Measurement of fuzz fibers on fabric surface using image analysis methods

Fuzz on the fabrics, which is the fibers protruded from the fabric surface, is very important in view of appearance quality, since it causes unpleasant appearance on the fabrics and also leads to pilling which makes fabric appearance and softness worse. However, fuzz on fabric surface is measured mostly by subjective methods (human vision) rather than objective methods. Thus, in this study, objective method using image analysis techniques has been developed for the measurement of fuzz on fabric surface. Fuzz on the fabric has also been ranked and rated by experts in order to see the reliability of the results obtained from the fuzz measurement. It was observed that correlation coefficient (r) between rating value and objective measurement value was 0.9 and this correlation coefficient value confirmed the reliability of this method.     

Orthotropic theory for the prediction of mechanical performance in thermally point-bonded nonwovens

The orthotropic theory is applied for the nonwoven fabrics that have a preferred orientation direction, the case if the structure is not isotropic. The polynomial regression analysis is employed to allow the attainment of more statistically meaningful information. A functional form based on the transformation rule is developed for the orthotropic approach. The predictions thus obtained are seen to be in excellent agreements with experimental data and the resulting compliances exhibit meaningful relationships for the processing conditions. The compatibility of the compliances from tensile and shear analyses has been explored prior to a practical application of the four compliances defining the in-plane strain-stress field.     

Relationship between fiber orientation distribution function and mechanical anisotropy of thermally point-bonded nonwovens

Current efforts to establish links between geometrical features and mechanical performance of nonwoven fabrics in general, and of point-bonded (spot-bonded) nonwovens in particular has been made using the measurements of Fiber Orientation Distribution Function (ODF) and tensile modulus which occurs during controlled-deformation experiments. Image analysis technique (using the Fast Fourier Transform) was used to quantify the fiber orientation distribution. The results suggest that, within a typical window of processing conditions, the fiber orientation has a significant influence on the anisotropical behavior of nonwoven. The data also suggest that mechanical anisotropy of thermally point-bonded nonwovens is likely to be governed by different load transfer mechanism according to the applied macroscopic tensile direction.     

Application of image analysis to the prediction of EBC barley kernel weight distribution

It is known that the barley kernel size is an important factor regarding the uniformity of the malting and brewery processes, barley valuation, approval and market value. In order to facilitate the barley purchasing process, a fast field technique for kernel size evaluation, such as the image analysis technique proposed in this work, would be greatly appreciated as a fast and simple procedure for barley selection. In this study a close correlation between the image analysis and the standard EBC was obtained with a correlation factor of 0.999 and a regression coefficient of 0.991 between the two methodologies. The proposed IA methodology was found to accurately predict the Scarlett and Prestige barley varieties weight distribution especially when considering the crucial ‘business transactions selection’ classes.     

Discrimination of wheat grain varieties using image analysis and neural networks. Part I. Single kernel texture

The development of non-destructive methods for the evaluation of cereal grain varieties has important implications for the food processing industry. The described experiment investigated 11 varieties of spring and winter wheat of different quality class. The analysis was performed on images acquired from a flatbed scanner interfaced to a PC. Kernel images were digitalized at high resolution (2673 × 4031) with 24-bit depth and 400 dpi. The variables input into the statistical model were the textures of single kernel projections. Textures were computed separately for seven channels (R, G, B, Y, S, U, V). The results were examined with the application of discriminant analysis and neural networks. The accuracy of texture-based classification of 11 wheat varieties reached 100%. The experimental design which yielded the most satisfactory results comprised texture measurements from the combined area of 20 kernels and variables from seven channels input into the neural network. The final classification quality was not affected by the year of cultivation, moisture content or grain variety.     

Development of an objective fabric pilling evaluation method. I. Characterization of pilling using image analysis

An objective evaluation method for woven fabric pilling has been developed using image processing and statistical analysis. Five ASTM photographic standard images were analyzed to determine a characterization method for fabric pilling. Images were filtered by various image analysis techniques such as fast Fourier transformation (FFT) and fast wavelet transformation (FWT). Three parameters including the number of pills, the total pixel area of pilling, and the sum of the gray values of pill images have been defined and extracted automatically from the images. Finally, the relationship between pilling grade and those parameters has been established by a series of statistical analyses.     

