Image classifying method based on transfer learning multiple attractor cellular automata (MACA)

Abstract

The invention discloses an image classifying method based on transfer learning a multiple attractor cellular automata (MACA) and mainly solves the problems that an existing image classifying method based on transferring cannot avoid the empty basin appearance, the similarities of a source domain sample and a target domain sample are not accurately calculated, the effect of transferring from the source domain sample to the target domain sample is poor, and the classification accuracy is low. The image classifying method comprises the steps: (1) performing image data pre-processing; (2) training a multiple attractor cellular automata (MACA) tree in a source domain space; (3) dividing a target domain training set; (4) constructing a local mode space training set; (5) training a multiple attractor cellular automata (MACA) tree in a local mode space; (6) generating a target domain multiple attractor cellular automata (MACA) tree. The image classifying method has the advantages of strong generalization ability and high classifying accuracy and effectively solves the problems that the existing image classifying method cannot avoid the empty basin appearance and poor transferring effect.

Description

technical field [0001] The invention belongs to the technical field of image processing, and further relates to an image classification method based on migration learning multi-attractor cellular automata in the technical field of machine learning. The invention utilizes a migration learning method to transfer the image knowledge of the source domain to the target domain for assisting the learning of the classifier and improving the classification accuracy of the image. Background technique [0002] As the use of digital images is increasing rapidly, it plays an increasingly important role in people's lives. In many image pattern classification problems, collecting training samples with class labels is expensive and time-consuming, meanwhile, it is difficult to train effective predictors based on limited labeled image data. Transfer learning uses the potential auxiliary knowledge of the source domain data to assist the learning of the target domain classifier. At present, ...

AI Technical Summary

Problems solved by technology

[0007] The train of thought of realizing the present invention is, use a kind of cellular automata classification method with empty basin judgment to generate multi-attractor cellular automata MACA tree, avoid the appearance of empty basin, improve the generalization performance of image classifier; At the same time, propose The new pattern distance measure is used to calculate the similarity between the source domain sample and the target domain sample of the image, which makes the calculation of the similarity between the source domain sample and the target domain sample of the image more accurate, and improves the transferability of the source domain sample; finally, For the problem that a small number of labeled samples in the target domain cannot reflect the overall distribution of samples in the target domain, the source domain training set and the target domain training set are divided into local pattern spaces, and then transfer learning is performed in the local pattern space, so that only a small number of target domains In the case of labeled samples, a better migration effect can also be achieved, thereby improving the classification accuracy of the classifier

Images