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

A go referee system based on mlp neural network and computer vision

A computer vision and neural network technology, applied in the field of MLP neural network and image recognition, can solve problems such as inapplicability, many influencing factors, and failure to achieve the effect, and achieve the effect of fast operation, high recognition accuracy, and high accuracy

Active Publication Date: 2021-08-27
SOUTHWEST UNIVERSITY FOR NATIONALITIES
View PDF13 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the effect that people want is still not achieved. The biggest problem is that there are many unforeseen influencing factors, so a specific method cannot be applied to all situations.

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
  • A go referee system based on mlp neural network and computer vision
  • A go referee system based on mlp neural network and computer vision
  • A go referee system based on mlp neural network and computer vision

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0041] The technical solutions in the embodiments of the present invention will be described clearly and in detail below with reference to the drawings in the embodiments of the present invention. The described embodiments are only some of the embodiments of the invention.

[0042] The technical scheme that the present invention solves the problems of the technologies described above is:

[0043] refer to figure 1As shown, the application diagram of the neural network 1 of the present invention is shown, which is the training process of the MLP artificial neural network, which is used to find the characteristics of the chessboard to determine the chessboard in the incoming picture. Specifically, input the picture into the training model:

[0044] 1) Mark out the checkerboard range in the input image.

[0045] 2) Using the multi-channel pixel values ​​in the marked range as feature values ​​to generate feature vectors.

[0046] 3) Iterative training to generate a chessboard...

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 claims a Go referee system based on MLP neural network and computer vision, which includes an image normalization processing module, an MLP neural network module and a Go referee algorithm module; the image normalization processing module is through channel transformation, image cutting , uniform light processing, corner detection and other means to preprocess the image to facilitate subsequent recognition; the MLP neural network module includes a chessboard recognition model and a chess piece recognition model, which is used to recognize the position of the chessboard and Reversi and save its information In the TXT file; the late stage Go referee algorithm module is used to judge the outcome of the game. By reading the state and position information of Reversi in the TXT file, the victory and defeat state of Reversi is obtained according to the algorithm, and the result is converted It is displayed to the user as an SGF (Go General Purpose) picture.

Description

technical field [0001] The invention belongs to MLP neural network and image recognition technology, and specifically relates to image acquisition and image processing technology. Background technique [0002] With the development of artificial intelligence, the application of deep learning and image recognition technology is more extensive. As the starting point of deep learning, MLP neural network has certain advantages in dealing with classification problems. In the field of Go, due to holding a large-scale Go game, a large number of Go referees need to be hired, the cost is high, and the judgment speed is slow, and judgment errors may also be made. Therefore, many people began to study algorithms, through image acquisition, image processing, and then through the Go discrimination algorithm to determine the outcome. Among the many methods, a fixed camera is used, which cannot be moved. Finding a nearly perfect shooting angle has high requirements for hardware equipment a...

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): G06K9/46G06K9/62G06T7/13G06T7/73
CPCG06T7/13G06T7/73G06T2207/10004G06T2207/10024G06T2207/20081G06T2207/20084G06T2207/20164G06V10/44G06V10/751G06F18/2413
Inventor 韩柯宋鹏云张寅睿刘阳辉虎帅珂杨鹏飞冉恒周航郭子铭完颜志峰
Owner SOUTHWEST UNIVERSITY FOR NATIONALITIES