基于SVM-Qt的废旧织物颜色识别系统的设计与实现

Design and Implementation of Color Recognition System for Waste Fabric Based on SVM-Qt

为了提高废旧纺织物颜色分类的质量及效率,笔者提出一种基于德尔菲法和SVM的颜色及深浅识别的策略,并结合Qt实现识别系统的设计。首先对获取的图像进行预处理,并构造颜色及深浅支持向量机分类器;然后使用德尔菲法确定废旧纺织物颜色及深浅的特征点及权重;最后,对训练得到的颜色及深浅支持向量机分类器进行测试。实验结果表明:该方法平均识别率达到了90%以上,可以对织物颜色及深浅进行准确识别。

In order to improve the quality and efficiency of color classification of waste textiles,a strategy of color and shade recognition based on Delphi method and SVM is proposed,and the design of recognition system is implemented in combination with Qt.First,preprocess the acquired image and construct a color and shade support vector machine classifier;then use Delphi method to determine the color and shade feature points and weights of the waste textile;finally,the color and shade support vector machine Classifier for testing.The experimental results show that the average recognition rate of this method is more than 90%,and it is feasible to accurately recognize the color and shade of the fabric.