High-Precision Medicine Bottles Vision Online Inspection System and Classification Based on Multifeatures and Ensemble Learning via Independence Test

Abstract

To address the problem of online automatic inspection of drug liquid bottles in production line, an implantable visual inspection system is designed and the ensemble learning (EL) algorithm for detection is proposed based on multifeatures. A tunnel structure is designed for visual inspection system, which allows the bottles inspection to be automated without changing original processes and devices. A high-precision method is proposed for vision detection of drug liquid bottles. A local background difference method is utilized as a soft ON–OFF to capture the bottle image. An image gray-level equalization preprocessing technology is used to eliminate the impact from illumination. Three features are designed, which contains blocked histogram of gradient, blocked histogram of gray, and raw pixel. An EL algorithm is proposed based on independence test and multifeatures, after theoretically analyzing the precondition of precision boosting to EL. Some results of analysis and comparison prove that the proposed method is advanced compared with baseline methods. Specially, there exist remarkable advantages in our method when there are some noises in sample labels. Then, we carried on a 72-h continuous test on a practical production line, in which the error rate of inspection is less than 1‰. In terms of time and precision, it is superior to the traditional manual detection. Hence, the test results prove that the visual inspection system designed and algorithm proposed are advanced and practical.