Objective evaluation of multidirectional fabric wrinkling using image analysis

In the textile industry, the wrinkled fabrics are regularly evaluated subjectively in reference to a set of visual standards. However, due to the disadvantages of visual evaluation, which are unreliable and time-inefficient, several objective methods were recently developed. In this paper, a new objective evaluation of multidirectional realistic fabric's wrinkling generated by the French method of “cylindre creux” was proposed using the image processing. Four characteristics of wrinkled fabrics were evaluated to estimate wrinkle grade with a statistical model. The study reveals a good correlation between the objective wrinkling evaluation (using image analysis) and the subjective evaluation (using the visual standards).     

应用小波分析的服装关节部位抗皱性评价

为研究服装在实际着装过程中起皱的客观评价方法,以15块机织试样为研究对象,将其制作成试穿裤,进行实际着装起皱,然后对折皱图像进行主观评价,利用小波分析技术提取特征值,最后将小波特征值与主观评价及折皱回复角度进行对比研究。结果表明：小波分析的细节系数标准差与专家主观评价结果具有良好的一致性,可提取小波二层分解时水平方向的细节系数标准差作为取代主观评价的客观指标,以节约时间和成本;织物经向抗皱性对着装时服装抗折皱变形的贡献最大,斜向其次,纬向最小;采用折皱回复角表征织物抗皱能力时,建议增加斜向折皱回复角的测试,同时赋予经纬向不同的权重（经向大于纬向）,以提高测试结果与实际着装时的吻合度。     

声学分析测定织物手感

与织物的视觉外观相同,织物的手感也是消费者购买纺织品的评价指标。影响织物手感的因素很多：纤维、纱线及其表面结构和后处理。测定纺织品特定手感性能的目的是用客观数值的方式表征其手感特点。介绍了一个可以定量描述织物手感特点和柔软性的测试系统,该测试系统是在声学分析的基础上进行测试的。     

基于图像处理的织物缝纫平整度客观评价

织物的缝纫平整度是决定服装外观的重要因素,但肉眼评价存在一定的主观性,且常用的AATCC Test Method 88B-2006标准样照仅分5个等级,限制了评价的精度。利用图像处理技术探讨了客观评价织物缝纫平整度的方法。试验对5种常见织物采用不同的抽褶量进行车缝,以产生不同的平整度外观,进行平整度主观评价后,再借助MATLAB图像处理技术,提取缝纫图像的多个统计参数与小波特征,对客观参数与主观评价结果进行相关分析,得到与主观评价结果相关性较好的客观参数。研究结果表明:小波分解5层时的水平细节系数标准差,即SH5与主观评价具有良好的一致性,可以作为取代主观评价的客观指标。     

基于卷积神经网络的织物缝纫平整度客观评价

针对大多数评价织物缝纫平整度等级方法对实验条件均有较高的要求,且织物种类及环境等因素对实验结果均有较大影响的现状,提出利用卷积神经网络分析织物缝纫平整度等级的方法,以提高等级分类的准确率和效率。设计了一个基于残差卷积神经网络的织物缝纫平整度客观评价模型,该模型以1000个普通织物的缝纫图像作为训练样本输入,得到缝纫平整度的分类结果,所选织物包含10种常见服装面料品类(塔夫绸、塔斯隆、雪纺、顺纡绉、尼丝纺、麂皮绒、天丝斜纹、真丝缎面、平布、交织绸)。研究结果表明:经200个测试集样本的验证,该模型的评价准确率达96%,与智能化评价以及建立预测模型方法相比,利用卷积神经网络分析织物缝纫平整度等级的方法,具有较好的准确率,且具备获取样本图像流程简单、效率高的优势。     

基于数字图像相关法的针织物泊松比测定

为解决针织物因其各向异性,传统泊松比测定方法不适用的问题,结合数字图像相关法对针织物进行单轴拉伸测试,提出了一种以纬平针织物试样整体作为研究对象且在其较大形变下测试其泊松比的方法。实验选取3种纬平针织物,首先录制试样单轴拉伸的整个过程,导出每1帧图像,将图像转化为灰度图后,在MatLab软件中用数字图像相关法进行位移分析,用SPSS软件对载荷方向拉伸的计算值与实际拉伸值进行t检验,验证了可行性,计算所得泊松比在正常取值范围内,避免了织物颈缩问题,且每秒可提取30帧图片进行位移分析,提高了精度,为研究针织物的泊松比提供新思路。     

