基于机器视觉的煤矸智能识别系统研究

Research on Coal Gangue Intelligent Identification System Based on Machine Vision

自动化的煤矸识别对于提升分拣效率及改善工作环境至关重要。提出了一种基于机器视觉的煤矸智能识别系统,采用加权平均及双边滤波算法对煤矸图像进行预处理,随后采用灰度方差和惯性矩均值进行煤矸特征的提取,最后利用最小二乘支持向量机(LSSVM)进行煤矸智能识别。试验结果表明,煤矸识别的准确率大于97%。

Automated identification of coal gangue is crucial for improving sorting efficiency and enhancing working conditions.Proposed a coal gangue intelligent identification system based on machine vision,which preprocesses coal gangue images by using weighted averaging and bilateral filtering algorithms,subsequently gray variance and inertia moment mean are utilized for coal gangue feature extraction,finally carries out the intelligent coal gangue recognition by using least squares support vector machine(LSSVM).The experimental results show that the accuracy of coal gangue identification exceeds 97%.