Animation Effect Production and Design based on Optimized Deep Neural Networks using Enhanced Crayfish Optimization

As computer technology advances, animation is employed by many various organizations due to its increased performance, simplicity, and effectiveness. Animation is commonly used in multimedia performances and simulation platforms, which benefit from reliable course websites and precise network animation resources. Two issues have recently emerged for knowledge-based autonomous animation production systems including insufficient learning capacity and data waste on the website and lack of the animation effect generated. So, to address these two issues, an Enhanced Cray Optimisation Algorithm with Deep Neural Network (ECOADNN), a Deep Learning (DL) based optimized animation learning system is proposed. It uses Image Retrieval (IR) technology of early animation effects to continuously learn experience and generate the most popular animation effects for animation effect production and design. In contrast to current methods such as Three Spatial Forms (3SF) and Computer-Aided Design, Reinforcement Learning, and Computer Vision (CAD-RL-CV), the proposed ECOA-DNN obtains a higher accuracy of 99.94% and outperform the conventional techniques.