After a brief introduction on the overall architecture of a fingerprint recognition system, this hands-on lecture explores the classical fingerprint feature extraction steps: segmentation of the ridge-line pattern from the background, estimation of local ridge-line orientation and frequency, enhancement of the ridge-line pattern, and minutiae detection. For each step, a simple but effective algorithm is discussed and implemented using Python, NumPy and OpenCV.
Preparation before the lecture
The participants are suggested to review the lecture notes and configure the development environment. You can run the example locally or online.
Raffaele Cappelli is an associate professor at the Department of Computer Science of the University of Bologna; he is in charge of the “Computer Vision” course at the Laurea degree in Computer Science and Engineering.
His research activity focuses on biometric systems, and he mainly works in the fingerprint recognition field, where he is well known for his contributions to fingerprint classification, recognition, synthetic generation, and performance evaluation.
He is coauthor of various scientific papers and chapters in books; he is one of the organizers of the four international fingerprint verification competitions (FVC) and of the recent performance evaluation initiative named “FVC-onGoing”. He has served the program committees of important conferences on biometric systems and he works as a reviewer for the main journals in the field. Raffaele Cappelli served as the “Sample Synthesis” area editor of “Encyclopedia of Biometrics” (Springer) and the “Fingerprint” area editor of the “IEEE Biometrics Compendium”.
He received the Laurea degree cum laude in Computer Science in 1998, his PhD in 2002, and he is an associate professor since 2015.