Quality evaluation of pickling cucumbers using hyperspectral reflectance and transmittance imaging—Part II. Performance of a prototype

This paper reports on the development and evaluation of methods and algorithms for detecting both external and internal quality of pickling cucumbers using the hyperspectral reflectance and transmittance images acquired by an online prototype described in a previous paper [1]. Experiments were performed in 2 years on ‘Journey’ pickling cucumbers, some of which were subjected to mechanical stress to induce internal defect in seed cavity. Hyperspectral images of the ‘Journey’ pickling cucumbers were collected under reflectance, transmittance, and their combination modes. Partial least squares analysis was performed on spectra extracted from the hyperspectral images to predict firmness, color, and the presence of internal defect. The system performed well on predicting skin color (chroma and hue) with the coefficient of determination (R ²) ranging between 0.75 and 0.77; however, it had poor prediction of fruit firmness. Transmittance data in the spectral region of 675–1,000 nm provided the best detection of internal defect for the test pickling cucumbers, with the detection accuracy up to 99%. Up to the best four wavelength combinations were identified using linear discriminant analysis for internal defect detection. The hyperspectral imaging technique can be used for simultaneous detection of color, size, and internal defect on pickling cucumbers.     

Evaluation of internal defect and surface color of whole pickles using hyperspectral imaging

Hyperspectral imaging operated under simultaneous reflectance (400–675 nm) and transmittance (675–1000 nm) modes was studied for non-destructive and non-contact sensing of surface color and bloater damage in whole pickles. Good and defective pickles were collected from a commercial pickle processing plant. Hyperspectral images of these pickles were obtained using a prototype of on-line hyperspectral imaging system, operating in the wavelength range of 400–1000 nm. Principal component analysis was applied to the hyperspectral images of the pickle samples for bloater damage detection. Color of the pickles was modeled using tristimulus values calculated based on the hyperspectral images. There were no differences in chroma and hue angle of good and defective pickles. The average chroma of good and defective pickles was 15.5 and 15.0, respectively, and the hue angle 94.0° and 93.8°, respectively. Transmittance images at 675–1000 nm were much more effective for internal defect detection compared to reflectance images for the visible region of 500–675 nm. An overall defect classification accuracy of 86% was achieved, compared with an accuracy of 70% by the human inspectors. With further improvement, the hyperspectral imaging system could meet the need of bloated pickles detection in a commercial plant setting.     

Hyperspectral Imaging-Based Classification and Wavebands Selection for Internal Defect Detection of Pickling Cucumbers

Hyperspectral imaging is useful for detecting internal defects of pickling cucumbers. The technique, however, is not yet suitable for high-speed online implementation due to the challenges in analyzing large-scale hyperspectral images. This research aimed to select the optimal wavebands from the hyperspectral image data, so that they can be deployed in either a hyperspectral or multispectral imaging-based inspection system for the automatic detection of internal defects of pickling cucumbers. Hyperspectral reflectance (400–700 nm) and transmittance (700–1,000 nm) images were acquired, using an in-house developed hyperspectral imaging system running at two conveyor speeds of 85 and 165 mm/s, for 300 “Journey” pickling cucumbers before and after internal damage was induced by mechanical load. Minimum redundancy–maximum relevance (MRMR) was used for optimal wavebands selection, and the loadings of principal component analysis (PCA) were also applied for qualitatively identifying the important wavebands that are related to the specific features. Discriminant analysis with Mahalanobis distance classifier was performed for the two-class (i.e., normal and defective) and three-class (i.e., normal, slightly defective, and severely defective) classifications using the mean spectra and textural features (energy and variance) from the regions of interest in the spectral images at selected waveband ratios. The classification results based on MRMR wavebands selection were generally better than those from PCA-based classifications. The two-band ratio of 887/837 nm from MRMR gave the best overall classification results, with the accuracy of 95.1 and 94.2 % at the conveyor speeds of 85 and 165 mm/s, respectively, for the two-class classification. The highest classification accuracies for the three-class classification based on the optimal two-band ratio of 887/837 nm were 82.8 and 81.3 % at the conveyor speeds of 85 and 165 mm/s, respectively. The mean spectra-based classification achieved better results than the textural feature-based classification, except in the three-class classification for the higher conveyor speed. The overall classification accuracies for all selected waveband ratios at the low conveyor speed were slightly higher than those at the higher conveyor speed, since the low speed resulted in more scan lines, thus higher spatial resolution hyperspectral images. The identified two-band ratio of 887/837 nm in transmittance mode could be applied for fast real-time internal defect detection of pickling cucumbers.     

