The use of graphic design elements in commercial architectural design in the context of intelligence

Abstract

In this paper, firstly, in the context of intelligence, using techniques such as hierarchical features, local perceptual field, weight sharing, and spatial subsampling make the convolutional neural network with representational learning ability, certain translation, scaling, and deformation invariance, which can accurately extract the features of target objects in graphic design elements. Next, the network structure, loss function, and optimization methods of MaskR-CNN are analyzed, and the MaskR-CNN convolutional neural network is implemented based on the TensorFlow framework, and the network is applied to the extraction of buildings from graphic design elements. Then the borrowed landscape technique in graphic design is used to enrich the combination form of elements of architectural design through the mirror effect of water landscape. The selected IALD dataset is composed of 180 data images and 180 corresponding labeled images, and the effect of high-resolution building extraction of graphic design elements based on the MaskR-CNN model is verified by simulation experiments. The simulation results show that Mask R-CNN improves the accuracy of building extraction from graphic design elements by 5.11%, mAP also improves by about 10.09%, and the inference time is less than 1 second; Mask R-CNN has good robustness and accuracy for building extraction from graphic design elements. This study has important research significance for the depth and development of the commercial architectural design.

Keywords

• maskr-cnn
• tensorflow framework
• loss function
• commercial architectural design
• accuracy
• robustness.
• 65d17