Analysis of Computer Multimedia Aided Design and Hand-drawing Effect Based on Grid Resource Sharing Collaborative Algorithm

Abstract

Hand-drawn has received numerous attentions in the computer vision since it is one of the few visual descriptors that accurately signify visual information. But, designers need a lot of time, effort, and highly skilled producers. They also need high-performance computer technology; otherwise, rendering times could be long. Initially, the data are collected from60k Airbag CAD Design dataset and are fed to pre-processing segment. In pre-processing, Multimodal Entity Graph Collaborative Filtering (MEGCF) is used to eliminate noise from the image. Multi-Objective Matched Synchrosqueezing Chirplet Transform (MOMSCT), was used for extracting the features such as shape, color, and texture. The functionality, geometry and hierarchy are classified using Historical Information Passing Networks (HIPN). The neural network's weight parameter is optimized by the Kookaburra Optimization Algorithm (KOA), which enhances the HIPN. The CMADHAE- HIPN -KOA proposed is executed in Python. The proposed method is examined using performance measures, like accuracy, precision, sensitivity, computation time, and recall. Higher accuracy of 16.65%, 18.85%, and 17.89%, and higher sensitivity of 16.34%, 12.23%, and 18.54%, is achieved by the proposed CMADHAE- HIPN -KOA approach. In comparison to the existing approach, there are 14.89%, 16.89%, and 18.23% as well as 82.37%, 94.47%, and 87.76% less computing time.