Journal of Fiber Bioengineering and Informatics
 
  Online Journals
   » All Issues
   » Most Read Papers
   » Most Downloaded Papers
   » RSS   |   Email Alert
  Paper Search
Search DOI ADV Search
  Google Scholar Search
  Useful Links
» The 15th Textile Biogenineering and Informatics Symposium
» Textile Bioengineering and Informatic Society
 
JFBI -> 2015, Volume 8 Issue 4, 31 December 2015  
Select | Export to EndNote
TENCEL with a Microbial Barrier for Medical Bras
Rogina-Car Beti, Bogovi\'c Slavica, Katovi\'c Drago
JFBI. 2015, 8 (4): 635-643.   DOI: 10.3993/jfbim00153
Full Text: PDF (2145 KB)  ( 203 )
Show Abstract ( 66 )
The goal of the research was to determine the properties of the microbial barrier TENCEL$^{\circledR}$ knitted fabrics intended for medical bras. The samples were tested according to a new method developed in the earlier research by the same authors. The most resistant forms of microorganisms of a pathogenic bacterial endospore of the {\it Bacilllus} genus were used to investigate microbial barrier permeability. Based on the samples tested and their characteristics, medical bra construction was developed with the aim of reducing irritation for the body part that underwent surgery. The data on the forms and measures were obtained using a 3D body scanner.
Study on Sound Insulation Properties of Different Coated Woven Fabrics
Hafeezullah Memon, Ningning Wang, Chengyan Zhu
JFBI. 2015, 8 (4): 645-656.   DOI: 10.3993/jfbim00170
Full Text: PDF (18829 KB)  ( 187 )
Show Abstract ( 45 )
The aim of this paper is to find the relation between material parameters and insertion loss of different fabrics using statistical analysis. This research primarily deals with the sound absorption analysis of different uncoated and coated woven textiles fabrics used for curtains as household textiles. The analysis of surface morphology was done by scanning electron microscopy to determine the significance of surface structure onto the sound insulation property. The acoustic properties were measured by reverberation method. The maximum sound insertion loss, minimum sound insertion loss, over all sound insertion loss and percentage improvement in sound insertion loss has been discussed and suggested the woven textiles to be better sound absorber at higher frequencies. Moreover, the effect structural parameters on average sound insulation index were analyzed using SPSS software. The results revealed that warp density, linear density of warp yarn, thickness are influential parameters for the sound insulation property of uncoated fabric whereas the areal density, linear density of warp yarn and thickness influence the sound insulation property coated fabrics.
3D Garment Segmentation Based on Semi-supervised Learning Method
Mian Huang, Li Liu, Ruomei Wang, Xiaodong Fu, Lijun Liu
JFBI. 2015, 8 (4): 657-665.   DOI: 10.3993/jfbim00174
Full Text: PDF (1844 KB)  ( 134 )
Show Abstract ( 55 )
In this paper, we propose a semi-supervised learning method to simultaneous segmentation and labeling of parts in 3D garments. The key idea in this work is to analyze 3D garments using semi-supervised learning method which can label parts in various 3D garments. We first develop an objective function based on Conditional Random Field (CRF) model to learn the prior knowledge of garment components from a set of training examples. Then, we exploit an effective training method that utilizes Joint- Boost classifiers based on the co-analysis for garments. And we modify the JointBoost to automatically cluster the segmented components without requiring manual parameter tuning. The purpose of our method is to relieve the manual segmentation and labeling of components in 3D garment collections. Finally, the experimental results show the performance of our proposed method is effective.
Non-contact Human Body Measuring Technology Based on Camera Calibration Technique
Yue Wang, Shoushan Jiang
JFBI. 2015, 8 (4): 667-677.   DOI: 10.3993/jfbim00161
Full Text: PDF (289 KB)  ( 103 )
Show Abstract ( 45 )
The basic theory of camera calibration is firstly introduced in this paper. The model of camera distortion is put forward. And discussed the parameters and the calibration process of the mathematical model of 3D human body reconstruction. In the process of camera calibration, an improved algorithm based on the two steps is proposed. This method has low requirements on experimental. This method has low requirement to experiment, and only with coplanar points to calibrate. By the process of fractional step calibration, the nonlinear equation is linear, which is beneficial to improve the calibration accuracy.
Design of Functional Bellyband for Pregnant Women
Tian Wei, Qian Zhao, Xing Zhang
JFBI. 2015, 8 (4): 679-686.   DOI: 10.3993/jfbim00165
Full Text: PDF (1257 KB)  ( 103 )
Show Abstract ( 23 )
This study has investigated the physical characteristics and needs of pregnant women to introduce a scientific and practical design of bellyband to satisfy pregnant women demand. Structure and material of supporting bellyband have been introduced in the study and its functional rationality also has been verified by many testers. Finally, the experiment result has been proved that the design of supporting bellyband has helped pregnant women to ease the burden of their waist efficiently and effectively after analysed the result very carefully.
