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

Code spraying character recognition method based on probabilistic neural network

A probabilistic neural network and character recognition technology, applied in the field of inkjet character recognition based on probabilistic neural network, can solve the problems of inability to directly support multi-classification, noise sensitivity and low reliability.

Active Publication Date: 2020-02-07
西安海若机电设备有限公司
View PDF9 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The recognition method based on template matching has a simple algorithm and is easy to implement, but it is sensitive to noise and has low reliability; the method of support vector machine is suitable for small sample situations and has good generalization performance, but it cannot directly support multi-classification

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
  • Code spraying character recognition method based on probabilistic neural network
  • Code spraying character recognition method based on probabilistic neural network
  • Code spraying character recognition method based on probabilistic neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0031] refer to figure 1 , a method for recognizing coded characters based on a probabilistic neural network, comprising the steps of:

[0032] 1) Image preprocessing: image preprocessing is performed on the input RGB inkjet character image, that is, the collected RGB inkjet character image is converted into a grayscale image and Gaussian filtering is performed to denoise, so as to ensure that the overall grayscale distribution characteristics of the image remain unchanged. Such as figure 2 shown;

[0033] 2) Character positioning: such as image 3 As shown, FAST-16 corner point detection uses a certain pixel P as the center pixel point. In this example, the gray value of 16 field pixel points on a circle with a radius of 3 is considered. If these 16 pixel points are consecutive n Contiguous pixels, their gray values ​​are all higher than I p +t is greater, or both are greater than I p -t is small, satisfying the formula (1), then the pixel point p in the center of the c...

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 invention discloses a code spraying character recognition method based on a probabilistic neural network, and the method is characterized in that the method comprises the following steps: 1) preprocessing of an image; (2) character positioning, (3) character segmentation, (4) feature fusion, (5) training and (6) character recognition. The invention adopts a PNN training model to recognize codespraying characters, has the advantages of being high in accuracy, easy to train and high in convergence speed, and has good application value in the field of industrial code spraying character recognition.

Description

technical field [0001] The invention relates to a character intelligent recognition technology, in particular to a code-spraying character recognition method based on a probabilistic neural network. Background technique [0002] The production date, production batch and origin information of food and medicine are generally printed on the outer packaging bag with coded characters. Consumers and producers can use these coded characters to understand the relevant information of the product. At present, traditional inkjet character detection is done by human eyes, which is inefficient and expensive. Therefore, the research on the method of automatic recognition of inkjet characters has important application value to meet the safety of food and medicine. [0003] At present, the methods of inkjet character recognition include: a method based on template matching, a method based on a support vector machine (SVM), and the like. The recognition method based on template matching ha...

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 Applications(China)
IPC IPC(8): G06K9/34G06K9/62
CPCG06V30/153G06F18/253G06F18/214
Inventor 马玲罗晓曙赵书林郑伟鹏
Owner 西安海若机电设备有限公司