Search

The purpose of this study is to propose a new method to achieve pattern generation from garment sample without damage. The non-contact three-dimensional (3D) scanner was employed to get the point cloud data of garment samples. The Bowyer-Watson algorithm was used to implement Delaunay triangulation for surface reconstruction. The finite element (FE) approach was employed to achieve the consideration of the fabric properties in surface development. The proposed method was demonstrated to effectively realize the pattern generation of 3D sample clothes with fabric properties without damaging the garment samples, and to be suitable for different clothing styles and fabrics. Compared with traditional methods, the proposed method has higher accuracy (2.21% higher on average) and better stability.

The automatic recognition of garment flat information has been widely researched through computer vision. However, the unapparent visual feature and low recognition accuracy pose serious challenges to the application. Herein, inspired by multi-object instance segmentation, the method of mask region convolutional neural network (Mask R-CNN) for garment flat multi-component is proposed in this paper. The steps include feature enhancement, attribute annotation, feature extraction, and bounding box regression and recognition. First, the Laplacian was employed to enhance the image feature, and the Polygon annotated component attributes to reduce the interaction interference. Next, the ResNet was applied to realize identity mapping to characterize redundant information of components. Finally, the feature map was entered into two branches to achieve bounding box regression and recognition. The results demonstrated that the proposed method could realize multi-component recognition effectively. Compared with the unenhanced feature, the mAP increased by 2.27%, reaching 97.87%, and the average F1 was 0.958. Compared to VGGNet and MobileNet, the ResNet backbone used for Mask R-CNN could improve the mAP by 11.55%. Mask R-CNN was more robust than the state-of-the-art methods and more suitable for garment flat multi-component recognition.

This study is to explore the effect of fabric parameters on fragrance retention, which was based on the olfactorymeasurement technology with the quantitative headspace method. The fragrance retention of different fabrics wasquantitatively evaluated by Electronic Nose (e-nose) at different time after volatilization. Quick-drying Tester was usedto test the fabric drying rate, which was related to fragrance retention. Besides, wicking property and porosity of fabrics,two factors of moisture transmission, were tested and calculated for analysis too. It was found that fabrics with the highercotton content had the better fragrance retention due to their hydrophilicity and water retention property of fibers. Plainfabric had the shorter fragrance retention than twill fabric since its lower porosity and the higher capillary pressure ledto the faster fragrance dissipation. As the fabric density increased or the yarn count decreased, the fragrance retentionincreased. Since their wicking properties decreased, the process of perfume diffusion would slow down. The data andmethods presented in this paper provide a basis for optimizing the parameters of fragrant fabric.

The goal of the study is to develop a novel method to manufacture the functional bras. The high precision three-dimensional (3D) scanner was employed to get the point cloud data. A fixed mount was invented to keep the bra cup stable and decrease measuring error. A bottom holder was prepared by the 3D printer to place the bra cup during the injection process. Furthermore, the injection points coordinate values and the injection volumes can be determined based on the 3D image of the bra cup and the thickness of those positions. At last, the three-axis automatic robot which was coupled with a precision liquid dispenser is used to inject the microcapsules solution into the bra cup for the preparation of functional intimate apparel. The proposed method was verified to be feasible and effective through a practical example.