The Algorithm of ICA Based on PCA for Fabric Defect Detection
Junfeng Jing, Juan Zhao, Pengfei Li, Hongwei Zhang, Lei Zhang
JFBI. 2015, 8 (4): 687-696.   DOI: 10.3993/jfbim00166
Full Text: PDF (2387 KB)  ( 139 )
Show Abstract ( 34 )
The Independent Component Analysis (ICA) algorithm based on Principal Component Analysis (PCA) is described in this paper to achieve the raw textile defect detection. In the first step, the observed matrix $X$ is constructed from a large number of defect-free sub-images and PCA is operated to achieve dimension reduction. In the second step, the transformation matrix $W$ and independent basis subspace $s$ are obtained from defect-free sub-images through ICA. In the final step, feature extraction is achieved from the overlapping sub-windows of a test image. Then a sub-window is classified as defective or non-defective according to Euclidean distance. The results have been analyzed in detail and illustrated this approach has better performance in raw textile.
PSO-based Medical Image Processing for Kienb\"ock Biomechanical Analysis
Xiaoyan Jia, Jindong Zhang, Bin Liu, Yuehai Pan, Zhigang Liu,Kai Liu
JFBI. 2015, 8 (4): 697-704.   DOI: 10.3993/jfbim00167
Full Text: PDF (1799 KB)  ( 88 )
Show Abstract ( 18 )
Through the lunate bone biomechanical analysis can be used for kienb\"ock medical diagnosis and treatment. The pressure sensitive film can reflect intuitively the stress of lunate bone's each point. This paper obtains stress analysis of lunate bone based on PSO (Particle Swarm Optimization) algorithm's image analysis and processing of pressure sensitive film. The paper uses the grayscale function to change a target image into the grayscale image, and uses the PSO algorithm for function optimization to segment image with the original image. Then we obtain remaining achieving gray value, and calculate the pressure. Through the analysis of the experimental data, we obtain the maximum value, minimum value and average value of the pressure. The analysis of processing results showed that the PSO algorithm could segment the image accurately and the remaining larger pixel gray values concentrated in the three fossa of lunate bone. The results verify the accuracy and efficiency of the method.
Two-step Registration in 3D Human Body Scanning Based on Multiple RGB-D Sensors
Pengpeng Hu, Yueqi Zhong, Ge Wu, Duan Li
JFBI. 2015, 8 (4): 705-712.   DOI: 10.3993/jfbim00171
Full Text: PDF (10317 KB)  ( 149 )
Show Abstract ( 40 )
In this paper, we propose a universal registration method for the body scanner consists of multiple fixed sensors. Firstly, a new double-faced checkerboard is designed to apply calibration method into the initial estimations of the relative poses of point clouds. Secondly, ICP (Iterative Closet Point) algorithm is utilized for further registration. Since ICP algorithm may fail in situations of outliers, ambiguity or missing data, we make full use of the geometry feature of creased papers to solve these problems. A new body scanning system with fast capture speed is also proposed to validate our method. The experiment results demonstrate our approach is robust and fast.
Research of Biometric Key Generation Based on Fingerprint Bit-strings
Chengyang Xie, Jiayong Liu, Xu Yao, Dianhua Tang
JFBI. 2015, 8 (4): 713-724.   DOI: 10.3993/jfbim00172
Full Text: PDF (347 KB)  ( 176 )
Show Abstract ( 79 )
Biometric key technology is the organic combination of biometric encryption technology and traditional cryptography. Biometric key can directly encrypt data or encrypt key, with the character of portable use and not easily being stolen, forgotten and broken. This article provides an algorithm for generating key based on the fingerprint feature bit-strings, extracting fingerprint feature information with bit-strings form as first step, generating key by the combination of this feature information and BCH error correcting code secondly. Experiments show that the algorithm can generate stable key of encryption on the premise of protecting the user's fingerprint information. It can further improve the security strength and reach two-factors protection if the biometric key is stored in the smart card, which has certain practical value.
