Computer-Aided Industrial Product Design based on Image Enhancement Algorithm and Convolutional Neural Network

被引：0

作者：

Xiao K. ^{[1
]}

Ni T. ^{[2
]}

机构：

[1] School of Communication, Guangxi Vocational Normal University, Guangxi, Nanning

[2] School of Literature, Journalism&Communication, Xihua University, Sichuan, Chengdu

来源：

Computer-Aided Design and Applications | 2024年 / 21卷 / S3期

关键词：

Artificial Intelligence; Computer Aided Industrial Design; Computer Vision; Convolutional Neural Network;

D O I：

10.14733/cadaps.2024.S3.92-106

中图分类号：

学科分类号：

摘要：

In order to effectively realize the integration of conceptual design and detailed design, AI should be comprehensively used in product design to process the geometric feature information of products and realize the comprehensive design and high-quality production of new products. This article discusses the application of digital image processing technology based on computer vision and artificial intelligence (AI) in computer aided industrial design (CAID), and proposes an image enhancement algorithm for industrial design products based on convolutional neural network (CNN). The algorithm enhances the stability and anti-over-fitting performance of the network by compressing the model of CNN with image enhancement processing, and optimizes the design process and work efficiency of CAID. In the case of expanding network scale, this article adopts parallel verification method, which is more effective than single user verification method. The simulation shows that the model constructed in this article can quickly train to achieve the target accuracy of CAID image processing, and can support the feature extraction and modeling stage of CAID, which can not only optimize the design content, but also improve the design efficiency. © 2024 CAD Solutions.

引用

页码：92 / 106

页数：14

共 15 条

[1] Cao W., Applying image registration algorithm combined with CNN model to video image stitching, The Journal of Supercomputing, 77, 12, pp. 13879-13896, (2021)
[2] Dhaya R., Light weight CNN based robust image watermarking scheme for security, Journal of information technology and digital world, 3, 2, pp. 118-132, (2021)
[3] Dhiman G., Juneja S., Viriyasitavat W., Mohafez H., Hadizadeh M., Islam M.-A., Gulati K., A novel machine-learning-based hybrid CNN model for tumor identification in medical image processing, Sustainability, 14, 3, (2022)
[4] Gonthina M., Chamata R., Duppalapudi J., Lute V., Deep CNN-based concrete cracks identification and quantification using image processing techniques, Asian Journal of Civil Engineering, 24, 3, pp. 727-740, (2023)
[5] Hou Y., Li Q., Zhang C., Lu G., Ye Z., Chen Y., Cao D., The state-of-the-art review on applications of intrusive sensing, image processing techniques, and machine learning methods in pavement monitoring and analysis, Engineering, 7, 6, pp. 845-856, (2021)
[6] Hu L., Qin M., Zhang F., Du Z., Liu R., RSCNN: a CNN-based method to enhance low-light remote-sensing images, Remote Sensing, 13, 1, (2020)
[7] Hu Z., Fang W., Gou T., Wu W., Hu J., Zhou S., Mu Y., A novel method based on a Mask R-CNN model for processing dPCR images, Analytical Methods, 11, 27, pp. 3410-3418, (2019)
[8] Ilesanmi A.-E., Ilesanmi T.-O., Methods for image denoising using convolutional neural network: a review, Complex & Intelligent Systems, 7, 5, pp. 2179-2198, (2021)
[9] Jia C., Wang S., Zhang X., Wang S., Liu J., Pu S., Ma S., Content-aware convolutional neural network for in-loop filtering in high efficiency video coding, IEEE Transactions on Image Processing, 28, 7, pp. 3343-3356, (2019)
[10] Liu M., Zhou Z., Shang P., Xu D., Fuzzified image enhancement for deep learning in iris recognition, IEEE Transactions on Fuzzy Systems, 28, 1, pp. 92-99, (2019)

← 1 2 →