biggest percentage value indicates that the template matches the fingerprint image files. The experiment has been done classification process as much as 61 input fingerprint image with each 5 image formats are *.bmp, *.gif, *.jpg, *.png, and *.tif, so the total input fingerprint image as much as 305. For image format type *.bmp, *. gif, *. png, and *.tif on type template Plain Arch, Plain Whorl, and Double Loop point out that its success zoom as big as 100%. On Tented Arch increase supreme success on image format *.bmp, *. jpg, *. png, *. tif, on Ulnair Loop increase supreme success on image format *.png, *. tif and Radial Loop increase supreme success on image format *.bmp, *. png, *. tif. Image format that right usually experience fault which is on success zoom is contemned to image format *.jpg to type template Plain Arch, Radial Loop, Plain Whorl and Double Loop, then for image format *.gif on type template Tented Arch and Ulnair Loop. Keywords: image processing, fingerprint, template matching