Solder Joint Inspection Using Imaginary Part of Gabor Features

Author(s):  
Hao Wu ◽  
Tianya You ◽  
Xiangrong Xu ◽  
Aleksandar Rodic ◽  
Petar B. Petrovic
2000 ◽  
Author(s):  
Sheng Liu ◽  
Dathan Erdahl ◽  
I. Charles Ume

Abstract A novel approach for flip chip solder joint quality inspection based on vibration analysis is presented. Traditional solder joint inspection methods have their limitations when applied to flip chip solder joint quality inspection. The vibration detection method is a new approach which has advantages such as being non-contact, non-destructive, fast and can be used on-line or during process development. In this technique, a flip chip was modeled as a thick plate supported by solder bumps. Changes in solder joint quality produce different vibration responses of flip chip, and change its natural vibration frequencies. In this paper, the vibration frequencies of a flip chip on a ceramic substrate were calculated using the finite element method. Based on vibration analysis, a laser ultrasound and interferometric system was developed for flip chip solder joint quality inspection. In this system, chips with good solder joints can be distinguished from chips with bad joints using their vibration responses and frequencies. Defects recognition methods were developed and tested. Results indicate this approach offers great promise for solder bump inspection in flip chip, BGA and chip scale packages.


2011 ◽  
Vol 121-126 ◽  
pp. 4931-4935
Author(s):  
Yong Cong Kuang ◽  
Gao Fei Ouyang ◽  
Hong Wei Xie ◽  
Xian Min Zhang

To improve the performance of current solder joint inspection method, an efficient method based on statistical learning is proposed in this paper. In the method, the solder was divided into several sub-regions to determine the defect type. To resolve imbalance problem, an improved over-sampling algorithm was proposed in which the synthetics samples are generated between the boundary samples and their neighbors. AdaBoost was used for feature selection and classification for every sub-region. Experiments results showed that the defects of solder joints can be identified properly using the proposed algorithm.


Author(s):  
Nian Cai ◽  
Guandong Cen ◽  
Jixiu Wu ◽  
Feiyang Li ◽  
Han Wang ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document