基于计算机视觉技术对滩羊肉新鲜度分级方法研究

正利用计算机视觉技术对滩羊肉品新鲜度分级方法进行研究,提取肌肉区域图像在RGB和HIS颜色空间的特征分量,分析这些特征分量在滩羊肉品贮藏期间的变化趋势。结果显示,滩羊肉图像的R值随贮藏时间的延长线性降低,G和B值则随贮藏时间的延长线性增加;色度(H值)指向由红转为蓝绿色,饱和度(S值)随贮藏时间的延长先减后增,而亮度(I值)没有明显的趋向性。运用神经网络建立滩羊肉新鲜度分级模型判别正确率达90%以上,表明基于计算机视觉     

基于图像处理的储藏小麦电导率变化的相关性研究

定期测定不同储藏条件下小麦的电导率值,同时用扫描仪采集小麦的表面图像并提取其图像特征,研究储藏过程中小麦的颜色特征参数与电导率的相关性。结果表明:R值、G值、B值、I值、电导率均与储藏时间均呈极显著性相关。与电导率相关性最显著的是I值,其中,瑞星1号小麦的电导率与I值的数学模型:y=1.3E-16x~(8.4613)(电导率值为y,I值为x,下同),R~2=0.869;郑麦8998小麦的电导率与I值的模型:y=1.7E-18x~(9.2785),R~2=0.913;两种小麦的电导率与I值的模型:y=1.0E-8x~(4.5932),R~2=0.676。     

烘烤过程中烟叶颜色特征参数与色素含量的关系

为了明确烟叶颜色特征与色素含量的关系,以红花大金元品种不同成熟度烟叶为试验材料,研究了烘烤过程中颜色特征参数和色素含量的变化以及二者间的关系.结果表明,在整个烘烤进程中,烟叶图像的3个颜色特征参数的大小依次为R(彩色数字图像中红色的亮度值)＞G(彩色数字图像中绿色的亮度值)＞B(彩色数字图像中蓝色的亮度值);不同成熟度烟叶R、G、B分量的平均值均表现为过熟＞适熟＞尚熟.烘烤过程中成熟度低的烟叶叶绿素降解速度较快,降解量明显大于成熟度高的烟叶;尚熟烟叶的类胡萝卜素含量在变黄和定色期大量降解,直到定色期结束时与适熟和过熟烟叶的类胡萝卜素含量接近,而过熟烟叶的类胡萝卜素含量下降幅度较小.R值与烟叶叶绿素含量间呈极显著负相关,B值与烟叶类胡萝卜素含量间存在显著负相关;R,G组合和r,g值(颜色分量)均与色素含量有较好的相关性;H(色调)值与烟叶叶绿素和类胡萝卜素含量间均存在极显著的正相关.选取与烟叶色素含量均具有显著相关关系的8个颜色特征参数,即H,g,r-g,G-R,G/R,G/(R+B),(G-R)/(G+R)和(R-G)/(R+G+B)值,建立了对烟叶色素含量的逐步回归方程,经F测验达到极显著水平.因此,烘烤中不同成熟度烟叶颜色特征参数和色素含量的相关性明显,可以用颜色特征参数作为辅助指标来判断烟叶色素含量.     

UST-4型条干仪所测毛羽值与纱线颜色的关系

研究了Uster-4型条干仪测试的毛羽值与纱线颜色的关系,发现纱线的颜色对毛羽值有很大影响.选定一个目测最黑的纱样为标准样,其他纱线试样与标准样的毛羽值偏差量△H为2样品之间的色差综合变量△E的对数.色光变量中的明度变量L(即颜色深浅或亮度)与毛羽值的相关性很高,而红绿变量a、黄蓝变量b、彩度变量C和色调变量G与毛羽值的关系不太密切.     

BP人工神经网络南疆红枣颜色分级方法的研究

以南疆红枣颜色分级为研究对象,从预处理后的红枣图像中提取红体均值(R)、绿体均值(G)和蓝体均值(B)以及它们的均方差σR、σG、σB共6种颜色特征变量;再将图像从RGB到HIS颜色空间转换,然后从HIS颜色空间中,提取色度均值(H)、亮度均值(I)和饱和度均值(S)以及它们的各自的均方差σH、σS、σI共6个颜色特征变量,总计12个颜色特征变量,最后应用BP神经网络进行红枣颜色分级。结果表明,BP人工神经网络分级与人工分级的一致度达到了91.6%,该网络分级效果良好,能较好地满足红枣颜色分级的需求,对南疆红枣产品的生产、销售具有一定的理论指导和实际应用意义。     

