Empty bottle wall defect detection method and device

Abstract

The invention relates to an empty bottle wall defect detection method, which comprises the following steps: shooting two images by using a camera before and after the same empty bottle is rotated for 90 degrees during advancing, then transmitting the images to a CPU of an industrial personal computer to perform analysis on the images, and judging whether the bottle wall has defect. Image processing comprises the following steps: A, scanning edge point pairs on a bottle neck, positioning the bottle wall, and dividing a detection area of the bottle wall to perform subarea processing; B, pre-processing image data in the positioned area by adopting a grey stretching method; C, partitioning the images by adopting a maximum between-cluster variance method to acquire target information; and D, performing connectivity analysis on the partitioned bottle wall images, extracting characteristic data of each defect, and judging whether each detected connected domain has real defect according to the mass center position, posture ratio and area characteristic of the connected domain. The invention discloses a detection device used for the detection method at the same time. The detection method and the detection device are easily applied in detection equipment of an industrial flow line so as to realize automatic high-speed accurate detection on the empty bottle wall defect.

Description

[0001] technical field [0002] The invention relates to a method and a device for detecting a defect in a bottle wall, in particular to a method and a device for detecting a defect in an empty bottle wall. Background technique [0003] At present, beer and beverage production enterprises pay more and more attention to product quality, but the quality of bottles on the production line of enterprises is difficult to achieve the expected goal, and there are often defects such as cracks. Especially for recycled bottles that are repeatedly washed and reused, unwashed trademarks are likely to adhere to the bottle wall, so a comprehensive inspection of the bottle wall is required. Nowadays, most enterprises use manual inspection. When the bottles pass through the light inspection box installed next to the conveyor chain, the unqualified ones are found to be manually removed by naked eye observation. This traditional detection method has the following disadvantages: [0004] 1. T...

AI Technical Summary

Problems solved by technology

[0004] 1. The detection accuracy is low, which cannot meet the customer's requirements for product quality, and it is difficult to detect small defects, which brings hidden dangers to the safety of food packaging;

[0005] 2. The detection efficiency is low, which cannot meet the needs of high-speed production of automated production lines;

[0006] 3. The inspectors are prone to fatigue and cannot maintain the inspection standards;

[0007] 4. Manual work is not conducive to the integration of information

Chinese patent 200710028027.1 "A method and device for detecting defects in the mouth of an empty bottle" The detection method cannot be transplanted into the detection of the bottle wall due to the characteristics of the bottle wall itself: the method of direct reflection of the light source can obtain a circular plane The image of the bottle mouth, but it is not suitable for the 360-degree three-dimensional bottle wall with obvious transmission and inconspicuous reflection. The difference in shape characteristics of the bottle mouth and wall images also makes the processing methods have different characteristics

Images