Optical absorption and scattering properties of normal and defective pickling cucumbers for 700�C1000?nm

An effective optical inspection system for detecting defective pickling cucumbers is needed to help the pickle industry deliver consistent pickled products to the consumer. This research was intended to measure the optical absorption and scattering properties of normal and internally defective pickling cucumbers, using hyperspectral imaging-based spatially-resolved technique. Spatially-resolved hyperspectral scattering images were acquired from 50 freshly harvested ‘Journey’ pickling cucumbers in the summer of 2008 before they were subjected to rolling under mechanical load to induce internal damage. The damaged cucumbers were imaged 1 h and 1 day after the mechanical stress treatment. Spectra of the absorption and reduced scattering coefficients for pickling cucumbers were extracted from the spatially-resolved scattering profiles, using an inverse algorithm for a diffusion theory model, for the spectral range of 700–1000 nm. It was found that within 1 h after mechanical damage, changes in the absorption and reduced scattering coefficients for the cucumbers were minimal. One day after mechanical damage, the absorption coefficient for the cucumbers increased significantly (at 5–10% level) for the wavelengths of 700–920 nm, whereas the reduced scattering coefficient decreased significantly for the wavelengths of 700–1000 nm (at 10% level). Overall mechanical damage caused greater changes in absolute value to the scattering properties than to the absorption properties. This research suggests that effective defect detection can be achieved by enhancing scattering characteristics measurement in the optical evaluation of pickling cucumbers.     

Determining optimal wavebands using genetic algorithm for detection of internal insect infestation in tart cherry

This paper reports the results of waveband selection for detecting internal insect infestation in tart cherries as a precursor to development of a dedicated multispectral vision system. A genetic algorithm (GA) approach was applied on hyperspectral transmittance images (580–980 nm) and reflectance spectral data (590–1,550 nm) acquired from both intact and infested tart cherries. The GA analysis indicates that the ability of using transmittance imaging approach for detecting internal insect infestation in tart cherries would be limited. According to the GA analysis on the reflectance spectra, visible wavelengths were of less importance than NIR wavelengths for the purpose of distinguishing intact cherries from infested ones. The PLSDA results indicate that models built with three or four GA selected wavelength regions gave similar classification accuracy to the model built with full wavelength region, which demonstrates the efficiency of the GA variable selection procedure. However, due to the stochastic nature of the GA, the efficiency of using these wavebands in a multispectral vision system needs to be verified in future work.     

高光谱图像对白萝卜糠心的无损检测

为实现白萝卜异常品质糠心的无损检测,构建高光谱图像技术检测白萝卜糠心的检测系统。获取了光源透射、反射和半透射模式下白萝卜的高光谱图像信息,结合偏最小二乘分析（partial least squares discriminantanalysis,PLS-DA）、支持向量机（support vector machine,SVM）、人工神经网络（artificial neural network,ANN）3 种算法分别建立白萝卜糠心的识别模型。结果表明：3 种检测模式中,基于透射模式的高光谱图像系统检测准确率最高;3 种预测模型中,ANN模型优于PLS-DA和SVM模型。其中,基于透射模式的ANN模型,高光谱图像对萝卜糠心的检测总体准确率达94.3%,效果最好。因此,采用透射模式的高光谱图像技术对白萝卜糠心的检测是可行的。     

Prediction of firmness and soluble solids content of blueberries using hyperspectral reflectance imaging

Currently, blueberries are inspected and sorted by color, size and/or firmness (or softness) in packing houses, using different inspection techniques like machine vision and mechanical vibration or impact. A new inspection technique is needed for effectively assessing both external features and internal quality attributes of individual blueberries. This paper reports on the use of hyperspectral imaging technique for predicting the firmness and soluble solids content (SSC) of blueberries. A pushbroom hyperspectral imaging system was used to acquire hyperspectral reflectance images from 302 blueberries in two fruit orientations (i.e., stem and calyx ends) for the spectral region of 500–1000 nm. Mean spectra were extracted from the regions of interest for the hyperspectral images of each blueberry. Prediction models were developed based on partial least squares method using cross validation and were externally tested with 25% of the samples. Better firmness predictions (R = 0.87) were obtained, compared to SSC predictions (R = 0.79). Fruit orientation had no or insignificant effect on the firmness and SSC predictions. Further analysis showed that blueberries could be sorted into two classes of firmness. This research has demonstrated the feasibility of implementing hyperspectral imaging technique for sorting blueberries for firmness and possibly SSC to enhance the product quality and marketability.     

