Clothing Design Style Recommendation Using Optimized Semantic-Preserved Generative Adversarial Network

Recommendations for clothing design styles provide a tailored and efficient buying experience, decreasing consumers' decision fatigue and boosting interest. There are a number of obstacles to implementing clothing design style recommendations, including the requirement for diverse and accurate data to train efficient algorithms, the possibility of biases in recommendation systems, the complexity of comprehending subtle customer preferences, and the ever-changing nature of fashion trends. To overcome this complication, Clothing Design Style Recommendation Using Optimized Semantic-Preserved Generative Adversarial Network (ICMA-SPGAN-SFOA-CD) are proposed. Initially, the images collected from the clothing dataset are given as input. Afterward, the data are fed to pre-processing. In pre-processing, Reverse Image Filter (RIF) is used for redundant of data and noise removal. The pre-processing output is fed to Pyramidal Convolution Shuffle Attention Neural Network (PCSANN) for clothing design style recommendation. The recommended clothing design style was given for classification using Semantic-Preserved Generative Adversarial Network (SPGAN) optimized with Sheep Flock Optimization Algorithm (SFOA)for classifying clothing design style as Basic clothing, Looseness Season for clothing, Collar type, Colour and Advanced clothing . MATLAB is used to implement the proposed ICMA-SPGAN-SFOA-CD method. The performance of the proposed ICMA-SPGAN-SFOA-CD approach attains 25%, 21.5%, and 22.5% high precision,25.3%, 27.5%, and 21.8% high recall and 27.6%, 24.8%, and 23.2% high F1-Scorecompared with existing methods such as RCNN Framework Using L-Softmax Loss (CAR-RCNN-LSL)  ,Clothing Attribute Recognition Based on Clothing fashion style recognition with design issue graph (CFSR-DCNN-DIG), Personalized Smart Clothing Design Based on Multimodal Visual Data Detection (PSCD-DNN-MVDD) models respectively.