OCR on Assembled PCB Components
Read any character text under challenging conditions
Graphical programming environment for deep learning-based industrial image analysis
Most chips assembled onto a PCB are labeled with a string of alphanumeric characters to track them through production. Specular glare can result in low-contrast images, which make it difficult for a machine vision system to locate and recognize characters. To successfully decode characters on electronic components and modules, an optical character recognition (OCR) system needs to tolerate reflective surfaces as well as deformed, skewed, and poorly etched characters.
With Cognex Deep Learning, it is easy to read deformed characters, despite image formation challenges. This deep learning-based approach to OCR saves time during training and development by reducing excessive labeling, and successfully reads characters in challenging situations. The software simply requires an engineer to set a region of interest and character size. Once set, the tool’s pretrained font library deciphers characters and reads strings without training. In situations where characters are very difficult to read, the software can be retrained directly using characters with variations.