基于图像纹理特征的土鸡蛋微裂纹无损检测

Nondestructive method to detect small crack of native egg based on image textural feature

为了提高土鸡蛋表面微裂纹检测的准确度和效率,提出一种基于图像纹理特征的土鸡蛋微小裂纹无损检测方法.利用工业相机对150枚土鸡蛋采集数字图像,采用高斯滤波、灰度变换等方法对土鸡蛋图像进行预处理;利用灰度共生矩阵进一步提取图像纹理特征,将纹理特征参数作为不同分类器包括簇类独立软模式法、线性判别分析(linear discriminant analysis,LDA)和偏最小二乘支持向量机输入,进行土鸡蛋有无裂纹判别.结果表明,采用图像纹理特征参数建立的土鸡蛋有无裂纹LDA模型判别准确度最高,达到96.0%.

In order to improve the detection accuracy and efficiency for shell small crack of native egg,a method based on textural feature of images was proposed.Digital image was obtained by industrial camera and then preprocessed by Gauss filtering and grayscale transformation.After that,textural feature of images was extracted based on gray level co-occurrence matrix(GLCM).For crack identification,textural feature parameters were used as classifier input which included soft independent modeling of class analogy(SIMCA),linear discriminant analysis(LDA) and least squares support vector machine(LS-SVM).The results showed that LDA model achieved the best correct classification rate(CCR) at 96%.