Fingerprint identification using neural networks
Date of Publication
1994
Document Type
Bachelor's Thesis
Degree Name
Bachelor of Science in Electronics and Communications Engineering
Subject Categories
Engineering
College
Gokongwei College of Engineering
Department/Unit
Electronics and Communications Engineering
Honor/Award
Awarded as best thesis, 1994
Abstract/Summary
Abstract. Being a unique characteristic of every human being, a person's fingerprints are useful as a reliable identifying element in a person identification system. Neural networks, though already an old technology (circa 1960's), has recently gained interest for its possible benefits in applications requiring simulated human intelligence. Here, the two concepts are linked to create a fingerprint identification system using neural networks.
The system consists of a video camera as the capture device for black fingerprint impressions on paper. The camera output is fed to a digitizer and the image data is saved using the TIFF format. The image is later processed by an 80486 PC. Image processing routines written in C improve the quality of the images and convert them into the required format for input to the neural network. The neural network software, also written in C, is the fingerprint identifying engine of the system. The applicability of two types of neural networks, namely the backpropagation network and self-organizing map (SOM), was tested.
Abstract Format
html
Language
English
Format
Accession Number
TU10537
Shelf Location
Archives, The Learning Commons, 12F Henry Sy Sr. Hall
Physical Description
74 numb. leaves
Recommended Citation
Lim, E. Y., Ong, J. L., Tan, C., Tiu, C. G., & Yuvienco, M. B. (1994). Fingerprint identification using neural networks. Retrieved from https://animorepository.dlsu.edu.ph/etd_honors/153
