【摘要】 针对焊缝缺陷图像分类识别问题,提出一种基于独立成分分析(ICA)的分类识别的优化算法。焊缝特征提取是焊缝缺陷识别的关键技术,首先介绍焊缝缺陷图像的预处理过程、独立成分分析算法原理,最后对数据库焊缝缺陷图像采用支持向量机进行分类识别。实验证明,独立成分分析(ICA)算法能很好地提高焊缝缺陷分类识别率。更多还原

【Abstract】 Aiming at the problem of X-ray weld defect identification, proposes an optimization algorithm based on Independent Component Analysis(ICA) for feature extraction and support vector machine for classification and identification of weld defects. Weld feature extraction is thekey technology for weld defect identification. Introduces the preprocessing process of weld defect image and the principle of ICA algorithm,uses the support vector machine to classify and identify the database image. Experiments show that the ICA algorithm can improve the clas-sification rate of weld defects.更多还原