Measurement and fissuring of rice kernels during quasi-moisture sorption by image analysis

Fissuring associated with kernel elongation was evident in a moisture-adsorbing environment at 15 °C of relative humidity 88.72±0.28% with moisture content from 6% (d.b.) to 16.3% (d.b.). The average length and width of 800 kernels was measured during the sorption test using a Cervitec Grain Inspector equipped with two digital cameras. Samples were exposed to both a moisture-adsorbing and desorbing environments at 15 °C with relative humidities of 23.4±0.53%, 55.9±0.27%, 70.98±0.28% and 88.72±0.28%. On image analysis, the kernels changed in size from 5.13 to 4.84 mm in length and 2.9 to 2.73 mm in width. Both length and width changed as expected during moisture-adsorbing and moisture-desorbing tests. Fissured kernel percent was related to changes in the average length of the kernels during the moisture-adsorbing tests. The average length and fissured kernel percent of rice kernels measured by image analysis may be considered as a reliable indicator of changes in their dimensions during quasi-static moisture sorption processes.     

Objective evaluation of antimicrobial property of textile materials using image analysis

Performing the right antibacterial testing definitely has become one of the most critical aspects in evaluating the antimicrobial abilities of the textile materials. However, antimicrobial testing is by nature complex, delicate, and laborious. Therefore most of antimicrobial analysis methods, either antibacterial or antifungal, rely on subjective assessments. In this study, an image analysis method has been developed to count the colonies during the process of antibacterial test for textile materials. The reliability of the the software was investigated by comparing the result of image analysis with that of manual counting, which showed that the reliability of the newly proposed method was sufficiently high.     

Comparison of threshold algorithms for automatic image processing of rice roots using freeware ImageJ

High-throughput phenotyping of crop root system architecture using digital image analysis requires costly special software (WinRHIZO). Novel freeware, ImageJ, has also been developed for the similar purpose, but the presetting of the threshold to create root binary images makes this method time-consuming. This study compares the 16 algorithms available in the ImageJ for processing of rice root images. Among the algorithms, the Triangle algorithm proved to be the best binary method, where the coefficient of correlation between ImageJ-estimated and WinRHIZO-estimated root lengths is extremely high (r = 0.986). However, using the Triangle algorithm, ImageJ overestimated the rice root length compared with WinRHIZO. By multiplying the values obtained using ImageJ by 2/3, the estimates closely corresponded to those estimated by WinRHIZO. The correspondence of root lengths estimated using WinRHIZO and ImageJ with Triangle algorithm was valid for roots of various morphologies, and for rice plants grown in uplands, rainfed lowlands, and irrigated lowlands. This report proposes the completely automated estimation of rice root length using freeware ImageJ with the appropriate threshold algorithm for image processing.     

Applying image analysis to automatic inspection of fabric density for woven fabrics

The gray line-profile method is introduced to find fabric density. Some patterned fabrics like stripe design as well as solid fabrics of basic weave structures are used to verify the efficiency and accuracy of the method. The approach is compared with Fourier transform method. Although the gray line-profile method is concise, it shows good results in both solid and patterned fabrics. In addition, it does not require a pre-processing or filtering technique in space or frequency domain to enhance the image suitable for the analysis. However, the approach is slightly influenced by the filter size for finding the local minimums of profile graph.     

The robustness of objective fabric pilling evaluation method

Previously, we proposed a new method to identify fabric pilling and objectively measure fabric pilling intensity based on the two-dimensional dual-tree complex wavelet reconstruction and neural network classification. Here we further evaluate the robustness of the method. Our results indicate that the pilling identification method is robust to significant variation in the brightness and contrast of the image, rotation of the image, and 2 ⁱ (i is an integer) times dilation of the image. The pilling feature vector developed to characterize the pilling intensity is robust to brightness change but is sensitive to large rotations of the image. As long as all fabric images are adjusted to have the same contrast level and the sample is illuminated from the same direction, the pilling feature vectors are comparable and can be used to classify the pilling intensity.     

Application of image analysis to optimization of the bread-making process based on the acceptability of the crust color

Consumption of bread and the demands concerning its quality features, being one of them its appearance, have been experiencing rapid growth. Thus, the standardization of its production aiming to keep its quality, applying new methods. The objective of this research was to develop a method to optimize the bread-making processes based on the acceptability of its crust color. For this effect, bread was experimentally produced using a Box-Behnken experimental design with three factors (sugar-flour relation, Baking temperature and Baking time) and three answer variables (L*, a*, b* = parameters of CIELab color space); determination of color, by means of the acquisition, pre-processing, and analysis of images of bread samples until getting the color expressed in CIELab coordinates; an analysis of sensorial acceptance was made determining the L*, a*, and b* with the highest acceptance by consumers; finally, the optimization of the production process was made based on the L*, a*, and b* parameters, getting the optimal production parameters. The results show that by using the proposed method, it is possible to correlate the parameters of CIELab color space and the acceptance of the final consumer aiming to optimize bread making processes, it means getting bread with crust color of maximum acceptability.     

