Three-Dimension Animation Character Design Based on Probability Genetic Algorithm

The Three-Dimension (3D) animation design typically rely on front and back information is critical component in many downstream image processing task such as activity recognition and motion tracking. However, there is currently a lack of automated approaches for generating anime character in the 2D design and 3D design is performed efficiently but computational high and many similarity characters. This paper, proposed Probability Genetic Algorithm (PGA) method is performed efficiently by using 3D animation is detecting the similarly of another animation character design. The PGA is automating a time-consuming process allowing rapid generation of diverse character designs and helps to explore a wider design specific parameter and constraints to be incorporated into the algorithm. Initial data acquire from the danbooru dataset and pre-processing using data augmentation for rotation, slipping to find the various direction of the animation character design. The proposed PGA method is evaluated using the danbooru data achieving a higher accuracy of 91.25% respectively. The existing techniques, Mask Region Convolutional Neural Network (RCNN) and Deep Neural Network (DNN) are evaluated the proposed method.