定量分析钻石火彩方法的可行性研究

运用钻石光学效果观测仪采集钻石样品在环形光线下的图像,运用HSI(色调、饱和度、亮度)颜色模型转换技术,将图像由RGB颜色模型转换到HSI颜色模型进行处理,计算钻石的火彩值。对比分析钻石图像中彩色的分布特征和火彩值,彩色分布较多的钻石样品,火彩值也较高,火彩值与肉眼感知结果基本一致,说明定量分析钻石火彩的方法准确可行。对比分析钻石的火彩值与冠角、亭角之间的关系,结果显示托尔夫斯基提出的理想切工的钻石呈现出较高的火彩,彼此佐证;钻石的火彩值与亭角或者冠角之间并非简单的线性函数关系,说明定量分析钻石火彩的必要性。     

手机数字图像与甘薯β-胡萝卜素含量间相关性

该研究旨在探讨手机数字图像信息与甘薯β-胡萝卜素含量间的关系。采用智能手机采集甘薯块根切片的图像,对图像的RGB信息与甘薯β-胡萝卜素含量间的关系进行了研究,并建立了预测模型。研究发现,甘薯β-胡萝卜素含量与甘薯切片图像的绿值(G)间呈极强的负相关,与蓝值(B)呈中等强度负相关,红值(R)与β-胡萝卜素含量之间无相关性。采用对数函数对G值与β-胡萝卜素含量间的关系进行拟合,模型的拟合确定系数(R~2)达到0. 947,模型的预测相关系数(r_p)、预测均方误差(RMSEP)和标准偏差比(SDR)分别为0. 983、0. 819和5. 269。结果表明,手机数字图像可以反映甘薯β-胡萝卜素含量间的差异,使用图像的颜色值信息可以较为精确地估计甘薯β-胡萝卜素含量,为甘薯品质快速检测提供了新的思路。     

声-超声参数与木材解剖特征的关系研究

为探索利用声-超声(AU)技术预测落叶松木材解剖性质的可行性,测量了落叶松无疵小试样的波速(V)、峰值电压(A)、均方根电压(RMS)、上升时间(RT)、频率形心(FC)等五个声-超声参数和年轮宽度(RW)、晚材率(LR)、微纤丝角(MFA)、管胞长度(TL)和管胞宽度(TW)等5个解剖特征。分别利用一元线性回归分析方法和多元线性回归分析方法研究了声-超声参数与解剖特征之间的相关性。结果表明:1)不同解剖特征和单个声-超声参数之间的相关性存在差异。其中,管胞长度与波速呈显著正相关,其相关性决定系数较高(R~2=0.31),与其它4个声-超声参数的相关性较低(R~2≤0.16);微纤丝角与波速呈显著负相关,其R~2=0.46,与其它4个声-超声参数的相关性较低(R~2≤0.14);年轮宽度、晚材率、管胞宽度与5个声-超声参数相关性都较差(R~2≤0.11)。2)利用多元回归分析方法建立的微纤丝角线性预测模型的效果高于仅以波速为自变量建立的微纤丝角线性预测模型的效果,决定系数从0.46提高到0.63。     

基于Kubelka-Munk双常数理论的纬全显色提花织物配色算法

纬全显色结构提花织物,采用不同颜色的纱线与织物结构相配合,能够在织物表面获取各种各样的花形图案及丰富的颜色,由于织物结构与各单色纱线种类的千变万化,颜色设计一直以来都是生产设计中的难题,为了求得纬全显色提花织物的色彩显色模型。本文采用黑、白、红、绿、黄五种颜色为纬纱,按两组分不同比例混合交织得到单经双纬的纬全显色提花织物试样,通过大量实验测试,用数学中的最小二乘方法求得Kubelka-Munk双常数理论中的单纱吸收系数K值和散射系数S值,从而得到纬全显色提花织物的配色算法、并对织物中各纬纱颜色的表面比例进行预测。结果表明Kubelka-Munk双常数理论可以较好的解释纬全显色提花织物颜色与各单纱颜色比例之间的关系。     

