Fish recognition method and device based on PCA, and storage medium

Abstract

The invention provides a fish recognition method based on a PCA, and the method comprises the steps: extracting a feature point of a fish contour image; forming a horizontal coordinate matrix throughthe horizontal coordinates of the feature points, and forming a vertical coordinate matrix with the vertical coordinates of the feature points; carrying out the standardization processing of the horizontal coordinate matrix and the vertical coordinate matrix, and obtaining a standard horizontal coordinate matrix and a standard vertical coordinate matrix; carrying out the principal component analysis of the standard horizontal coordinate matrix and the standard vertical coordinate matrix to obtain a main component for distinguishing fishes; and completing the recognition of the fishes accordingto the main components of the fishes. The invention also discloses active interactive equipment and a non-transient readable storage medium, so as to achieve the above method. The method can achievethe effective recognition of different fishes.

Description

technical field [0001] The present invention relates to the field of image recognition, and more specifically, to a PCA-based fish recognition method, device and storage medium. Background technique [0002] In the research and application of many fields, it is often necessary to conduct a large number of observations on multiple variables that reflect things, and collect a large amount of data for analysis and search for laws. Large multivariate samples will undoubtedly provide rich information for research and application, but it also increases the workload of data collection to a certain extent. More importantly, in most cases, there may be correlations between many variables, which increases It increases the complexity of the problem analysis and brings inconvenience to the analysis. For example, in fish research, due to the variety of fish species and different shapes, the collection and analysis of fish data will encounter the above problems. Therefore, it has become...

AI Technical Summary

Problems solved by technology

Large multivariate samples will undoubtedly provide rich information for research and application, but it also increases the workload of data collection to a certain extent. More importantly, in most cases, there may be correlations between many variables, which increases Increased the complexity of problem analysis, and at the same time brought inconvenience to the analysis

Images