Egg embryo classification based on deep learning

Abstract

The invention provides an egg embryo classification based on deep learning. The method comprises the following steps of: collecting embryo images of five days, and dividing the embryo images into three classes of samples including a normal embryo, a suspension embryo and a non-insemination embryo; preprocessing the embryo images, extracting the ROI (Region Of Interest) of each image, and carrying out normalization on the sizes of the images; combining with a transfer learning method, using a CNN (Convolutional Neural Network) model pre-trained by an AlexNet classical network in ImageNet to carry out fine tuning training on a target set; and utilizing the trained model to distinguish an image to be detected. Compared with the prior art, the egg embryo classification is characterized in that the problems of the multiple classifications of the CNN model on an aspect of a small-scale egg embryo data set can be successfully solved, the egg embryo classification is high in accuracy, and the engineering requirements of the detection and the classification of egg embryo survival can be met.

Description

Technical field [0001] The invention relates to image processing, deep learning and convolutional neural networks, and particularly relates to an embryo classification method. Background technique [0002] At present, in engineering, most of the detection and classification of chicken embryo viability use traditional artificial egg inspection. The embryonic blood vessels of the egg embryo are judged by the human eye to detect the viability of the egg embryo. However, the method of human eye biopsy is easily interfered by subjective factors, and There are shortcomings such as easy visual fatigue and low detection efficiency. It is prone to misdetection and missed detection. It is difficult to meet the high standards of modern embryo detection and classification industry. Therefore, egg embryo classification detection technology has been extensively studied. [0003] There are many researches on the viability detection and classification of egg embryos using machine vision technology...

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