绿色翡翠颜色的HSL色度学特征

目前的翡翠市场暂时未建立起评价绿色翡翠颜色的统一标准。基于HSL色度学的绿色翡翠颜色分级理论与技术,本研究拟采用机器视觉法。根据色度学原理,以HSL颜色空间模型为理论基础,在色温5 500K白光光源下,通过彩色数码摄像头采集绿色翡翠样品的色彩,对每个样品图像颜色进行HSL值分析,从而量化绿色翡翠颜色的参数指标,并将所得到的HSL数值按不同色相(H)投点到二维的SL图像上,得到翡翠绿色色彩的HSL分布区间及其色度学特征,确定绿色翡翠各种色彩类型的HSL值边界,从而区分和确定绿色翡翠的色调,划分绿色翡翠的颜色浓度和明亮度,量化绿色翡翠的色彩类型。     

基于不同颜色模型定量预测永川秀芽在制品含水率

为定量预测永川秀芽在制品的含水率,基于不同颜色模型探究在制品的色泽变化,并结合偏最小二乘（partial least square,PLS）法建立含水率的定量预测模型。结果表明：在永川秀芽初制过程中,在制品的红绿度、蓝色通道均值增高,含水率和亮度、黄蓝度、红色通道均值、绿色通道均值、色调均值等15 个颜色模型分量降低,即色泽表现为变暗、变黄;通过热图与聚类分析,可将在制品分为2 个大类、4 个亚类,且理条工序对在制品含水率、色泽的影响最为显著;利用17 个颜色模型分量和PLS方法建立了含水率的定量预测模型,以校正集相关系数（Rc）、交互验证均方根误差（root-mean-square error of cross-validation,RMSECV）、预测集相关系数（Rp）、预测均方根误差（root-mean-square error of prediction,RMSEP）、相对分析误差（relative percent deviation,RPD）为评价指标。模型的Rc、Rp、RMSECV、RMSEP分别为0.979、0.980、0.044 7、0.044 3。RMSECV、RMSEP的差值仅为0.000 4,且RPD达到5.04,表明模型具有极好的预测能力和泛化能力,为实现永川秀芽在制品含水率的在线监测提供了一种新方法。     

Automated prediction of sensory scores for color and appearance in canned black beans (Phaseolus vulgaris L.) using machine vision

Evaluation of canning quality of beans is commonly carried out by simple visual inspection that is time-consuming, resource intensive, and biased by the experience of the panelist. Moreover, there is not a standard scale to rate visual quality traits of canned beans. In this research, a machine vision system was implemented and tested for automatic inspection of color (COL) and appearance (APP) in canned black beans. Various color and textural image features (average, standard deviation, contrast, correlation, energy, and homogeneity from red, green, blue, lightness, red/green, yellow/blue, hue, saturation and value color scales) were extracted from beans and brine images, and evaluated to predict the quality rates for COL and APP of a group of bean panelists using multivariate statistics. Sixty-nine commercial canned black bean samples from different brands and markets were used for analysis. In spite of the “fair” agreement among the sensory panelists for COL and APP, as determined by multi-rater Kappa analysis, machine vision data based on partial least squares regression model showed high predictive performance for both COL and APP with correlation coefficients of 0.937 and 0.871, and standard errors of 0.26 and 0.38, respectively. When a classification was performed based on both COL and APP traits, a support vector machine model was able to sort the samples into two sensory quality categories of “acceptable” and “unacceptable” with an accuracy of 89.7%. Using simple color and texture image data, a machine vision system showed potential for the automatic evaluation of canned black beans by COL and/or appearance as a professional visual inspection.     

Classification of pre-sliced pork and Turkey ham qualities based on image colour and textural features and their relationships with consumer responses

Images of three qualities of pre-sliced pork and Turkey hams were evaluated for colour and textural features to characterize and classify them, and to model the ham appearance grading and preference responses of a group of consumers. A total of 26 colour features and 40 textural features were extracted for analysis. Using Mahalanobis distance and feature inter-correlation analyses, two best colour [mean of S (saturation in HSV colour space), std. deviation of b∗, which indicates blue to yellow in L∗a∗b∗ colour space] and three textural features [entropy of b∗, contrast of H (hue of HSV colour space), entropy of R (red of RGB colour space)] for pork, and three colour (mean of R, mean of H, std. deviation of a∗, which indicates green to red in L∗a∗b∗ colour space) and two textural features [contrast of B, contrast of L∗ (luminance or lightness in L∗a∗b∗ colour space)] for Turkey hams were selected as features with the highest discriminant power. High classification performances were reached for both types of hams (>99.5% for pork and >90.5% for Turkey) using the best selected features or combinations of them. In spite of the poor/fair agreement among ham consumers as determined by Kappa analysis (Kappa-value < 0.4) for sensory grading (surface colour, colour uniformity, bitonality, texture appearance and acceptability), a dichotomous logistic regression model using the best image features was able to explain the variability of consumers’ responses for all sensorial attributes with accuracies higher than 74.1% for pork hams and 83.3% for Turkey hams.     

