Claim Missing Document
Check
Articles

Found 2 Documents
Search
Journal : InComTech: Jurnal Telekomunikasi dan Komputer

Fingerprint Authenticity Classification Algorithm based-on Distance of Minutiae using Convolutional Neural Network Hariyanto Hariyanto; Sarifuddin Madenda; Sunny Arief Sudiro; Tubagus Maulana Kusuma
InComTech : Jurnal Telekomunikasi dan Komputer Vol 11, No 3 (2021)
Publisher : Department of Electrical Engineering

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22441/incomtech.v11i3.13770

Abstract

Fingerprint identification systems are vulnerable to attempted authentication fraud by creating fake fingerprints that mimic the live. This paper proposes method to detect whether a fingerprint is live fingerprint or fake fingerprint using Convolutional Neural Network (CNN). We construct a features database of distances among minutiaes of fingerprints, where the distance calculation is based-on Euclidean Distance. Furthermore, the distance features database that has been constructed is classified using the CNN. CNN is a deep learning method designed for machine learning processes so that computers recognize objects in an image and this method has capability classifying an object. The numerical results have shown that the best accuracy achieves 99.38% when the learning rate is 0.001 with the epoch of 100.
Generation of Teeth Caries Features for Human Dental Caries Classification Linda Wahyu Widianti; Sarifuddin Madenda; Johan Harlan; Sunny Sudiro; Farina Pramanik
InComTech : Jurnal Telekomunikasi dan Komputer Vol 11, No 3 (2021)
Publisher : Department of Electrical Engineering

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22441/incomtech.v11i3.13804

Abstract

Many dental diseases are experienced by humans, one of which is dental caries, there are three types of human dental caries, namely enamel caries, dentin caries and pulp caries. This study contains the detection of caries disease in human teeth using two-dimensional images and radiological results of x-ray periapical radiographs from a test image dataset that has a number of pixels between 374x288 to 672x514 pixels with an image resolution of 96 DPI. The original data of existing dental images was processed using Matlab language to obtain caries features through three stages of the processes: pre-processing stage which are stages of the preprocessing process that converts data from a two-dimensional color image (row/height, column/width) that is stored using three channels Red, Green and Blue (RGB), into a grayscale image with one channel, the process of extracting dental caries features by performing calculations caries area and calculate the distance of the caries area to the nerve canal (pulp), and the process of building learning or reference data from dental caries using 24 radiograph periapical data on molar tooth images processed using Matlab. Dental caries features extraction process and the features learning process to generate references features from dental caries is the main objective of this research. This study result was references features for human dental caries classification.