Share Email Print
cover

Proceedings Paper • new

Coin classification in a complex environment
Author(s): Huanhuan Chang; Zhiqiang Wei; Lei Huang; Jie Nie; Wenfeng Zhang; Lu Wang
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Coin classification automatically plays important roles in many applications, e.g., vending systems. Glossy reflection is one of the key factor that affect the performance of vision-based coin classification, especially in a complex environment. In this paper, we propose a novel method for robust coin classification. Contrary to the previous method, we get the glossy area first. Edge features and texture features are used in glossy area detection. Then the deep learning features are extracted based on non-glossy area instead of the whole coin image. Finally, the coin classification results are got from the VGG nets scheme. Comprehensive experiments show that our method is robust under various complex environments. The comparison experiments demonstrate that our method can outperform the state-of-the-art method. Our method achieves 95.80% accuracy.

Paper Details

Date Published: 6 May 2019
PDF: 9 pages
Proc. SPIE 11069, Tenth International Conference on Graphics and Image Processing (ICGIP 2018), 110691K (6 May 2019); doi: 10.1117/12.2524185
Show Author Affiliations
Huanhuan Chang, Ocean Univ. of China (China)
Zhiqiang Wei, Ocean Univ. of China (China)
Lei Huang, Ocean Univ. of China (China)
Jie Nie, Ocean Univ. of China (China)
Wenfeng Zhang, Ocean Univ. of China (China)
Lu Wang, Ocean Univ. of China (China)


Published in SPIE Proceedings Vol. 11069:
Tenth International Conference on Graphics and Image Processing (ICGIP 2018)
Chunming Li; Hui Yu; Zhigeng Pan; Yifei Pu, Editor(s)

© SPIE. Terms of Use
Back to Top