A new method to evaluate lower eyelid sag using three-dimensional image analysis

Lower eyelid sags as well as wrinkles represent age-related morphological changes of the skin surface. However, a quantitative method to evaluate lower eyelid sagging has not been previously established. We designed a new quantitative evaluation method that uses non-invasive skin scanning, which is based on the difference between the superficial dimension of the sagging surface of the lower eyelid and the dimension of its projection area. In 97 females, 2-D and the 3-D images were taken. By 3-D image analysis, the difference between the superficial dimension of the sagging surface of the lower eyelid and the dimension of its virtual projection area was assessed, and was defined as the sag parameter. This parameter was significantly correlated with the sag score (a photographic scale to assess the degree of sagging) and with aging. The accuracy of the sag parameter was confirmed in a clinical test using a sag treatment lotion and a placebo lotion. The sag score decreased in skin treated with the sag treatment lotion, but the change was not significantly different from that of the placebo treated skin. On the contrary, the sag parameter was significantly reduced (P < 0.05) after topical application of the sag treatment lotion compared with the placebo-treated skin. These results indicate that the sag parameter as proposed herein is useful in clinical studies to evaluate slight changes in lower eyelid sagging.     

图像分析法测试黑板条干的研究

简要介绍了数字图像处理技术在纺织上的应用及发展趋势,基于数字图像处理技术,开发出一套能够客观评价黑板条干的系统软件。     

Objective evaluation of wrinkled fabric using radon transform

Abstract

Wrinkling is one of the most important visible properties of a fabric for the consumer that is routinely evaluated in reference to a set of visual standards in the textile industry. The visual evaluation is unreliable and time-inefficient. This paper introduces a new quantitative analysis method for fabric wrinkle and addresses the development of an image analysis technique using the radon transform (RT) and texture analysis to evaluate it. Objective results from the RT and texture analysis are compared with subjective ones from human experts. The study reveals a linear relationship between the RT as objective evaluation and subjective evaluation having a correlation coefficient of 0.97. The correlation between texture analysis and subjective evaluation is acceptable.     

基于数字图像处理的印刷墨斑分析方法及应用研究

针对印刷品常遇到的墨斑问题,利用数字图像处理技术分析印刷墨斑,建立了印品墨斑的分析方法及分析模型。在此基础之上,将该方法应用到喷墨纸、新闻纸、铜版纸、双胶纸上,并对四种纸张的印刷墨斑进行分析,同时将该方法与人眼视觉评价体系进行相关性分析。结果表明:本文构建印刷墨斑的数学模型及方法很好地分析了印刷品的墨斑,并与人眼视觉评价结果有很好的相关性,其中,喷墨纸运用此方法效果最佳。     

用定量图像分析法测量聚酰胺纤维粗细

介绍了用高分辨率扫描仪和Fibershape软件测量产业用纤维粗细的方法。由于试样准备工作简便快捷,可以实现大量纤维的扫描和测量,从而使测量结果具有较高的统计精确度。而且,该测试方法还可给出纤维粗细分布的信息。不同粗细的聚酰胺纤维的测量结果与它们的线密度值是高度相关的。Fibershape是一种经济、方便和可靠的纤维粗细测试手段。     

餐饮企业形象定量分析技术及应用实例

餐饮企业形象在引导顾客消费、提升餐饮企业品质和创造无形价值方面，起着重要的作用。要确立鲜明独特餐饮企业形象，必须做好餐饮企业形象的分析工作。但目前国内外对餐饮企业形象分析，往往局限于质的方面，缺少从量化的角度进行评价和分析。因此这种分析比较笼统，也无法对餐饮企业形象改善起到比较实际的指导作用。本文试图从量化的角度确立餐饮企业形象分析的且体方法，因此在分析餐饮企业形象特点、构成要素的基础上，提出了餐饮企业形象量化分析的一些具体方法，并结合实例进行了直观地说明。餐饮企业形象量化分析方法的提出，不仅是希望在理论上做一些开拓性的探索，也希望能够对业界在进行餐饮企业形象分析时提供有用的工具。     

Genetic evaluation of mastitis in dairy cattle using linear models, threshold models, and survival analysis: a simulation study

The objective was to study, by simulation, whether survival analysis results in a more precise genetic evaluation for mastitis in dairy cattle than cross-sectional linear models and threshold models by using observation periods for mastitis of 2 lengths (the first 150 d of lactation, and the full lactation, respectively). True breeding values for mastitis liability on the underlying scale were simulated for daughters of 400 sires (average daughter group size, 60 or 150), and the possible event of a mastitis case within lactation for each cow was created. For the linear models and the threshold models, mastitis was defined as a binary trait within either the first 150 d of lactation or the full lactation. For the survival analysis, mastitis was defined as the number of days from calving to either the first case of mastitis (uncensored record) or to the day of censoring (i.e., day of culling, lactation d 150 or day of next calving; censored record). Cows could be culled early in lactation (within 10 d after calving) for calving-related reasons or later on because of infertility. The correlation between sire true breeding values for mastitis liability and sire predicted breeding values was greater when using the full lactation data (0.76) than when using data from the first 150 d (0.70) with an average of 150 daughters per sire. The corresponding results were 0.60 and 0.53, respectively, with an average of 60 daughters per sire. Under these simulated conditions, the method used had no effect on accuracy. The higher accuracy of sire breeding values can be translated into a greater genetic gain, unless counteracted by a longer generation interval.     