Citrus canker detection using hyperspectral reflectance imaging and PCA-based image classification method

Citrus canker is one of the most devastating diseases that threaten marketability of citrus crops. Technologies that can efficiently identify citrus canker would assure fruit quality and safety and enhance the competitiveness and profitability of the citrus industry. This research was aimed to investigate the potential of using hyperspectral imaging technique for detecting canker lesions on citrus fruit. A portable hyperspectral imaging system consisting of an automatic sample handling unit, a light source, and a hyperspectral imaging unit was developed for citrus canker detection. The imaging system was used to acquire reflectance images from citrus samples in the wavelength range between 400 and 900 nm. Ruby Red grapefruits with normal and various diseased skin conditions including canker, copper burn, greasy spot, wind scar, cake melanose, and specular melanose were tested. Hyperspectral reflectance images were analyzed using principal component analysis (PCA) to compress the 3-D hyperspectral image data and extract useful image features that could be used to discriminate cankerous samples from normal and other diseased samples. Image processing and classification algorithms were developed based upon the transformed images of PCA. The overall accuracy for canker detection was 92.7%. Four optimal wavelengths (553, 677, 718, and 858 nm) were identified in visible and short-wavelength near-infrared region that could be adopted by a future multispectral imaging solution for detecting citrus canker on a sorting machine. This research demonstrated that hyperspectral imaging technique could be used for discriminating citrus canker from other confounding diseases.     

Embedded bone fragment detection in chicken fillets using transmittance image enhancement and hyperspectral reflectance imaging

This paper is concerned with the detection of bone fragments embedded in compressed de-boned skinless chicken breast fillets by enhancing single-band transmittance images generated by back-lighting and exploiting spectral information from hyperspectral reflectance images. Optical imaging of chicken fillets is often dominated by multiple scattering properties of the fillets. Thus, resulting images from multiple scattering are diffused, scattered and low contrast. In this study, a fusion of hyperspectral transmittance and reflectance imaging, which is a non-ionized and non-destructive imaging modality, was investigated as an alternative method to the conventional transmittance X-ray imaging technique which is an ionizing imaging modality. An image formation model, called an illumination–transmittance model, was applied for correcting non-uniform illumination effects so that embedded bones are more easily detectable by a simple segmentation method using a single threshold value. Predicted bones from the segmentation were classified by the nearest neighbor classifier that was trained by the spectral library of mean reflectance of chicken tissues like fat, meat and embedded bones. Experimental results with chicken breast fillets and bone fragments are provided.     

The effect of controlled atmosphere storage on pickle production from pickling cucumbers cv. ‘Troy’

Fresh pickling cucumbers (cv. Troy) were stored for 30 days at 7°C and 90–95% relative humidity (RH) under different controlled atmosphere (CA) combinations, and samples taken at 0 (i.e., without storage), 10, 20 and 30 days of storage were processed to sweet pickle. At each sampling, physical and chemical analyses were carried out in the fresh pickling cucumbers to determine the changes in the quality with storage time. Besides, physical, chemical and sensory analyses were carried out in the pickles elaborated from the fresh samples taken at the same periods, after keeping at room temperature for 6 months, with the aim of determining CA and storage time effect on the final pickle quality. It was found that storage of cucumbers to be processed to pickle could be possible for less than 10 days at 7°C temperature and 90–95 RH under normal atmosphere (NA). However, physical and chemical analyses showed that storage period of fresh pickling cucumbers could be prolonged up to 30 days under the same storage conditions, if suitable atmosphere combinations are created. Nevertheless, it was concluded that restricting the storage period of fresh pickling cucumbers to 20 days could give better results after processing to pickle. An erratum to this article can be found at     

Development of a portable hyperspectral imaging system for monitoring the efficacy of sanitation procedures in food processing facilities

Cleaning and sanitation in food processing facilities is a critical step in reducing the risk of transfer of pathogenic organisms to food consumed by the public. Current methods to check the effectiveness of sanitation procedures rely on visual observation and sub-sampling tests such as ATP bioluminescence assays and culturing methods. To augment existing verification methods, a hand-held visible hyperspectral imaging device was developed. The device is capable of acquiring reflectance images using ambient lighting, and fluorescence responses to supplemental violet (405 nm) excitation. To enhance the ability of detecting relatively low intensity fluorescence responses in the presence of ambient lighting, the device includes the ability to identify wavebands where the intensity of ambient lighting is relatively low. Valleys in ambient illumination intensity when using fluorescent lighting were found at around 475, 520, 570, and 675 nm. A principal goal is to acquire data to support development of a commercially-viable, hand-held, imaging system.     

Effects of Fruit Size on Fresh Cucumber Composition and the Chemical and Physical Consequences of Fermentation

ABSTRACT: The composition of pickling cucumbers varied with fruit size, which affected buffer capacity, sugar utilization, terminal pH, and texture of the fermented fruit. We found that as cucumber size increased (from less than 27 to 51 mm in dia), malic acid, pH, buffer capacity, and dry matter content decreased, and glucose and fructose contents increased. Fruit firmness and bloater damage were greater in large than in small, fermented, whole cucumbers. Blanching (75 °C, 30 s) had little effect on the fermentation and prevention of bloater formation in finished products, regardless of fruit sizes. It was demonstrated that cucumber juice can serve as a model system for studying the metabolic, but not the physical (texture, bloater damage), consequences of lactic acid bacteria chosen as starter cultures for cucumber fermentation.     