Measurement of the geometrical features and surface color of rapeseeds using digital image analysis

Digital image analysis was applied to determine the geometrical features and color of rape seeds surface, and to discriminate some impurities, that are difficult to separate in the cleaning process. The paper notices on methodological aspects, and the experiment described constitutes the first stage of studies on the possibility of applying digital image analysis to rapeseed quality estimation, so the results obtained should be treated as preliminary. The geometrical features of seeds and their color were analyzed using the LUCIA G ver. 4.8 software. It was found that variation in geometrical dimensions of seeds was much lower than in color of their surface, so minimum sample size utilized for color measurements should be larger. The surface color of seeds was feature that insufficiently differentiates seeds of different dimensions. Only small seeds were characterized by somewhat changed distribution of color on their surface. An analysis of color of rape and stickywilly seeds in RGB (red/green/blue) model showed distinct differences in value ranges, enabling to distinguish between these seeds. Surface color of mature, immature and broken seeds cannot be used to distinguish these fractions.     

不同光质处理对采后桃果皮色泽及花色苷代谢的影响

为研究不同光质处理对桃果采后色泽的影响,探讨光照对桃果花色苷代谢的调控机制,本实验以‘中桃九号’为实验材料,在（22±1）℃条件下对桃果进行不同光照处理（红、绿、蓝、白光）,光照时间12 h/d,以黑暗处理为对照。分析不同光照处理后桃果色泽、花色苷含量,及花色苷合成途径酶活力、结构基因和相关转录因子表达水平的变化。结果表明：红光、绿光对桃果皮着色没有明显影响,白光有微弱的促进作用,而蓝光能显著促进桃果皮色泽的提升,采后第6天时蓝光处理组桃果皮花色苷含量达到27.26mg/kg,分别是白光处理组和对照组的4.48倍和10.34倍。在蓝光作用下,花色苷合成途径酶活力以及结构基因和转录因子表达水平在大多数时间点显著高于对照组以及其他光照处理组（P<0.05）。其中,结构基因PAL、CHS、F3H、DFR、ANS、UFGT和转录因子MYB10.1的表达水平与桃果皮色泽参数以及花色苷含量呈显著正相关。综上,蓝光处理通过上调花色苷合成通路诱导桃果皮花色苷的合成和积累。研究结果将加深对光照调控植物花色苷代谢机制的理解,同时为研发桃采后色泽调控技术提供理论依据。     

鲜食葡萄果穗形状颜色的多视角投影成像检测

设计了一种基于平面镜的低成本多视角投影成像结构,用于获取鲜食葡萄果穗不同侧面信息来判断果穗形状、颜色是否合格。采用两片前表面平面镜来延伸单目相机的拍摄视野,以最大限度地获取果穗全表面信息。通过图像处理方法分割果穗的实像虚像区域,并借助悬挂果穗的高度不变属性对虚像区域进行放大,得到三个每隔120°的同样高度果穗。提取果穗区域、轮廓宽度曲线参数来对果穗外观形状进行评价,与人工分级对比,对果穗形状分级的准确率为95.5%;将彩色图像RGB转换到HSI颜色空间,从色度图像(Hue)获取果穗成熟时的典型颜色区域,计算果面着色面积比例,并按照着色面积比例的大小进行颜色分类,准确率为81.1%。结果表明多视角同时成像的方法可用于葡萄外观的分级,为在线检测提供参考。     

Application of Image Analysis Combined with Computational Expert Approaches for Shrimp Freshness Evaluation

This study was aimed to evaluate the freshness and quality of cultured shrimp (litopenaeus vannamei) during 9 days of storage on ice (i.e., at a temperature of 0°C) using image processing technique. A lighting chamber was used to provide uniform conditions for illumination. The shrimp freshness was evaluated using computer vision technique through color changes of head, legs and tail of the harvested shrimps. Thirty-six color parameters of the images such as mean and variance of red (r), green (g), blue (b), lightness hue (h), saturation (s), value (v), luma information (i and y), the luma component (y), chroma component (cr), lightness (L*), redness (a*), yellowness (b*), chroma (c), and hue (h) were analyzed. Some parameters, such as b*, from side pictures and r mean, b variance, v mean, y mean, b* mean and (L*) mean from top pictures changed with a rather similar trend during the storage period. Different computational expert approaches such as linear discriminant analysis, quadratic discriminant analysis, K nearest neighbors, and discriminant partial least squares regression were examined for shrimp freshness classification. For this, all the variables and the subsets of variables were selected by means of stepwise linear discriminant analysis, stepwise orthogonalization, classification and regression trees. The shrimp freshness was characterized with a high classification accuracy of 90%. Freshness evaluation using image processing is proposed as a potential technique to the food industry.     