Quality assessment of durum wheat storage centres in Sicily: Evaluation of vitreous, starchy and shrunken kernels using an image analysis system

The proportion of vitreous kernels in a sample is an internationally recognized specification for determining the value of durum wheat (Triticum durum Desf.). Vitreous kernels are mostly related to quality, which affects the pasta performance during cooking. Vitreousness and the amount of shrunken kernels are visually assessed during the grading process. This assessment is subjective and tedious.A machine vision system was developed to determine the percentage of vitreous, starchy, piebald and shrunken kernels in approximately 100 grain samples, using a trans-illuminated image of one layer of non-singulated kernels (in bulk) acquired by a digital camera. Classification models were developed with stepwise Linear Discriminant Analysis, as well as an on-line Bayesian classifier integrated with an image analysis system. The overall correct classification in Starchy classifier was high 98.58% in the Training set, made up of 6679 grains, following the Linear Discriminant Analysis classification, of 30 Italian cultivars harvested in 2005 in three localities. An independent Test set was constituted by samples collected in 30 Sicilian Storage Centres in the 2007 harvest season. The overall classification was 96.03%. For the Shrunken classifier 95.27% of the Training set and 99.58% of the Test set were correctly classified. The image analysis system was more reliable than the human inspectors who validated the system, both for the same samples measured many times and at different times.     

Estimating potato crisp colour variability using image analysis and a quick visual method

Summary Image analysis gave better precision than colorimetry in measuring the darkening caused by excess free sugar during crisping of potatoes. The image analyser was used to measure individual crisp Average Optical Density (AOD) values in order to examine the variability of AOD within and between tubers. It is unnecessary to measure more than one crisp per tuber when assessing breeding lines, although two crisps per tuber are recommended for quality control. Crisps from at least ten tubers should be measured. A ‘Quick Crisp’ method, in which single crisps from each of four tubers are judged against standard samples, is reported. Regression of results from this method on crisp reflectance percentage (Agtron score) gaveR ² of 0.967. However, the observer tended to overestimate at low values and underestimate at high values. Over several trials, the crossover point varied from 15 to 50 Agtron score units. Measurement of crisp colour variability for improving selection, management and purchasing decisions is discussed.     

Evaluation of malting barley quality using exploratory data analysis. II. The use of kernel hardness and image analysis as screening methods

This paper presents an exploratory investigation of the use of image analysis and hardness analysis of barley kernels for characterisation and prediction of malting quality. A sample set of fifty barley samples representing 15 spring barley and 10 winter barley varieties grown at two locations in Denmark was used. The samples were micro-malted and mashed and analysed for 13 quality parameters according to the official methods of the European Brewery Convention. A sub-sample of the barley samples was analysed on two different single kernel instruments: (1) Foss Tecator GrainCheck was applied for non-destructive recording of single kernel size and shape (width, length, roundness, area, volume and total light reflectance) and (2) Perten Single Kernel Characterization System 4100 was applied for single kernel hardness and weight determinations. The eight variables from these single seed analyses have been used in two different ways, either as means and standard deviations, or as appended histogram spectra representing 250 kernels from each bulk sample. By the two methods, it has been possible to obtain reasonable Partial Least Squares Regression (PLSR) models for the structural and physical part of the malting quality complex associated to malt modification, but it was as expected impossible to predict the biochemical parameters associated with nitrogen chemistry and enzymatic power. The best model was achieved for (1→3, 1→4)-β-D-glucan in barley. The hardness of the barley kernels is by far the most important variable for describing malting performance. The additional use of the morphological data as acquired by fast non-destructive image analysis, however, also reveals some malting quality information by improving the calibration models based on hardness alone. The brightness of the kernels is by far the most important GrainCheck variable but also kernel size and shape is associated to malting performance. In general, the utilisation of the single kernel readings (used as histogram spectra), compared to sample mean and standard deviation, did not provide additional information for an improved prediction of the malting quality parameters.     

