Development of a Vision System to Enhance the Reliability of the Pick-and-Place Robot for Autonomous Testing of Camera Module used in Smartphones

Phan, Hoang-Anh; Bui, Duy; Dinh, Tuan Nguyen; Hoang, Bao-Anh; Ngoc, An Nguyen; Quoc, Dong Tran Huu; Thuy, Ha Tran Thi; Bui, Tung Thanh; Thanh, Van Nguyen Thi

doi:10.1109/iceet53442.2021.9659578

Cited by 3 publications

(2 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In our study, we solve the practical issue that a camera module manufacturing company is facing. In the previous work, we proposed an effective vision system to improve the reliability of pick-and-place robots for the autonomous testing of camera modules [34]. The system confirmed the presence of the camera modules in feeding trays and the placement accuracy of the modules in test sockets by using a simple image processing algorithm based on histogram information.…”

Section: Introductionmentioning

confidence: 95%

“…The vision system equipped for the pick-and-place robot helps identify correctly and incorrectly positioned camera modules in the socket (Figure 2b), thus reducing the failure rate. A simple classification model was proposed based on computing the histogram of the image of the camera module on the socket, thereby detecting the incorrect position [34]. In this work, machine learning models are employed to improve the performance of the developed system.…”

Section: Autonomous Component Test-ing Systemmentioning

confidence: 99%

See 1 more Smart Citation

Development of an Autonomous Component Testing System with Reliability Improvement Using Computer Vision and Machine Learning

Phan,

Duong,

Thi

et al. 2024

ECTI-CIT Transactions

View full text Add to dashboard Cite

This study evaluated computer vision-based models, including Histogram Analysis, Logistic Regression, Sift-SVM, and Deep learning models, in an autonomous testing system developed for smartphone camera modules. System performance was assessed in a practical factory setting with workers operating the system, and metrics such as processing time, sensitivity, specificity, accuracy, and defect rate were evaluated. Based on the results, the Sift-SVM model demonstrated the greatest potential for enhancing the reliability of the system with a processing time of 0.01578 seconds, a sensitivity of 99.811%, and a reduction in the failure rate to 1888 PPM. The study findings suggest that Sift-SVM has the potential to be practically applied in the industry, thus improving the speed and accuracy of automatic defect detection in manufacturing and reducing the defect rate.

show abstract

Section: Introductionmentioning

confidence: 95%

Section: Autonomous Component Test-ing Systemmentioning

confidence: 99%