A Survey of Major Techniques of Clothing in Vision
Dongyan Huang, Li Liu, Xiaodong Fu, Lijun Liu, Qingsong Huang
JFBI. 2015, 8 (4): 725-732.   DOI: 10.3993/jfbim00175
Full Text: PDF (1401 KB)  ( 196 )
Show Abstract ( 32 )
Clothing in vision plays an important role in many applications of digital clothing, virtual fitting, fashion design and manufacturing. The research of clothing in vision is full of technical challenges, such as background detection and features extraction. In this paper, we introduce the latest remarkable works of clothing in vision area, including clothing segmentation, clothing recognition and clothing retrieval. There are many remarkable advances on the basis of the predecessors' achievements in the three fields. Firstly, we provide an overview of the techniques for clothing segmentation and clothing recognition. Then, we introduce and analyze the representative works on clothing retrieval. Finally, we forecast broader application prospect and future research work of clothing in vision.
Daylight-triggered Directional Water Transport Fabric Prepared with TiO$_2$ Sol-gel Method
Huiqin Li, Xibo Hao, Jixian Gong, Qiujin Li, Jianfei Zhang,Zhenxiang Ding
JFBI. 2015, 8 (4): 733-740.   DOI: 10.3993/jfbim00182
Full Text: PDF (4308 KB)  ( 121 )
Show Abstract ( 26 )
To build directional water transport fabric, cotton knitting fabric was finished with TiO$_2$ sol by two methods: padding and spray. After finishing, the fabrics were irradiated in a self-made UV light box, during which the water contact angle and directional water transport ability were tested. It was found that the fabrics's irradiated side turned from hydrophobic to superhydrophilic within 2 hours, and after 2 hours's irradiation they would recover to hydrophobic within 2 hours. The fabric's directional water transport ability increased with the extend of irradiation time. The sprayed fabric responded more quickly than the padded fabric and took less time to recover than the padded fabric. But the padded fabric had higher maximum one-way water transport capacity.
Noninvasive Ambulatory Hemodynamic Monitoring Based on Electrocardiogram and Impedance Cardiography
Xinyu Hu, Xianxiang Chen, Ren Ren
JFBI. 2015, 8 (4): 741-749.   DOI: 10.3993/jfbim00162
Full Text: PDF (888 KB)  ( 113 )
Show Abstract ( 26 )
Two different noninvasive ambulatory hemodynamic monitoring devices (belt-type and chest-type) based on Electrocardiogram (ECG) and Impedance Cardiography (ICG) has been designed, fabricated and tested. Hardware designs of the two ambulatory hemodynamic monitoring devices based on Tetrapolar configuration and placement of the electrodes were introduced. Hemodynamic parameters such as Stroke Volume (SV), Cardiac Output (CO) and Cardiac Index (CI) can be estimated according to Kubicek Formula by extracting characteristic points and characteristic periods in the ICG Signal. CI is CO divided by body surface area. CI is comparable among different people because it is not influenced by the body height and weight. The body's physiological responses to postural change are primarily a reaction to the change of gravity, because change of gravity can cause changes of blood flow distribution in organs and tissues. Different body postures (upright or supine) can result in reducing or rising of CO. The detection accuracy has also been validated with a commercial ICG detection instrument from Mindray company, and the correlation coefficient is 0.83.
Research on Non-rigid Structure from Motion: A Literature Review
Yaming Wang, Xiaomeng Yan, Mingfeng Jiang, Junbao Zheng
JFBI. 2015, 8 (4): 751-760.   DOI: 10.3993/jfbim00164
Full Text: PDF (96 KB)  ( 200 )
Show Abstract ( 58 )
Non-rigid Structure from Motion (NRSfM) is a classical computer vision problem. And the main methods used to solve it are in general based on shape models or trajectory models. This paper will provide an overview over kinds of solutions proposed in these researches. It not only gives out the theoretical insights proposed by researchers in recent years, but also discusses them with their pros and cons. At the same time, the progress of the research about this topic is described in detail and its long-term trend is introduced at the end. This paper is very easy to understand, which mainly introduces two practical, everyday models for the NRSfM problem, namely trajectories based model and shape based model. Both of them are based on matrix factorization technology. Inevitably, some relevant optimization methods are mentioned to solve the projection matrix and corresponding coefficients effectively.
A Novel Algorithm for the Real-time Analysis of Uterine Contraction Status
Zhaoxia Chen, Yaosheng Lu, Duoying Zhang, Xiaodong Li, Renhuan Yang
JFBI. 2015, 8 (4): 761-770.   DOI: 10.3993/jfbim00176
Full Text: PDF (566 KB)  ( 796 )
Show Abstract ( 64 )
Against the problems of existing uterine contraction identification algorithms, mainly in the\linebreak inapplicability to real-time identification of the characteristic points of uterine contraction wave, a novel method based on a series of criteria for real-time analysis is proposed in this paper. After confirming the beginning, end and peak of the analyzed segment, a series of criterion are used to identify the status of current uterine contraction point. Meanwhile, the status of current uterine contraction point is corrected by a buffer mechanism to ensure accuracy. The experiments show that the conformity between the real-time analysis results and two experts' analysis results are high, and the kappa coefficients are as high as 0.874 and 0.872. Moreover, the time required for the analysis of a uterine contraction point is only $0.0032\pm 0.0002$ (mean $\pm$ SD) seconds, which is far less than the acquisition and output time of a uterine contraction point by pressure probe. Therefore, the proposed method can meet the requirements of real-time analysis in both accuracy and efficiency.
