Multi-Element Deep Learning Using False Detection Images for Training Set -Effective For License Plate Detection-
- In deep learning, in order to improve learning performance, preprocessing and ingenuity to combine a plurality of discriminators are performed. It can be inferred that it has elements exceeding the set of learning. Therefore, a configuration to combine multiple recognition elements with low loss will be studied. The advance category classification method is expected to narrow the scope of learning in the next stage. Combining elements specialized for FalsePositive/FalseNegative removal after the positive/negative determination is considered to be effective if the accuracy of the subsequent stage is high. We conducted a license plate recognition experiment by combining these and achieved the best performance for Caltech data.
Author: | Kazuo Ohzeki, Yoshikazu Kido, Yutaka Hirakawa, Stefan-Alexander SchneiderORCiDGND |
---|---|
URL / DOI: | https://www.ieice.org/ken/index/ieice-techrep-117-514-e.html |
Identifier: | 0913-5685 OPAC HS OPAC extern |
Parent Title (English): | IEICE Technical Report |
Subtitle (English): | Pattern Recognition and Media Understanding |
Publisher: | IEICE |
Document Type: | Article |
Language: | English |
Date of Publication (online): | 2018/03/11 |
Year of first Publication: | 2018 |
Volume: | Vol. 117 |
Issue: | 514 |
Number of pages: | 6 Seiten |
First Page: | 25 |
Last Page: | 30 |
Institutes: | Fakultät Elektrotechnik |
Research focus: | FSP2: Mobilität |
Publication Lists: | Schneider, Stefan-Alexander |
Publication reviewed: | begutachtet |
Licence (German): | |
Release Date: | 2021/02/16 |