Metal coin identification method based on deep neural network and apparatus thereof

Abstract

An embodiment of the invention provides a metal coin identification method based on a deep neural network. The method comprises the following steps that a first deep neural network model is designed based on a characteristic of a metal coin, and the first deep neural network model comprises a random noise network layer and a light noise processing layer; the random noise network layer is removed from the trained first deep neural network model so that a second deep neural network model is obtained; the second deep neural network model is used to identify the metal coin which is not identified. By using the method in the embodiment of the invention, the deep neural network model which can effectively remove influences of the random noise and the light noise of the metal coin can be obtained. The model is used to identify the metal coin so that an error-prone metal coin identification problem caused by metal coin abrasion or an illumination influence can be effectively avoided. Accuracy of the metal coin identification is effectively increased. Besides, the embodiment of the invention provides a metal coin identification apparatus based on the deep neural network.

Description

technical field [0001] Embodiments of the present invention relate to the field of neural networks, and more specifically, embodiments of the present invention relate to a metal coin identification method and device based on a deep neural network. Background technique [0002] This section is intended to provide a background or context for implementations of the invention that are recited in the claims. The descriptions herein are not admitted to be prior art by inclusion in this section. [0003] With the development of smart technology, the use and demand of image recognition is also developing rapidly. The so-called image recognition mainly includes: identifying the target object from the image, or identifying the category of an object in the image, etc. It can be understood as similar to when people face an image or a scene, they can distinguish and identify the objects appearing in the image or scene through the naked eye and brain. [0004] At present, the commonly ...

AI Technical Summary

Problems solved by technology

However, in the field of metal coin recognition, since the difference between different types of metal coins may be small, and the wear of metal coins may be serious, it is difficult for Hu invariant feature search to effectively capture the shape features of metal coins

[0008] 3) Based on the SIFT feature point matching search, since there are many similar textures of metal coins, and the edge feature reflection of the font position may be serious, and there may be different degrees of wear and tear, it is easy to extract effective SIFT feature points. Few problems, so that the mismatch phenomenon is serious

Images