Fault identification on cigarette packets - an image processing approach

摘要

The proposed work presents a technique for an automated process for fault diagnosis in cigarette packets. The proposed work is based on application of image processing techniques in LabVIEW platform. The objectives of the proposed work are (i) to count the number of cigarettes in an open packet, and (ii) to check for defects, if any, in the barcode. National Instrument's Smart camera is used to capture images of cigarette packets moving in a conveyor belt and process the images to fulfill the above objectives. The technique was subjected to offline and on-line testing on more than 50 cigarette packets from five different vendors. The results obtained are found to be acceptable in all cases to fulfill the objectives.