Method for automatically identifying species of common freshwater fish based on images

Abstract

The invention discloses a method for automatically identifying species of common freshwater fish based on images. The method comprises the following steps: firstly, extracting a fish outline, sequentially carrying out complanation, length unification and fish head identification treatment on the obtained outline, then extracting an included angle of the head of a fish body, a vertice of the included angle, a height of a tail caudal peduncle, and a middle point of the tail caudal peduncle, further calculating a characteristic value of the included angle of the fish head and the width-length ratio of the fish, and finally, identifying four common freshwater fish of parabramis pekinensis, crucian carps, silver carps and grass carps by taking the included angle of the fish head and the width-length ratio of the fish as characteristics. The method provided by the invention is more reliable than a method of utilizing color characteristics obviously influenced by surroundings and illuminationor utilizing fish back outline characteristics obviously influenced by fins deformation to identify the fish species.

Description

technical field [0001] The invention relates to the field of target recognition, in particular to an automatic recognition method for common freshwater fish species through image processing. Background technique [0002] Before deep processing of freshwater fish as food, it is necessary to complete the task of classifying different types of fish. During the breeding period of freshwater fish, it is also necessary to distinguish different types of fish and collect their characteristic information. The traditional method is manual selection. This method exists The disadvantages are: bad working environment, high labor intensity, easy to damage fish body (such as fish scale falling off, fish fin damage, etc.), low efficiency and affecting the quality of fish. [0003] In order to realize automatic recognition of freshwater fish, image processing technology has been applied to the field of freshwater fish recognition. At present, there are three main methods of fish recognition...

AI Technical Summary

Problems solved by technology

[0002] Before deep processing of freshwater fish as food, it is necessary to complete the task of classifying different types of fish. During the breeding period of freshwater fish, it is also necessary to distinguish different types of fish and collect their characteristic information. The traditional method is manual selection. This method exists The disadvantages are: harsh working environment, high labor intensity, easy to damage the fish body (such as fish scales falling off, fish fin damage, etc.), low efficiency and affecting the quality of fish

Although the above three methods can identify different fish bodies, the identification results are easily affected by the following factors: 1) the angle and intensity of light irradiation are different; 2) the different stages of freshwater fish (juvenile fish, adult fish, Big fish); 3) The surface color of the fish body, tail, and fins are prone to obvious changes due to external influences

Images