Intelligent sorting system for batch detection of pearl shapes based on machine vision

Abstract

The invention discloses an intelligent sorting system for detecting pearl shapes in batches based on machine vision, which includes a frame-shaped support for carrying equipment. Sorting mechanism, the lower part is provided with a conveyor belt, and the conveyor belt is provided with three top plates and three bottom plates evenly distributed, and holes arranged in a staggered manner are arranged in the middle of the top plate; the feeding mechanism includes a square hopper, connecting rod, vibrating motor; the visual detection mechanism includes a camera, LED surface light source, computer, drive motor, track connecting rod, lower mold plate; the sorting mechanism includes a sorting robot and a sorting container, and the sorting robot is set directly above the top plate. This system can automatically complete the simultaneous detection and sorting of multiple pearls, and the combination of multiple lines can also screen the size of the pearls. It has a simple structure, low manufacturing cost, can realize batch detection, and is easy to use and maintain.

Description

technical field [0001] The invention relates to detection based on machine vision, in particular to an intelligent sorting system for batch detection of pearl shapes based on machine vision. Background technique [0002] China's freshwater pearl production accounts for more than 95% of the world's pearl production, and its output value only accounts for 10% of the global pearl output value. The realization of automatic pearl sorting based on machine vision is extremely important for improving the output value of the entire industry. According to the promulgation of the national grading standard for cultured pearls (GB / T 18781-2008), the grading standards for pearls are clearly stipulated, and there are clear indicators for the grading of shape, color, size, and smoothness. To realize automatic sorting by machines, the first step is to The technical problem to be solved is the acquisition of the pearl image. The image is flat and the pearl is three-dimensional. Only by obtain...

AI Technical Summary

Problems solved by technology

The shortcomings of this invention in terms of image acquisition technology: multiple high-speed cameras are used to obtain the surface of the pearl from different angles, which increases the cost; on the other hand, when grading the shape of the pearl, the distance between each camera and the pearl must be guaranteed It is difficult to unify, and the transparency of the glass tube is very high. Improper treatment of the light source will also cause reflection and refraction to affect the detection

The invention has disadvantages in image acquisition: fixed-point shooting makes it difficult to realize production, and the feeding action mechanism is complicated. The detection of each pearl requires the movement of the movable ejector rod, which is easy to wear, increases the cost and prolongs the pearl sorting time.

[0005] The above two examples are two kinds of single pearl detection methods. Although single detection has incomparable advantages in accuracy, the efficiency problem is obvious; if batch detection is required, batch detection equipment is required, and the cost is high

Images