Particle size characterisation of in-flow milling products by video image analysis using global features

The objective of this work was to characterise the particle size of milling products by image analysis. Four classes of milling products were obtained by varying the roll gap of the second break roll of the mill. Images were acquired by using an in-flow imaging system implemented in the mill, and 1300 images were recorded for each class. Three methods of image analysis were investigated: morphological opening, constant grey level run lengths and grey level spatial interdependences. Discriminant analyses were applied to the data extracted from the images by the three methods in order to identify each class of milling product. More than 77% of the samples were correctly assigned to their group, both for the calibration and validation sets. The best results were obtained by applying morphological openings or by computing parameters from the co-occurrence matrices. The number of correct classifications rose to 81% of samples with only three variables selected for the opening curves and to 83% with three co-occurrence parameters. © 1998 Society of Chemical Industry     

Size properties of legume seeds of different varieties using image analysis

Image analysis system was used to provide geometric parameters of legume seeds, which are important for designing of engineering processes such as drying, milling, germination etc. Measured features of bean and lentil seeds were projected area, equivalent diameter, MaxFeret, MinFeret and thickness. Three approximation models (an oblate spheroid, two sphere segments and a triaxial ellipsoid) were used to evaluate volume and surface area of lentil and bean seeds of various varieties. The best approximation model was found as the triaxial ellipsoid and the oblate spheroid for bean varieties and two sphere segments for lentil varieties. From the model data estimated specific surface area were ranged from 5.1–5.8 cm²/g for bean varieties and 11.57–11.95 cm²/g for lentil varieties. Image analysis system provided fast and accurate values of important technological properties of legume such as geometric parameters, volume and surface area.     

AKD用量对喷墨打印质量的影响

利用图像分析方法研究施胶剂AKD用量对喷墨打印纸的基本性能和打印质量的影响。包括喷墨打印后由于纸张施胶度的差别所导致的图像墨层匀度、点的边缘锐化值、文字的羽化与毛细管现象、点的实地密度、点的打印质量指数（IDQI）和喷墨打印质量指数（IPQI）的变化。根据图像分析法认为：对于施胶纸,是否加填以及填料种类对喷墨打印质量有较大的影响,且添加AKD有利于提高喷墨打印的质量。     

粳稻米饭图像解析与感官分析的相关性

124份东北粳稻图像解析的白度和光泽值与米饭感官的光泽、食味、冷饭、米饭综合评分等感官食味评价结果呈极显著正相关.图像解析分析的白度≥1.0、光泽≥0的水稻品种,具有较优质的食味品质.图像解析测定的白度和光泽值可以快速的鉴定水稻品种的食味品质,在批量检测米饭食味时可以替代常规的感官食味评价方法.     

Genetic evaluation of mastitis resistance using a first-passage time model for wiener processes for analysis of time to first treatment

A Wiener process is a Brownian-motion process initiated in a certain state in a state space, and the first passage time is defined as the time of the process to reach a predefined absorbing state where the process stops. Time from 31 d prepartum to first treatment of clinical mastitis (CM) was modeled as first passage times of such Wiener processes. Two processes were used to allow for several risk factors, and for each process, initiation was at some arbitrary time point, in a certain health state with drift toward or away from absorption (disease). The drift parameter of each process was expressed as linear functions of covariates (year of calving and sire). First passage time was defined as the time from process initiation until the first health status process reached zero (absorption). The model was fitted to records for 36,178 first-lactation daughters of 245 Norwegian cattle sires using a Bayesian approach and Markov chain Monte Carlo methods. Genetic evaluation of sires was carried out by calculating the posterior probability of no CM (the value of the survival function) by d 331, i.e., 300 d after first calving. Alternatively, sire evaluation was based on the integrated area under the survival curve. These measures were highly correlated (0.999), which indicates a small degree of crossings of the sire-dependent survival curves. Hence, sire-specific hazards were close to proportional, resulting in a higher rank-correlation to sire evaluations from a survival model with proportional hazards than to the results from a multivariate threshold model.     

QDA在火腿肠感官评定中的应用

采用定量描述法（QDA）对三种火腿肠进行了感官评定,并建立了三种火腿肠的QDA数据的蜘蛛网图,结果表明,此方法能区别三种火腿肠的感官特性,适用于火腿肠感官品质的评价。