Gender Comparison of Image Perception and Preferences for Spring $\bullet$ Summer Shirt Yarn-dyed Fabrics
Xiaoxi Zhou, Hui'e Liang, Zhiya Dong
JFBI. 2015, 8 (4): 771-782.   DOI: 10.3993/jfbim00181
Full Text: PDF (117 KB)  ( 188 )
Show Abstract ( 34 )
The research proposes to extract data of male and female consumers' image perception and preferences in yarn-dyed fabrics for spring$\cdot$ and summer shirts. The Semantic Differential (SD) evaluation on representative fabric samples by two groups of subjects was accomplished following the standardized sensory evaluation procedures. The differences in terms of image perception in yarn-dyed fabrics between male and female subjects was identified through Levene homogeneity variance test and independent samples T-test, and the evaluation factors of subjects' image perception was classified into 6 factors through factor analysis. The relationships between image word-pairs and subjects' preferences were validated with regression analysis. Experiment results show an evident difference in terms of image perceptions, preferences and the factors affecting preferences of the yarn-dyed fabrics between male and female subjects. The quantitative data could consequently provide guidance to help designing and producing differentiated yarn-dyed fabrics for designated sex consumers.
Adjacent Local Binary Patterns Based on Color Space Fusion for Color Image Classification
Shengsheng Wang, Dezhi Huang, Haiyang Jia, Dong Liu, Bolou Bolou Dickson
JFBI. 2015, 8 (4): 783-790.   DOI: 10.3993/jfbim00188
Full Text: PDF (2380 KB)  ( 131 )
Show Abstract ( 25 )
In this paper, we propose an improved image feature descriptor based on Local Binary Pattern, which is called Adjacent Local Binary Patterns based on Color Space Fusion (ALBPCSF). The proposed method fuses color feature and spatial relations. ALBPCSF uses the channel values of RGB and HSV color spaces to calculate the color feature. Then the proposed method considers the spatial relations which will be combined with the color feature. Finally, an image classification system framework based on ALBPCSF is given. In order to validate the performance, our method is compared with previous methods on Corel 1000 and MIT Vision Texture datasets. The results show that our approach is superior than other methods in color image classification.
Part Recognition Method Based on Visual Selective Attention Mechanism and Deep Learning
Dan Zhou, Nanfeng Xiao
JFBI. 2015, 8 (4): 791-800.   DOI: 10.3993/jfbim00196
Full Text: PDF (1279 KB)  ( 135 )
Show Abstract ( 26 )
In order to enable the industrial robots to recognize the specific targets quickly and accurately on the assembly line, an object recognition method driven by visual selective attention mechanism is proposed. With mass training data and a machine learning model containing a number of hidden layers, deep learning can learn more useful features, and thus ultimately improve the classification or the prediction accuracy. The main idea of this method is as follows: for all part images, the visual attention mechanism is used to choose salient regions in an image, achieving the goal of target segmentation. Then an image recognition method based on deep learning is applied to recognize the chosen salient regions. Experimental results show the effectiveness of the proposed method and the cognitive rationality.
Table of Contents - JFBI Vol 8 No 4
JFBI. 2015, 8 (4): 1000-1000.
Full Text: PDF (47 KB)  ( 114 )
Show Abstract ( 37 )
JFBI Vol 8 No 4 Cover
JFBI. 2015, 8 (4): 1001-1001.
Full Text: PDF (288 KB)  ( 85 )
Show Abstract ( 19 )

ISSN 1940-8676
JFBI is Ei Indexed Journal
Editor-in-Chief: Prof. Yi Li
  User Online  
  Announcement  
» September 5-8, 2022-The 15th Textile Bioengineering and Informatics Symposium (Blended Conference)
» July 6-9-TBIS 2021-The 14th Textile Bioengineering and Informatics Symposium (Blended Conference)
» July 7-10-TBIS 2020-The 13th Textile Bioengineering and Informatics Symposium (TBIS 2020 Webinar)
» 5th International Conference on Biomedical Polymers & Polymeric Biomaterials (ICBPPB 2021)
more>>     
Copyright All Rights Reserved © Journal of Fiber Bioengineering and Informatics
Supported by Beijing Magtech Co.ltd , E-mail: support@magtech.com.cn