Computer identification and artificial interaction combined household garbage target identification system

Abstract

The invention provides a computer identification and artificial interaction combined household garbage target identification system. The system includes a morphological identification module, an intermediate result comprehensive processing unit and an artificial assistant processing module, the morphological identification module receives the optical image shot by a sampling camera in real time and performs the morphological comprehensive processing of each frame of the received image, and after the repeated targets are identified and rejected, the target information and the image highlighting the targets are transmitted to the intermediate result comprehensive processing unit, and the image is transmitted to the artificial assistant processing module, the artificial assistant processing module continuously displays each frame of the received and processed image, one clicks the targets, which are not identified by the morphological identification module on the screen, on the displayed image based on the specific condition of the shot optical image, the module transmits the information corresponding to the clicking to the intermediate result comprehensive processing unit, and the intermediate result comprehensive processing unit further rejects the repeated targets based on the received information and the target coordinate and angle information is finally output.

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