Unlock instant, AI-driven research and patent intelligence for your innovation.

Coin identification method and processing terminal based on deep learning convolutional neural network

A convolutional neural network and coin recognition technology, applied in neural learning methods, biological neural network models, coin inspection, etc., can solve problems such as low recognition rate, long recognition process time, and low recognition efficiency, achieving high recognition rate, The effect of strong real-time computing ability and small resource occupation

Active Publication Date: 2021-05-28
PCI TECH GRP CO LTD
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The traditional recognition of the authenticity of coins is usually based on physical characteristics such as the weight and diameter of the coin. This recognition method has a low recognition rate, and the recognition process takes a long time and the recognition efficiency is low.

Method used

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
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Coin identification method and processing terminal based on deep learning convolutional neural network
  • Coin identification method and processing terminal based on deep learning convolutional neural network
  • Coin identification method and processing terminal based on deep learning convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] Below, in conjunction with accompanying drawing and specific embodiment, the present invention is described further:

[0037] Such as figure 1 As shown, a coin identification method based on deep learning convolutional neural network, including the following steps:

[0038] Step 1: Get training set and validation set

[0039] In this embodiment, 5 different coins are collected, including old genuine coins, new genuine coins and other 3 kinds of fake coins, such as collecting the fourth set of real coins including all denominations, the fifth set of real coins including all denominations and including all The fourth set of fake coins of currency value, the fifth set of fake coins including all currency values, and the third set of fake coins including all currency values, and according to the front and back of the coin (defining the currency value, one side is the front and the other side is the reverse) will be 5 different Coins are divided into 10 categories. Taking ...

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

PUM

No PUM Login to View More

Abstract

The present invention relates to a coin identification method and a processing terminal based on a deep learning convolutional neural network. The method includes the following steps: Step 1: Obtain a training set of several coin images including real coins and counterfeit coins and several real coin images The verification set; Step 2: Input the training set and the verification set to the preset convolutional neural network, train the convolutional neural network, and obtain the trained convolutional neural network; Step 3: Pre-recognize the coin image to be recognized processing to obtain the clearest coin image; step 4: input the clearest coin image into the trained neural network obtained in step 2, so as to identify the authenticity of the coin corresponding to the clearest coin image. The invention can effectively identify the authenticity of coins, has high identification rate and wider application range.

Description

technical field [0001] The invention relates to the technical field of coin identification, in particular to a coin identification method and a processing terminal based on a deep learning convolutional neural network. Background technique [0002] In many occasions, coins are needed, especially in self-service coin-operated shopping and consumption occasions, such as self-service vending machines in shopping malls, where coins are placed for self-service shopping, and for example, coins are placed in subway coin-operated machines to buy subway tickets , occasions like these face a large number of coin drops every day. In such a large amount of coin injection process, a very important problem is to ensure that the authenticity of the inserted coins can be identified, and the counterfeit coins can be identified to avoid losses. The traditional recognition of the authenticity of coins is usually based on physical characteristics such as weight and diameter of the coin. Such r...

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

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06T7/194G06T7/13G06T5/30G06T5/00G06N3/08G06N3/04G07D5/00
CPCG06N3/08G06T5/002G06T5/30G06T7/13G06T7/194G07D5/005G06N3/045
Inventor 丁保剑冯琰一孙树文
Owner PCI TECH GRP CO LTD