Classification of egg embryos based on deep learning

Abstract

The invention provides a method for classifying egg embryos based on deep learning. The method includes: collecting images of 5-day embryos and dividing them into three types of samples according to normal embryos, aborted embryos, and spermless embryos; preprocessing the embryo images, and extracting images ROI area and normalize the size of the image; combined with the transfer learning method, use the CNN model pre-trained on ImageNet by the AlexNet classic network to perform fine-tuning training on the target set; use the trained model to discriminate the test image. Compared with the prior art, the present invention can successfully solve the multi-classification problem of the CNN model on the small-scale egg embryo data set, has high accuracy, and can meet the engineering requirements of egg embryo viability detection and classification.

Description

technical field [0001] The invention relates to image processing, deep learning and convolutional neural network, in particular to an embryo classification method. Background technique [0002] At present, in engineering, most of the viability detection and classification of chicken embryos adopt traditional artificial egg detection, and the viability of egg embryos is detected by judging the blood vessels of egg embryos with human eyes, but the method of human eye examination is easily interfered by subjective factors, and There are disadvantages such as visual fatigue and low detection efficiency, which are prone to false detection and missed detection, and it is difficult to meet the high standard requirements of the modern embryo detection and classification industry. Therefore, egg embryo classification detection technology has been extensively studied. [0003] There are many studies on the viability detection and classification of egg embryos using machine vision tech...

AI Technical Summary

Problems solved by technology

[0002] At present, in engineering, most of the viability detection and classification of chicken embryos adopt traditional artificial egg detection, and the viability of egg embryos is detected by judging the blood vessels of egg embryos with human eyes, but the method of human eye examination is easily interfered by subjective factors, and There are disadvantages such as visual fatigue and low detection efficiency, which are prone to false detection and missed detection, and it is difficult to meet the high standard requirements of the modern embryo detection and classification industry. Therefore, egg embryo classification detection technology has been extensively studied

[0003] There are many studies on the viability detection and classification of egg embryos using machine vision technology. Machine vision technology replaces traditional manual inspection, and uses specific algorithms for image processing to carry out fine digital analysis and processing of embryo images, avoiding traditional manual inspection. However, the image processing process of this method is too cumbersome and the accuracy rate is not high

Images