Neural Network Model for Perceptual Evaluation of Product Modelling Design Based on Multimodal Image Recognition

With the homogenization of product function and performance, the design technology for product appearance quality has been increasingly valued by academia and industry and has become an effective technical way to meet the continuously growing diversified and personalized needs of consumers. The appearance quality attribute of a product can be characterized or described by its appearance image. Data-driven product appearance image design is based on the quantitative data of product appearance and consumer emotional needs and completes the product appearance through computer-aided design technology and intelligent algorithms. Design innovation can help companies quickly respond to consumers' emotional needs and effectively improve design quality and product competitiveness. When visual objects are disturbed in complex scenes, the issues such as how the human brain coordinates multisensory information processing and what neural processing mechanisms follow are still unclear. In this paper, a visual object recognition experiment in a complex scene was designed and the brain activation signals of three modalities of noise, added audio-visual (AVd), single visual noise and noise (Vd), and single-audio (A), were recorded. The properties and neural processing mechanisms of multisensory modulation of auditory stimuli during noisy image recognition were explored. Using the conjunction method combined with the classic “max criterion” rule, it was found that only when a certain amount of noise was added to the visual stimulus, the integration area changed. The product appearance has a decisive influence on the user's product perceptual attribute preference and greatly affects the consumer's satisfaction. The importance of product appearance image design is increasingly prominent. In addition, pattern analysis of brain activation signals confirmed that semantically consistent sounds can facilitate the recognition of noisy images and this facilitation shows a certain category selectivity when subdivided into categories. Using the analysis method of functional connectivity, a functional connectivity network containing nodes at different integration levels was constructed to explore the overall characteristics and processing patterns of the multisensory network. Through the analysis of the network connection relationship, it is found that the prefrontal cortex, STS, and lateral occipital lobe are the nodes with more aggregation in the network, and their functions are similar to the hub in the network. The brain functional network was constructed, and functional connectivity was used to explore the connection characteristics of the network and the multisensory modulation mechanism between different processing levels of the brain.