Injection Molding Inspection System Based on Machine Vision

Injection molding is a process which raw plastic materials are converted to plastic parts that are widely used in various industries like machinery, automobile, pharmaceutical, etc. This process is implemented by injection molding machines with mold component. Experience has shown that service life of mold directly influences the cost and quality of injection molding products. Therefore, injection molding requires an appropriate inspection system to make sure it could work normally and efficiently. Using an automated system instead of human monitoring, the inspection task will be more efficient and reliable. In this paper we employ an intelligent inspection system based on machine vision to protect mold from potential damages. Images provided by data acquisition section of the system will be processed by a computer vision based method. This method consists of a SVM model that classifies images based on features extracted by a LBP algorithm. In feature extraction phase, histograms of images are processed in a new way; which focuses on the most different parts between classes. Our experimental results show that the proposed method leads to a F-score of 96.7. Finally, the system will decide whether the machine stop or continue injection molding process depending on classification results.