基于小波概率神经网络的彩色纹理识别

Color Texture Recognition Based on Wavelet Probabilistic Neural Network

提出了一种将颜色信息融入到纹理识别中的新方法——基于小波概率神经网络的彩色纹理识别.首先将RGB彩色纹理图像转化为HSV彩色模型,用小波变换(WT)进行树形结构小波分解提取彩色纹理的特征,然后使用概率神经网络对测试样本进行分类识别.实验结果证明,该方法的识别效果比较好.

This paper puts forward to an algorithm for recognizing color textures based on wavelet probabilistic neuralnetwork.At first,The RGB color texture image is converted into HSV,extract features on the color texture image on the basis of tree-structured,then uses PNN to classify the different texture images.Experiment is conducted on different texture images.Compared to the literature[1],the effect of our method for texture recognition is obvious excelled it.