Open AccessIdentity Card Detection System using YOLOv3 and Image Rectification
Author(s) -
Gede Putra Kusuma,
AUTHOR_ID,
Angelica Faustine,
Nikolas Nasi
Publication year - 2022
Publication title -
international journal emerging technology and advanced engineering
Language(s) - English
Resource type - Journals
ISSN - 2250-2459
DOI - 10.46338/ijetae022_20
Subject(s) - computer science , rectification , identity (music) , artificial intelligence , computer vision , edge detection , canny edge detector , object detection , image (mathematics) , object (grammar) , pixel , enhanced data rates for gsm evolution , pattern recognition (psychology) , image processing , engineering , physics , voltage , acoustics , electrical engineering
— In the age of modern technology like today, object detection is something that is really needed. Object detection is done by considering the type of data collected. This research focused on Identity card detection from an input image taken by a smartphone camera. The Identity card detection is a preliminary step toward automatic identity data collection. Identity data collection is usually performed in a conventional way. This way leads to several problems such as bad data result, unreliable data verification, and long duration on confirming data validity. In this project, we will make an object detection system with YOLOv3 algorithm, and then the result will be used for an edge detection with Canny algorithm and image rectification. The testing result show that YOLOv3 algorithm could reach 92.59 mAP with 5s detection time. While the corner detection for image rectification manage to get an average error of 37.06 pixels. The establishment of this model has important practical significance for improving Identity Card detection process. Keywords—Identity Card Detection, Object Detection, YOLOv3 Model, Corner Detection, Image Rectification