Visual design element recognition of garment based on multi-view image fusion

Recently, three-dimensional or visual design, dressing, and simulation programs have become prominent in the garment industry. Image processing technology is increasingly utilized in the online customization process to adapt to the growth and revolution of garment customization. The emergence of online sites for browsing and purchasing personalized garments has given consumers a new platform to choose their outfits. The major challenge is extracting garment data, general clothing portrayals, and automatic dimensional extractions. Hence, this article proposes the Image Processing Technology-assisted Garment Visual Design Element Recognition (IMT-GVDER) model for tailoring clothing throughout the early phases of unique design and product development. The series of cloth pictures can be given as input to the recognition model from datasets. This clothing style recognition aids in predicting clothes' features and patterns, which aids in classifying them using efficient feature extraction and classification models such as Convolutional Neural Network (CNN). It helps to automatically recognize cloth images and categorize clothes styles depending on style components and their salient visual feature. The image texture characteristic variables can be utilized to classify the defects. The experimental outcome demonstrates that the suggested IMT-GVDER model enhances the prediction accuracy ratio of 98.7%, the matching rate by 97.6%, the performance ratio of 96.7%, and the F1-score ratio of 94.56% and reduces the error rate by 0.9% compared to other existing methods in visual clothing design.