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
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
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...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 