基于形态学及SVM思想的病变图象识别方法

提出了一种将形态学理论与SVM(支持向量机)算法结合起来的病变图象特征识别方法.利用形态学的广义骨架理论及形状因子,抽取图象特征,作为SVM训练数据,同时借助SVM良好的分类性能,对图象骨架进行分类,从而实现图象特征的快速分类,提高识别率.本文以红外乳腺图象为例,说明了本算法的各种特色.实验结果表明,该算法能有效提高图象识别率并具有一定的应用前景,同时,该方法对其他类似的模式识别问题也有一定的借鉴作用.

Image Recognition Method for Pathological Changes Based on Morphology and SVM

The paper brings forward a new image recognition method for pathological changes with morphology theory and SVM algorithm. Image character described by structure theory and frame sector is used as training data of SVM. Meanwhile, rapid classification of image character can be realized by the aid of favorable classification performance of SVM, by which image structure can be classified, which can improve recognition efficiency. The paper also gives the infrared image sample of galactophore to test the algorithm. The result shows that the algorithm can improve recognition ratios effectively and the algorithm has a broad foreground. As well as this method can be applied other similar pattern recognition.