ABSTRACT
The artificial rating accuracy of ancient Chinese coin is low, the cycle is long and the labor cost is high. At present, computer image processing technology is mostly used for coin denomination recognition or coin corrosion area recognition, and there is little research on the rating of ancient Chinses coins by image processing method. Therefore, this paper proposes a method of ancient Chinese coins rating based on the combination of image color and continuity features. The text adopts k-means algorithm to recognize the ancient Chinese coin region of the image, and extracts the variance and skewness characteristics of the H and I channel in the HSI color space of the ancient Chinese coin region. In this paper, Canny algorithm is adopted to extract the characters and edges of ancient Chinese coins, and the continuity characteristics of the raised characters and edges are quantitatively measured, and jointly constitutes the feature vector of ancient Chinese coins with color features. The rating score of ancient Chinese coins image is predicted by BP neural network model. Experimental results show that this method can accurately and quickly classify ancient Chinese coins by image information.
- Chu X. The timing of Chuxia modern coin Collection[J]. Collection Investment Guide,2016(1):30-31. (In Chinese)Google Scholar
- Guan Hanheng. A TRIAL TALK ON THE GRADE OF CHINESE COINS[J]. CHINA NUMISMATICS,1992(3):73-75. (In Chinese)Google Scholar
- Ding Weili, Li Yong, Chen Yu. Food Category Recognition Algorithm Based on Region Colour Features[J]. Electronic Science and Technology,2016,29(6):1-4,7. DOI: 10.16180/j.cnki.issn1007-7820.2016.06.001. (In Chinese)Google Scholar
- Jin Lei. Study on image processing technology of copper coin surface discoloration and corrosion[D]. Liaoning: Shenyang Ligong University,2011. DOI:10.7666/ D.D157574. (In Chinese)Google Scholar
- Guo Gaopeng. Study On Chinese Painting Recognition Based on Texture Characteristics and Colour Characteristics and RELM [J].Modern Scientific Instruments,2019(3):36-39. (In Chinese)Google Scholar
- Zhang Yueting, Yin Zhongke, Wang Jianying. A New Image Edge Detection Scheme [J]. Journal of electronics & information technology,2008,30(6):1295-1299. (In Chinese)Google Scholar
- Wang Hongshen, Zhang Xiangyu, Dou Yongkun, Edge connectivity evaluation algorithm for performance of edge detectors[J]. Computer Engineering and Applications,2018,54(16):192-196. DOI: 10.3778/j.issn.1002-8331.1705-0065. (In Chinese)Google Scholar
- Han Ding, Wu Pei, Zhang Qiang, Feature extraction and image recognition of typical grassland forage based on colour moment[J]. Transactions of the Chinese Society of Agricultural Engineering,2016,32(23):168-175. DOI: 10.11975/j.issn.1002-6819.2016.23.023. (In Chinese)Google Scholar
Recommendations
Research on Chinese ancient characters image recognition method based on adaptive receptive field
AbstractAs the main carrier of Chinese civilization, the importance of ancient Chinese documents cannot be overstated. However, the phenomenon of “Heavy storage and light use” is serious in modern society. In order to improve the utilization of its ...
On-line handwriting character recognition method with directional features and direction-change features
ICDAR '97: Proceedings of the 4th International Conference on Document Analysis and RecognitionWe propose a new on-line recognition method to recognize handwritten cursive-style characters correctly. Our method simultaneously uses both directional features, otherwise known as off-line features, and direction-change features, which we designed as ...
Image based recognition of ancient coins
CAIP'07: Proceedings of the 12th international conference on Computer analysis of images and patternsIllegal trade and theft of coins appears to be a major part of the illegal antiques market. Image based recognition of coins could substantially contribute to fight against it. Central component in the permanent identification and traceability of coins ...
Comments