基于多源信息融合的绿茶杀青叶水分含量智能感知方法

为了实现绿茶杀青过程中水分含量的快速有效检测,利用机器视觉结合近红外光谱技术,构建绿茶杀青过程中水分含量变化的定量预测模型。首先采集杀青过程中在制品的光谱和图像信息,然后采用竞争性自适应权重取样（competitive adaptive reweighted sampling,CARS）法、变量组合集群分析（variables combination population analysis,VCPA）法、变量组合集群分析法结合迭代保留信息变量（variable combination population analysis and iteratively retains informative variables,VCPA-IRIV）法和随机蛙跳法（random frog,RF）4 种变量筛选方法提取光谱中的特征波长,并融合图像中的15 个色泽和纹理特征建立线性偏最小二乘回归（partial least squares regression,PLSR）和非线性支持向量回归（support vector regression,SVR）预测模型。结果表明,与单一数据相比,基于融合数据所建立的模型能有效提高预测精度,其中基于CARS算法提取光谱特征波长融合图像的15 个颜色特征,并结合归一化预处理和主成分分析（principal component analysis,PCA）建立的SVR模型效果最佳,其中校正集相关系数为0.974 2,预测集相关系数为0.971 9,相对分析误差（relative percent deviation,RPD）为4.154 6,表明模型具有极好的预测性能。综上,本研究证明融合光谱和图像技术对绿茶杀青过程中水分含量预测的可行性,克服了单一传感器预测精度低的问题,为实现绿茶杀青叶水分含量的快速无损检测和精准把控杀青质量提供理论基础。     

紫外荧光喷墨油墨色调再现能力的研究

为了研究紫外荧光喷墨油墨的色调再现规律,本研究分别采用红、绿、蓝三色荧光喷墨油墨喷印了21级灰梯尺,并测试各灰阶的相对荧光强度,比较了三色荧光喷墨油墨色调再现能力的大小;针对光学性能各异的几种纸张,探讨了纸张亮度和光泽度对荧光喷墨油墨色调再现的影响;改变R、G、B颜色分量,调节白平衡。实验结果表明:红、绿、蓝三色荧光喷墨油墨色调再现规律和能力各异;纸张的亮度和光泽度对色调再现有较大的影响;当R、G、B颜色分量分别为255、110、66时,可呈现亮度最大的白色。     

Effects of storage temperature and stage of ripening on RGB colour aspects of fresh-cut tomato pericarp using video image analysis

Tomato fruit (Lycopersicon esculentum cv. Belissimo) were harvested at three different stages of ripening, sliced and stored at five different temperatures. Red–green–blue (RGB) images of the slices were taken regularly during storage, using a image processing system. For constructing a model, each of these colour aspects was considered to be built up by a variable part that changes according to a first order reaction mechanism and a fixed part that is invariable under the circumstances under study. All three colour aspects of the tomato slices (R, G and B) decreased exponentially during storage. The parameters of the model were estimated using multiple-response multiple-variate non-linear regression analysis using R, G and B simultaneously as response variables and time, temperature and ripening stage of the fruit at harvest simultaneously as explaining variables. To combine the information on the behaviour of the colour aspects during the preharvest and the postharvest period at different temperatures, it was assumed that the process of change during ripening was the same whether the fruit ripened on the plant or off-vine. So, the initial value for all three colour aspects (Col_0,R, Col_0,G and Col_0,B) during the postharvest experiments depended on the time the tomatoes were allowed to ripen on the plant. By using this fundamental approach to build the model and using all available data and information it became possible to describe and simulate the behaviour of the colour aspects of tomato slices as a function of the ripening stage and the applied storage temperature.Although the variance between replicates was high, the statistical analysis on the mean values of colour aspects over the replicates provided a percentage variance accounted for of 95%. The same model was validated with data of another experiment with another tomato cultivar (Durinta) over a larger range of maturity stages.