《Table 1 Difference in texture features between fruit and leaves under varying illumination conditio

  提示：宽带有限、当前游客访问压缩模式

本系列图表出处文件名：随高清版一同展现

《Feature extraction of hyperspectral images for detecting immature green citrus fruit》

1. 获取 高清版本忘记账户？点击这里登录

1. 下载图表忘记账户？点击这里登录

Grey Level Co-occurrence Matrices（GLCM），as main image texture analysis tool，is a statistical method to demonstrate image texture structure by statistical sampling of the pattern of the gray levels that occur in relation to other gray levels.GLCM can be generated by calculating how often a pixel with gray level value，i，occurs adjacent to a pixel with the value，j.That is to say，a co-occurrence matrix is specified by the relative frequencies P（i，j，d，θ）in which two pixels，separated by distance d，occur in a direction specified by the angleθ，one with gray level i and the other with gray level j[16].Table 1 shows the difference in texture features between fruit and leaves under varying illumination conditions.To detect green fruit using texture features，six most relevant features，including autocorrelation，cluster prominence，cluster shade，sum of squares，sum average and sum variance，were chosen for further classification.