Author Affiliations
11. Department of Criminal Science and Technology, Railway Police College, Zhengzhou 450053, China22. Shanxi Provincial Key Laboratory of Microstructure Electromagnetic Functional Materials, Shanxi Datong University, Datong 037009, China44. Wuxi Spectrum Vision Technology Co., Ltd., Wuxi 214000, China55. Institute of Forensic Science, Ministry of Public Security, Beijing 100038, China66. MOE Key Laboratory of Advanced Micro-Structured Materials, School of Physics Science and Engineering, Tongji University, Shanghai 200092, Chinashow less
Fig. 1. GaiaSorter hyperspectral sorter
Fig. 2. Three-dimensional perspective views of the front and back of 100 yuan RMB
Fig. 3. Spectral reflectance curves of the characteristic points on the front and back of real and counterfeit 100 yuan RMB banknotes
Fig. 4. The grayscale images of the front and back of the real and counterfeit 100 yuan RMB banknotes at 500, 660 and 870 nm
Fig. 5. The grayscale images of the real and counterfeit 100 yuan RMB based on band operation
Fig. 6. The first 12 principal components for the front sides of the real and counterfeit 100 yuan RMB
Fig. 7. The first 12 principal components for the back sides of the real and counterfeit 100 yuan RMB
Fig. 8. The texture informations of the grayscale images of the back sides of the real and counterfeit banknotes at 550 nm
From left to right are the mean, variance, inverse difference moment, contrast, dissimilarity, entropy, angle second-order moment, correlations, respectively
Fig. 8. The texture informations of the grayscale images of the front sides of the real and counterfeit banknotes at 550 nm
From left to right are the mean, variance, inverse difference moment, contrast, dissimilarity, entropy, angle second-order moment, correlations, respectively
序号 | 名称 | 作用 |
---|
1 | 均值 | 反映了灰度的平均情况 | 2 | 方差 | 反映了灰度变化的大小 | 3 | 逆差矩 | 反映了局部同质性, 当共生矩阵沿对角线集中时, 其值较大 | 4 | 对比度 | 反映了影响纹理的清晰度 | 5 | 非相似度 | 与对比度相同, 用来检测相似性 | 6 | 熵 | 是图像所具有的信息量的度量 | 7 | 角二阶矩 | 反映了图像灰度分布的均匀性 | 8 | 相关性 | 反映某种灰度值沿某个方向的延伸长度 |
|
Table 1. Texture features and its effect based on gray level co-occurrence matrix