AUTOMATIC INSPECTION OF LEVEL OF BEER BOTTLING USING IMAGE PROCESSING

Abstract

This thesis presents the design of automatic inspection of the level of bottling using machine vision system and also the working principle and the hardware structure of the system. The inspection the level of bottling is done using machine vision system via image processing by taking image of the bottle from a conveyor belt. A digital image processing and analysis-based approach is an essential and quick investigation of the level of beer bottling. In this work algorithm was developed for automatic inspection of the level of beer bottling system which consists of a computer program for processing image, and to classify the bottles as leveled, under filled or over filled. MATLAB programming language was used for image processing in inspection process. out of sixty bottle images samples used for verification, the algorithm identified the bottles as level filled, under filled or over filled liquids with an accuracy of 93.3% (56 bottles were properly filled) and 6.7% (4 bottles) were under filled or over filled. The research results showed that quality inspection, abnormality and irregular flow detection and count of bottles can be done using image processing, analysis and computer vision techniques.