Metal coin identification method and device based on deep neural network

A deep neural network and metal coin technology, applied in the field of neural networks, can solve the problems of edge feature reflection, wrong matching, and small difference in the font position, so as to avoid errors and improve accuracy.
CN104866868BActive Publication Date: 2018-09-07HANGZHOU LANGHE TECH
2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN Β· China
Patent Type
Patents(China)
Current Assignee / Owner
HANGZHOU LANGHE TECH
Publication Date
2018-09-07

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

Embodiments of the present invention provide a metal coin identification method based on a deep neural network. The method includes: designing a first deep neural network model based on the characteristics of the metal coin, the first deep neural network model including a random noise network layer and a light noise processing layer; removing the random noise network layer from the trained first deep neural network model to obtain The second deep neural network model: using the second deep neural network model to identify the metal coin to be identified. Through the method of the above-mentioned embodiments of the present invention, a deep neural network model that can effectively remove the influence of random noise and light noise of metal coins can be obtained, and metal coin recognition through this model can effectively avoid the damage caused by metal coin wear or light influence. The error-prone problem of metal coin identification can effectively improve the accuracy of metal coin identification. In addition, the embodiments of the present invention provide a metal coin identification device based on a deep neural network.
Need to check novelty before this filing date? Find Prior Art

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 ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More