Object outline extracting and matching device and method based on figure imaging

Abstract

The invention discloses an object outline extracting and matching device and method based on figure imaging. The device comprises a plane light source, a lens, a camera and a microprocessor; the planelight source arranged at one side of the lens generates approximate parallel light of which the main direction is perpendicular to the focal plane of the lens, and after an object to be detected is shaded, the parallel light is irradiated into the lens; the lens screens the incident light rays to converge a group of parallel light rays irradiated into the lens at a certain point of the focal plane of the other side of the lens, the camera placed at the point captures the light rays and generate an image, and the image contains the shade of the object to be detected; the microprocessor processes the image captured by the camera to obtain an outline curve of the object to be detected, and match the outline curve with an outline sample curve to recognize the object to be detected. The objectoutline extracting and matching device and method based on figure imaging are especially applicable to image recognition, transportation and positioning of objects such as package bottles, and have the advantages of being high in recognition rate, simple in structure and low in cost.

Description

technical field [0001] The invention belongs to the technical field of object image recognition and the technical field of waste intelligent recycling, and in particular relates to a device and method for extracting and matching contours of small objects such as packaging bottles based on back imaging. Background technique [0002] The development and promotion of intelligent recycling devices for waste plastic bottles and other garbage is considered to be one of the most effective ways to standardize the recycling system of packaging bottles and reduce "white garbage" pollution. In the intelligent recycling device for packaging bottles, object recognition technology is the core component. Efficient and ready identification can effectively eliminate wrong recycling and prevent recycling fraud, thereby greatly improving the reliability of the machine. [0003] The identification methods of Chinese patent applications CN 202762657U and 200620092237.8 are based on barcode scan...

AI Technical Summary

Problems solved by technology

Chinese patent application CN104408820A uses a camera to capture images of recycling compartments that do not contain and contain objects and use them as a base map and a comparison map to identify whether the object is a recyclable plastic bottle, but the recognition accuracy of this technology depends on the quality of the image

Chinese patent application CN101727703A discloses a tank image recognition device, which captures the image through a CCD camera and compares it with the image in the database, but does not give the technical details of the implementation

The application number is 200620092237.8. The Chinese patent application places light sources and photosensitive elements on both sides of the beverage bottle, but this can only determine the diameter of the object, and it is difficult to accurately detect and judge the beverage bottle put in.

In addition, there are other advances in the research on the shape image recognition of plastic bottles, such as machine vision methods, RGB methods, image comparison methods, etc. The above-mentioned technologies are complex and costly, and have not yet been applied to recycling machine products.

Images