Detection and Categorization of Defects on Paperboards using Image Processing

Abstract

This project proposes an effective method for detecting defects in paper boards. In the paper industries, the final stage of paperboards has many defects such as black spots, dirty marks, oil spots etc. They perform inspection manually. However, such detection methods are much expensive (i.e., labor cost) and time consuming. To overcome these problems, a method has been introduced to detect defects automatically and effectively in paper based on image processing. Although, most of the image-based approaches focus on the accuracy of fault detection, the computation time is also important for practical applications. The proposed method comprises of three steps. At the first step, the acquired RGB (Red, Green and Blue) image of the paper is converted into a gray scale image using LabVIEW tool which comes under preprocessing. Secondly, it extracts the dimensions of the paper. Finally this detects and identifies the defects i.e., holes and black spots on the paper based on their characteristics which comes under noisy object elimination. The operators at that work place are then intimated through an alarm signal.