Abstract
Target detection of electronic components on PCB (Printed circuit board) based on vision is the core technology for 3C (Computer, Communication and Consumer Electronics) manufacturing companies to achieve quality control and intelligent assembly of robots. However, the number of electronic components on PCB is large, and the shape is different. At present, the accuracy of the algorithm for detecting all electronic components is not high. This paper proposes an improved algorithm based on YOLO (you only look once) V3 (Version 3), which uses a real PCB picture and a virtual PCB picture with synthesized data as a joint training dataset, which greatly increases the recognizability of training electronic components and provides the greatest possibility for data enhancement. After analyzing the feature distribution of the five dimensionality-reduced output layers of Darknet-53 and the size distribution of the detection target, it is proposed to adjust the original three YOLO output layers to four YOLO output layers and generate 12 anchor boxes for electronic component detection. The experimental results show that the mean average precision (mAP) of the improved YOLO V3 algorithm can achieve 93.07%.
Highlights
The electronic information industry has the characteristics of high technology content, high added value and low pollution
With the improvement of the manufacturing process, materials and technology of electronic components, the appearance of electronic components has the characteristics of different shapes and large changes in size
Studying how to use efficient and fast target detection methods to detect a large number of electronic components on a PCB can provide more possibilities for defect detection and robot assembly of electronic products
Summary
The electronic information industry has the characteristics of high technology content, high added value and low pollution. In addition to traditional digital cameras, mobile phones, computers, and other 3C (Computer, Communication and Consumer Electronics) products, emerging 3C products have emerged in recent years: smart TVs, smartwatches, smart wearable devices, drones, sweeping robots, entertainment robots, etc. With the further development of market hotspot products represented by flat-panel TVs and smartphones, the electronic information industry has become increasingly influential in social change and is regarded as a strategic development industry by major countries around the. The traditional 3C industry is a labor-intensive industry, and labor is one of the major costs of
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
