Implementation of Animal Graphic Processing System for Process Design

  • Bin Xiao
Keywords: Process Design, Animal Graphic Image, Graphic Image Processing, Computer Image Processing System

Abstract

With the development of science and technology, graphic processing technology is constantly
updated and advanced. The processing of graphics and images plays an extremely important role in process
design. All process information is expressed in the form of graphics or images, but the current process system
platform only supports graphics or images in one direction, and can not meet the needs of users to process
graphics and images at the same time. Using computer image processing technology, through the processing of
animal graphic images, mastered the computer image processing technology of animal graphic images;
collecting the original animal graphic images, combined with computer image processing technology, realized
the processing of animal graphic images, graphic images of animals are applied to the process design. This
paper briefly discusses the basic structure and organization module of graphic image processing technology, as
well as the management of related process design. Finally, the research and application of animal graphic image
processing technology oriented to process resources are systematically analyzed. In this paper, the animal
graphic image processing oriented to process design is the research background, the characteristics of the
process design and the new requirements are analyzed. A animal graphic image processing system oriented to
the process design is researched and developed. This paper uses the similarity of neuron synchronization based
on pulse coupled neural network. The color image denoising method of ignition characteristics, the image
segmentation method uses the color image segmentation method based on Shannon entropy and pulse coupled
neural network. The method adopted in this paper comprehensively compares the effect of image denoising on
VMF, BVDF, The DDF, WVF, and SVF methods are better. In terms of image segmentation effect, the method
used in this paper has higher entropy value and shorter execution time than other methods. The overall effect is
better than the HOPFIELD method and the multi-spectral threshold method. The ANN method, the K-means
clustering method, the fuzzy method and the VPCNN method are better.

Published
2019-11-01