Predicting human dimensions in body images for automatic generation of female pants patterns

Gu, Bingfei; Li, Xinhua; Yan, Yanhong; Jian-jun, SU

doi:10.1177/0040517518821914

Cited by 9 publications

(8 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, the measurement points need to be selected manually, lack of automation. References [25] and [26] are dual-view anthropometric systems. They capture the front and side views of the subject, calculate the width and thickness of the measured girth based on the scale, and obtain the girth data by linear regression.…”

Section: Introductionmentioning

confidence: 99%

Girth Measurement Based on Multi-View Stereo Images for Garment Design

et al. 2020

View full text Add to dashboard Cite

In this paper, we propose a novel girth measurement system based on multi-view stereo images for garment design. Our system is set in a fixed location to capture three pairs of stereo images for the subject by six calibrated and synchronously triggered cameras. An important feature of this system is the use of an optimized semantic segmentation network that can efficiently segment the girth region in the captured six-view stereo images. Another important feature of this system is the use of color subspace classification and coordinate clustering that can effectively constrain the stereo matching within the scope of markers. Then, the system performs only on the corresponding clusters to extract stereo matching point pairs of markers correctly. The space coordinates of 3D point corresponding to each stereo matching point pair are calculated in each coordinate system of stereo cameras. The unified coordinates of these 3D markers are transformed from three different coordinate systems into one unified coordinate system. Girth is measured by curve fitting of these markers and calculating the length of the fitting curve. Our proposed system performs passive and intelligent girth measurement in garment design, and overcomes the problem of too many invalid stereo matching point pairs in girth measurement. Experimental results demonstrate its accuracy. Our system has a maximum bust measurement error of 1.28cm for woman and 1.31cm for man and a maximum waist measurement error of 1.18cm for woman and 0.99cm for man, which are within the error limit regulated by China national standards GB/

show abstract

Section: Introductionmentioning

confidence: 99%

Girth Measurement Based on Multi-View Stereo Images for Garment Design

et al. 2020

View full text Add to dashboard Cite

show abstract

“…By analyzing the front and side photos of the human body, the feature points of the feature parts were determined, so as to obtain the sizes of different parts of the human body. 30,31 The typical height range for the limits was analyzed to look for a landmark and then the shape characteristics were used to determine the actual position. Take the abdomen landmark as an example.…”

Section: Body-type Identification Based On Body Silhouettesmentioning

confidence: 99%

Classification analysis of young female students’ waist–abdomen–hip based on body photos

Cai

2021

Textile Research Journal

Self Cite

View full text Add to dashboard Cite

To improve body-type classification research and personalized clothing, this study adopted a research method of “three-dimensional (3D) scanning + photos” for the body-shape classification of young females’ waist–abdomen–hip. A total of 178 female college students were recruited for manual, photo and 3D body measurement to get the main body information. Based on the data acquired from 3D scanning, the corresponding heights, angles and other parameters of the waist, abdomen and hip were selected and used to analyze the human body in two respects of shape and height. Then the body-shape indexes and the height indexes were respectively analyzed, and 16 shape characteristic indicators and four height characteristic parameters affecting the waist, abdomen and hip were extracted. Three types in shape and two types in height were obtained, and the main classification rules of the waist–abdomen–hip shape were also concluded to identify the body type based on the body measurements extracted from body photos, which realized the automatic body-type identification based on body photos. It was of great practical significance to provide a basis for personalized customization of fast clothing and the subdivision of the human body shape, which could meet the individual customer’s requirements.

show abstract

“…Therefore, conventional clothing patterns design method does not meet the requirements of a large amount of manufacturers for the general public (Liu et al , 2019). With the development of deep learning, unrestricted intelligent image generation technology has achieved rapid development and has been applied to various fields of image processing and image design (Gu et al , 2019). The computer-aided automatic clothing patterns generation can not only avoid the high prices of single pattern style from specific designers, but also flexibly design different clothing patterns according to the requirements of the actual clothing design population.…”

Section: Introductionmentioning

confidence: 99%

Research on clothing patterns generation based on multi-scales self-attention improved generative adversarial network

Luo

2021

IJICC

View full text Add to dashboard Cite

PurposeClothing patterns play a dominant role in costume design and have become an important link in the perception of costume art. Conventional clothing patterns design relies on experienced designers. Although the quality of clothing patterns is very high on conventional design, the input time and output amount ratio is relative low for conventional design. In order to break through the bottleneck of conventional clothing patterns design, this paper proposes a novel way based on generative adversarial network (GAN) model for automatic clothing patterns generation, which not only reduces the dependence of experienced designer, but also improve the input-output ratio.Design/methodology/approachIn view of the fact that clothing patterns have high requirements for global artistic perception and local texture details, this paper improves the conventional GAN model from two aspects: a multi-scales discriminators strategy is introduced to deal with the local texture details; and the self-attention mechanism is introduced to improve the global artistic perception. Therefore, the improved GAN called multi-scales self-attention improved generative adversarial network (MS-SA-GAN) model, which is used for high resolution clothing patterns generation.FindingsTo verify the feasibility and effectiveness of the proposed MS-SA-GAN model, a crawler is designed to acquire standard clothing patterns dataset from Baidu pictures, and a comparative experiment is conducted on our designed clothing patterns dataset. In experiments, we have adjusted different parameters of the proposed MS-SA-GAN model, and compared the global artistic perception and local texture details of the generated clothing patterns.Originality/valueExperimental results have shown that the clothing patterns generated by the proposed MS-SA-GAN model are superior to the conventional algorithms in some local texture detail indexes. In addition, a group of clothing design professionals is invited to evaluate the global artistic perception through a valence-arousal scale. The scale results have shown that the proposed MS-SA-GAN model achieves a better global art perception.

show abstract

Predicting human dimensions in body images for automatic generation of female pants patterns

Cited by 9 publications

References 23 publications

Girth Measurement Based on Multi-View Stereo Images for Garment Design

Girth Measurement Based on Multi-View Stereo Images for Garment Design

Classification analysis of young female students’ waist–abdomen–hip based on body photos

Research on clothing patterns generation based on multi-scales self-attention improved generative adversarial network

Contact Info

Product

Resources

About