MUMBAI, India, Aug. 17 -- Intellectual Property India has published a patent application (202641065111 A) filed by Srm Trp Engineering College on May 23, 2026, for Image Processing–based Automated Surface Defect Detection In Smartphone Printed Circuit Boards (pcbs).
Inventors include Dr. A Muthuraj; Reeshwar Ravikumar; Rishikeshwaran M; Sudharsan L S; and Yoghanaarayanan A.
The application for the patent was published on August 14, 2026, under issue no. 33/2026.
Abstract: This invention presents an image processing–based automated system for detecting surface defects in smartphone printed circuit boards (PCBs). The system captures high-resolution images of PCB surfaces and processes them using several image preprocessing techniques including image resizing, grayscale conversion, Gaussian filtering, median filtering, histogram equalization, and edge enhancement to improve image clarity and reduce noise. Feature extraction techniques such as Canny edge detection, Gray Level Co-occurrence Matrix (GLCM), and shape feature extraction are applied to identify important defect patterns on the PCB surface. The extracted features are then used as input for machine learning classifiers including Artificial Neural Network (ANN) and Support Vector Machine (SVM). These classifiers analyze the extracted features and determine whether the PCB is defective or non-defective. The proposed system helps identify defects such as cracks, scratches, missing components, and irregular patterns on PCB surfaces. By automating the inspection process, the system improves the accuracy, efficiency, and reliability of PCB quality control in smartphone manufacturing industries.
Disclaimer: Curated by HT Syndication.
