Automatic measurement method for morphological parameters of prawn based on image recognition and cascade classifier

Abstract

The invention relates to the technical field of image collection and recognition, and specifically relates to an automatic measurement method for morphological parameters of a prawn based on image recognition and a cascade classifier. The automatic measurement method comprises the steps of S1, collecting a plurality of prawn color images to serve as samples; S2, training the samples, and then classifying the trained samples to obtain an LBP feature based cascade strong classifier; S3, collecting a prawn color image A to be measured, and performing normalization correction on the prawn color image A to obtain a normalized image B; S4, performing image segmentation on the normalized image to obtain a segmented image B; S5, performing ruler measurement on a segmented image C obtained in the step S4 to obtain a measurement image D; S6, performing image correction on the measurement image D obtained in the step S5 to obtain a corrected image E; and S7, recognizing the corrected image E by using the cascade strong classifier, and calculating morphological parameters of the prawn to be measured. According to the algorithm, accurate measurement for the morphological parameters of the prawncan be accurately implemented, and the measurement accuracy and the measurement efficiency can be improved.

Description

technical field [0001] The invention relates to the technical field of image acquisition and identification, in particular to an automatic measurement method for morphological parameters of prawns based on image identification and cascade classifiers. Background technique [0002] With the rapid development of society and economy, people's demand for prawns continues to increase, and the external morphology of prawns is an important basis for identifying species, and it is also an important reference for revealing the growth performance and health of prawns. my country has many prawn species such as Litopenaeus vannamei, Penaeus monodon, Penaeus japonicus and Penaeus sinensis, etc. Since 1997, the innovation of the shrimp seed industry has begun, and in 2004, my country's first new species of prawn "Huanghai No. 1" was bred. At present, more than ten new species of prawns with excellent economic characteristics have been bred, such as the new fast-growing variety of Litopenae...

AI Technical Summary

Problems solved by technology

Although it does not need to extract the features of the circumscribed rectangle after the image is rotated at any angle when the image is rotated, it solves the problem of extracting parameters of multiple circumscribed rectangles brought about by the rotation of the image, but this method does not need to extract the parameters of multiple circumscribed rectangles caused by the rotation of the image. The ratio of the length to the area is used to calculate the circularity feature, and then the training calculation is performed according to the circularity feature parameter and the color feature parameter. The original data of the neural network data source has gone through a two-stage calculation process, the calculation amount is large, and the error is doubled. Zoom in, so it trains the neural network through a large number of data sources, and the error of the trained classifier is also very large. This method is still feasible for qualitative judgment (whether it is diseased or not), but if quantitative analysis is required, it is necessary to calculate a specific target graph If the value of the objective parameter is large, it will cause a large error and cannot be applied, and the measurement efficiency is low due to the large amount of data processing brought by the two-level calculation.

Images