Method for identifying tea leaves based on colors and shapes

Abstract

The invention discloses a method for identifying tea leaves based on colors and shapes. By comprehensively utilizing a computer vision and image processing technology, increasing shape parameters of the tea leaves and improving a neural network algorithm, the automation for indentifying the qualify of the tea leaves is realized. The method comprises the following steps of: directly obtaining tea leaf images by a digital camera or a video camera and carrying out conversion and pre-treatment on image formats; and then, enabling tea leaf color characteristic parameters extracted based on an HSI (Hue-Saturation-Intensity) model and tea leaf shape characteristic parameters extracted by binary images to pass through a genetic neural network; and finally, finishing the automatic identification of the tea leaves. Through the way, a better identification effect can be obtained and the processing time of colored images is greatly shortened, thereby high coincidence between a detected result and a manual detected result is realized.

Description

technical field [0001] The invention relates to a method for identifying tea leaves with computer vision technology, in particular to a method for identifying tea leaves based on color and shape. Background technique [0002] At present, the quality grade review of tea in my country is still mainly based on sensory evaluation. The sensory evaluation of tea quality usually first examines the appearance of tea, including the color and shape of tea. There are many types of tea in my country, and the shape of tea is various. Therefore, there is a certain degree of subjectivity in the sensory evaluation of tea quality, and the human operation is easily disturbed by external factors such as the environment, thus affecting the accuracy of the evaluation results. [0003] With the application of computers in modern agriculture, the standardization of tea evaluation has been promoted. In order to have a strict and consistent standard in the process of tea production and distribution, ...

AI Technical Summary

Problems solved by technology

[0004] When manually detecting tea leaves, the color difference of tea is an important basis for recognition. When detecting with a computer vision system, the recognition mechanism of the human eye is simulated, and color is also selected as the main characteristic parameter. Usually, the image information obtained from the camera is composed of RGB components. However, due to the small difference in tea color, the distribution of RGB values ​​in the tea image has no obvious rules to follow, and direct use of these components often cannot obtain the desired effect, which is not conducive to being directly used as identification feature parameters

[0005] In addition, the BP neural network algorithm is used to automatically identify tea quality in the current computer identification system. This algorithm has a very slow convergence speed and is prone to fall into a state of local minimum and weak global search ability.

Images