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

System and method for distinguishing words and graphics in an image using neural network

A neural network and text technology, applied in character and pattern recognition, instruments, computer parts, etc., can solve the problem that neural network technology is not suitable for multifunctional business machines

Inactive Publication Date: 2007-05-23
PRIMAX ELECTRONICS LTD
View PDF3 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For the application of multi-function business machines, under the double consideration of speed and memory, the existing neural network technology is obviously not suitable for application on multi-function business machines, as a technology for separating text and graphics in images

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
  • System and method for distinguishing words and graphics in an image using neural network
  • System and method for distinguishing words and graphics in an image using neural network
  • System and method for distinguishing words and graphics in an image using neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0041] Before explaining the system and method for using the neural network to distinguish characters and graphics in images of the present invention, first introduce the basic neural network architecture, as shown in Figure 1, the neural network includes an input layer 11, a hidden layer 12 and an output layer 13 , where the input layer 11 has multiple neurons (8 points), which can input the data to be processed (for example, the grayscale value of the pixel); the hidden layer 12 has multiple neurons (13 points), which can record the temporary Processing results; the output layer 13 has a plurality of neurons (4 points), which can output the output value (output information) processed by the neural network. There is a connection between each neuron in the input layer 11 and each neuron in the hidden layer 12, and each connection has a weight value. Similarly, there is a connection between each neuron in the hidden layer 12 and each neuron in the output layer 13, and each conn...

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

This invention relates to a system and method to resolute image and fonts by use of neutral network, which uses network pre-study font resolution and processes the gray ladder image data about color brightness in the image block to generate one maximum font confidence value and decides the font status in the image block according to the comparing results between the font gate value and maximum font confidential value, wherein the confidential value is larger than the font gate value to determine the image block with font picture element; if not, the image block is all graph picture element.

Description

technical field [0001] The present invention relates to an image data processing technology, in particular to an image processing technology for distinguishing text pixels and graphic pixels from image data by using neural network technology, so as to achieve the purpose of image-text separation. Background technique [0002] Multi-function peripheral (MFP) is an image processing device that combines multiple functions such as scanning, copying, and printing. Because of the advantages of integrating multiple functions, it is deeply loved by consumers and has gradually become to become a mainstream commodity in the market. Among them, the copying function of the multi-function business machine can be described as a combination of its scanning and printing functions. For example, when the copy function is in operation, the scan function is activated, and its photosensitive coupling device (Charge Coupled Device, CCD) scans the document into an image data; and the print functi...

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): G06K9/20
Inventor 黄俊嘉
Owner PRIMAX ELECTRONICS LTD