Microscopy techniques and image analysis for evaluation of some chemical and physical properties and morphological features for seeds of the castor oil plant (Ricinus communis)

Ricinus communis seed is a source of protein and oil with a high potential to use as animal's feedstock and biodiesel production. However, the oil yield and the extraction efficiency depend on the process conditions applied, as well as on the physical, chemical and structural properties of the seed, which have not been fully investigated. Hence, the objective of this study was to evaluate some chemical and physical properties of R. communis seed as well as to describe and quantify the macro and microstructure of this raw material by microscopy techniques and image analysis. Chemical analysis confirmed the seeds’ high contents of protein (28.48 ± 0.25%) and fat (51 ± 0.31%). On the other hand, the values of geometric mean diameter (8.95 ± 0.05 mm), bulk density (538 ± 11 kg/m³), and true density (1458 ± 27 kg/m³), among others, were higher than the ones reported about similar oils seeds. Microstructural studies showed that the endosperm cells presented an ovoid shape, as obtained from the aspect ratio results (AR = 1.28 ± 0.17), and a cell density of 570 ± 10 cell/mm², resulting in a porous structure, while the embryo cells had a cell density of 4903 ± 2 cell/mm², and an AR of 2.41 ± 0.48, related to a more compact structure (rectangular form) in this part of the seed. Regarding to lipids bodies (lb), they were only visible in the endosperm cells, showing a circular shape (AR = 1.16 ± 0.1), and a mean cell density of 9.57 ± 2.40 lipid bodies/μm², associated to protein as observed by the mineral presence (K, P, Mg and S) as determined by the energy dispersive X-ray analysis. Microscopy techniques and images analysis were efficient tools for the characterization of macro and microstructure of seeds and the data obtained integrate numerical information that could be useful for thermal and mechanical processing of R. communis seed, as well as for the design process equipment.     

Detection of head blight (Fusarium ssp.) in winter wheat by color and multispectral image analyses

The use of camera vision to automatically detect head blight (scab) on wheat ears could provide information about the severity of this dangerous disease and help meet future food traceability requirements. Fusarium spp. is dangerous for both human and animal consumption and the ability to monitor symptom location and severity before the harvested product is further processed or stored could help determine whether the grain is fit for human/animal consumption, for bio-conservation, or is completely unusable.To generate various infection levels, field trials were conducted in 2008 and 2009 using wheat varieties with differing levels of susceptibility to the disease; plots were artificially infected with a spore suspension. A color (red, green, and blue) and a multispectral (red, infrared) camera system with real-time image analysis software were developed and compared to detect disease symptoms in the plots.The chlorophyll defect of the infected wheat ears was classified against the image background by setting binarization thresholds. The result was a black and white image. Single pixels or tiny clusters of pixels not belonging to the symptoms were eliminated by setting an area threshold. For both systems, a linear correlation was found between the camera and the visually detected disease levels of the wheat ears in the plots.In the non-infected control plots without disease symptoms, the multispectral system accurately measured “no disease” even though the digital color system detected too much infection (i.e., a false positive). The multispectral system showed a superior calibration capacity. While the color system had to calibrate for each variety, the multispectral system used only one calibration step before starting the measurements.     

甘蔗品种灰色模糊多维综合评估分析

采用方差分析,灰色模糊多维综合评估分析,选用2个主要经济性状与9个主要的工、农艺性状,对14个全国第二轮区域试验的甘蔗品种进行综合评价,结果表明：云蔗89/7、粤糖89/240、福农91/23,云蔗91/16、闽糖92/649、福农91/21、桂糖91/116、桂糖90/958个品种综合性状优良,可以考虑给予进一步繁殖,示范,推广;闽糖90/55、粤C29、粤农89/525、川糖91/91、川糖79/155个品种需要进一步试验观察,或者考虑作为亲本材料保存利用。     

Image analysis of the luster of fabrics with modified cross-section fibers

We have investigated the luster of modified cross-sectional fiber fabrics as one of the essential quality estimates for clothing development. We have confirmed an objective evaluation method, and have determined the experimental luster characteristics of modified cross-section fibers. The cross-section of the fibers in a fabric affects the appearance of a textile. We used the image analysis method to investigate the luster to determine the critical factors influencing the appearance of modified cross-section fiber fabrics. For similarly structured textiles in a component fabric, clear differences were observed in the fabric weave, density, percentage, and total area of blobs, which is image region. Color played a decisive role in the luster of the textiles, and luster was not significantly influenced by the modified cross-section fabric weave. In addition, the degree of luster did not increase in the order plain to twill to satin for modified cross-sectional fiber fabrics. All the split-type microfibers exhibited higher numerical luster values (percentage of pixels, and number and total area of blobs) than sea-island microfibers did. The degree of luster of the modified cross-sectional fiber fabrics was not high at specular reflection angles.