Image identification method based on depth learning and transfer learning

Abstract

The invention provides an image identification method based on depth learning and transfer learning. The image identification method based on depth learning and transfer learning includes the following steps: 1) a preparation step: reading a pre-training model, reading an image directory, and dividing a training set, a verification set and a test set; 2) a training step: constructing a full connection neural network classifier, taking the image set as input of the pre-training model, and using the output of the pre-training model to update the full connection neural network classifier; and 3) a storage step: storing the model result. The image identification method based on depth learning and transfer learning has the advantages of integrating with the application of depth learning and transfer learning so as to provide a relatively accurate bladder cancer diagnosis result for a user, on the basis of the extremely limited training time and training sample quantity.

Description

technical field [0001] The invention belongs to the technical field of image recognition, and in particular relates to an image recognition method based on deep learning and transfer learning. Background technique [0002] With the advent of the era of big data, deep learning technology is increasingly used in the application of image recognition. Deep learning is a powerful technique derived from artificial neural networks. The artificial neural network is inspired by the neural network of natural creatures. By constructing multi-level neurons and repeated training with a large amount of data, it can achieve the ability to accurately recognize images similar to humans. [0003] In the field of image recognition, deep learning technology has been proved to be the most effective means by numerous facts. Theoretically, a model with more parameters has higher complexity and greater capability, but it also means that the training efficiency is relatively lower and it is easier...

AI Technical Summary

Problems solved by technology

However, we see that machine learning algorithms have a key problem in current image recognition research: a large amount of labeled training image data in some emerging fields is very difficult to obtain

For image recognition in the medical field, due to the lack of professional image materials and the support of medical experts, many image recognition tasks have long training times, insufficient samples to support the training of convolutional neural networks, and poor performance of the model on new samples. many problems

Images