TANNING LEATHER CLASSIFICATION USING AN IMPROVED STATISTICAL GEOMETRICAL FEATURE METHOD

摘要：

Tanning is an important procedure in the leather production process.Tanning agent can change the physical properties and chemical compositions of leather, and ultimately alter the texture of the surface.In order to classify chrome tanning and vegetable tanning leather, this paper presents improved statistical geometrical features (ISGF) to proceed texture analysis for tanning leather and use two classifiers based on Fisher criterion and LVQ Net to compare chrome tanning and vegetable tanning leather, Our results suggest that ISGF can discriminate chrome tanning and vegetable tanning leather with less computation cost and more fit for tanning leather texture feature than SGF.

关键词： Leather texture Statistical geometrical features Irregularity Compactness Fisher criterion, LVQ Net

作者: LING WANG CHANG LIU

作者单位: College of Computer Science, Sichuan Normal University, Chengdu, 610066 P.R.China

会议类型: 国际会议

会议名称: 2007 International Conference on Machine Learning and Cybernetics(IEEE第六届机器学习与控制论国际会议)

会议地点: 香港

会议语种:英文

页码: 1765-1768

在线出版日期: 2007-08-19（万方平台首次上网日期，不代表论文的发表时间）