This computer-implemented algorithm identifies printed circuit board (PCB) components for quality control. Printed circuit board (PCB) component detection is essential for PCB manufacturing. Color image processing provides a rough estimate of a component’s location, and superpixel segmentation further refines the approximate location. While these techniques distinguish the background board color from components of interest, they do not always distinguish components from the background and may detect undesirable background areas as components of interest. A more efficient and effective printed circuit board (PCB) design and manufacturing process is needed; automated PCB component estimation solutions can address this.
Researchers at the University of Florida have developed an image-processing algorithm for identifying printed circuit board (PCB) components. This computer-implemented method comprises chromaticity-based image background subtraction via one or more processors, generating a noise-removed PCB image for AI-assisted component identification. Automating component detection increases the efficiency of printed circuit board manufacturing processes.
Reduces printed circuit board (PCB) image visual noise and unnecessary textures, efficiently locating PCB components
This computer-implemented algorithm uses chromaticity-based background noise subtraction to eliminate visual noise from printed circuit board (PCB) images to identify components. The printed circuit board images are first processed using a chromaticity-based algorithm, subtracting background noise, and enhancing the visual quality. An AI model trained to identify PCB components processes the images for fast and efficient identification. The accuracy of component identification is improved by reducing visual noise and using AI-assisted techniques. This algorithm applies to manufacturing settings to enhance the quality control of printed circuit boards and improve the reliability of electronic devices using them.
