Automatic morphological defect detection and classification in Li-ion battery radiographic images

碩士 === 國立陽明大學 === 生物醫學影像暨放射科學系暨研究所 === 100 === In the industry, using non-destructive testing (NDT) by X-ray inspection is very common, which can be divided into off-line and in-line testing. The aim of this thesis is to implement automatic machine learning methods to do in-line testing mainly for l...

Full description

Bibliographic Details
Main Authors: Pei-Yao Lin, 林培堯
Other Authors: Jyh-Cheng Chen
Format: Others
Language:zh-TW
Published: 2012
Online Access:http://ndltd.ncl.edu.tw/handle/95818160785479290762
Description
Summary:碩士 === 國立陽明大學 === 生物醫學影像暨放射科學系暨研究所 === 100 === In the industry, using non-destructive testing (NDT) by X-ray inspection is very common, which can be divided into off-line and in-line testing. The aim of this thesis is to implement automatic machine learning methods to do in-line testing mainly for lithium battery X-ray images in order to detect defects for classification. About lithium battery X-ray images, we focus eight areas to detect defect. There are two main steps in the study: feature extraction and classification. The aim on feature extraction is to find the position of defects and to outline the features of defects. Feature extraction method includes image processing, morphological analysis, edge detection, labeling, and projection curve observation. Two existing classification methods, support vector machine (SVM) and back-propagation neural network (BPN), were utilized as the classifier of our system. We also asked the experts to determine whether there is any defect in the objects. Finally, we verified the accuracy of feature extraction and classification. We use 200 lithium battery X-ray images to extract their characteristic features, randomly selected 70% of them as training data set and 30% as test data set. The results appear that our proposed system can detect the locations of the defects quickly and accurately. About classification, SVM and BPN obtained classification accuracy around 80% and 70%, respectively. Furthermore, we suggest that using SVM method to classify lithium battery defect detect.