A domestic garbage target recognition system combining computer recognition and human interaction

Abstract

The present invention is a household waste target recognition system combining computer recognition and manual interaction, comprising a morphological recognition module, an intermediate result comprehensive processing unit and a manual auxiliary processing module; Each frame of the image is subjected to morphological comprehensive processing, and after identifying and eliminating the duplicate targets, the target information and the image highlighting the target are sent to the intermediate result comprehensive processing unit, and the image is sent to the artificial auxiliary processing module; The frame-processed images are displayed continuously. According to the specific conditions of the captured optical images, manually click on the target objects that are not recognized by the morphological recognition module on the screen on the displayed image, and the module will send the corresponding click information to the intermediate result. The integrated processing unit and the intermediate result integrated processing unit further eliminates duplicate targets according to the received information, and finally outputs the coordinate and angle information of the target object.

Description

technical field [0001] The invention relates to a domestic garbage target recognition system which combines computer recognition and manual interaction. Background technique [0002] In machine vision technology, the existing image recognition methods usually extract certain features, compare the obtained features with ideal values, and compare the high similarity as the recognition result. [0003] In the field of multi-target sorting, there are many target categories and feature types that need to be identified, such as bottles and cans of various shapes and colors. Due to the large amount of calculation of feature extraction, the method of extracting multiple features cannot be achieved in real time. Meet the requirements; and the accuracy of the feature extraction method has not been high, and it is difficult to meet the use requirements in the industrial automation production line. Contents of the invention [0004] The technical problem of the present invention is: ...

AI Technical Summary

Problems solved by technology

[0003] In the field of multi-target sorting, there are many target categories and feature types that need to be identified, such as bottles and cans of various shapes and colors. Due to the large amount of calculation of feature extraction, the method of extracting multiple features cannot be achieved in real time. Meet the requirements; and the accuracy of the feature extraction method has not been high, and it is difficult to meet the use requirements in the industrial automation production line

Images