Visible to SWIR hyperspectral imaging for produce safety and quality evaluation

Hyperspectral imaging techniques, combining the advantages of spectroscopy and imaging, have found wider use in food quality and safety evaluation applications during the past decade. In light of the prevalent use of hyperspectral imaging techniques in the visible to near-infrared (VNIR: 400–1,000 nm) for agro-food evaluations, seldom reported are the instrument artifacts that may affect the quality of image data. Furthermore, hyperspectral-based research has focused on the development of image processing and detection aspects with minimal attention given to illustrating the underlying value of imaging with sufficient spatial resolution in the regions spanning from the visible to short-wavelength infrared (SWIR: 1,000–1,700). We have developed multiple generations of line-scan based hyperspectral imaging systems and expanded the imaging capabilities in the SWIR. With the use of our most recently developed VNIR and SWIR hyperspectral imaging systems, spectral and spatial attributes of apples with defects from 400 to 1,700 nm are presented. In addition, we characterize the second-order effect in the 800–1,000 nm range that emanates from the use of a diffraction grating in the VNIR hyperspectral imaging system. We have devised methods to perform SWIR spectral calibration and to remove the bad pixels inherent to the SWIR InGaAs focal plane array used in the imaging system. We envision that hyperspectral imaging techniques will continue to play a significant role in the agro-food sector as critical research tools, and in further applications for rapid inspection of produce safety and quality.     

INFLUENCE OF GROWING ENVIRONMENT AND STORAGE DURATION ON QUALITY OF FRESH-PACK CUCUMBER PICKLES3

Fruit of several pickling cucumbers (Cucumis sativus L.) grown in 1978 and 1979 in several environments under two soil nitrogen levels (high vs. normal) were stored for various time periods before fresh-pack processing. Firmness, color and general appearance as examined after equilibration were all highly affected by cultivar, growing environment, and storage duration but somewhat less by nitrogen level. Unexpectedly, color and appearance improved during the first 24 h after harvest. Acceptable firmness was maintained for at least 72 h after harvest. Fruit of genetically firm cultivars generally showed less change in firmness than did fruit of less firm cultivars.     

用光谱成像技术与分光光度法测量织物颜色的比较分析

针对分光光度法与光谱成像技术测量相同织物颜色结果存在差异的问题,选用Datacolor 600型分光光度计、Datacolor Spectravision多光谱成像系统和HIS高光谱成像系统,分别对同一套单色全棉针织物进行测量,探讨了3种仪器测得的颜色参数和光谱反射率差异的原因及规律。通过计算不同仪器间的色差和指数光谱相似性,采用皮尔逊相关系数进行数据分析。研究结果表明,HIS高光谱成像系统重复性好,重复测量的平均色差为0.154;3种仪器测得的光谱反射率具有强相似性;相较于Spectravision多光谱成像系统,HIS高光谱成像系统的颜色结果更接近于分光光度计;Spectravision多光谱成像系统的有效像元尺寸更小,织物纹理对颜色结果影响较大,Spectravision多光谱成像系统测量的明度偏低;HIS高光谱成像系统的有效像元大小与相机工作距离成正比,适用范围更广。     

Viability of commercial cucumber fermentation without nitrogen or air purging

BackgroundBloated cucumber defect, resulting from the accumulation of the biologically produced carbon dioxide (CO₂) in the fruit, reduces yield and economic gains for the pickling industry worldwide. It was the aim of this review to identify commonalities among effective strategies to reduce bloater defect and determine the theoretical viability of commercial cucumber fermentations without bloater defect and/or purging.Scope and approachThis article summarizes the known causes of fermented cucumber bloating defect, including sources of CO₂, and the strategies developed to mitigate the production of the carbonic gas such as controlled fermentation, inoculation of selected starter cultures, cover brine acidification and reformulation and the application of air or nitrogen purging.Key findings and conclusionsIt was understood that microbial activity during fermentation, cucumber tissue respiration, as well as the pressure in the fruits and fermentation tanks, ambient temperature and cover brine composition, impact the levels of dissolved CO₂ in the system. Although the biological conversion of oxygen to CO₂ reduces the cucumbers internal gas pressure, the dissipation of the gas from the tissue is reduced by brining. Once the gas accumulates in the cucumber tissue in concentrations high enough to displace it, the irreversible formation of hollow cavities or bloaters occurs. Residual CO₂ is produced by acid-preserved cucumbers, presumably by tissue respiration, which results in the absence of bloating. Thus, microbial activity seems to contribute most of the CO₂ needed for cucumbers to bloat. It is speculated that colonization of the internal cucumber tissue by indigenous microbes, in particular aerobic gram-negative bacteria, results in the localized production of CO₂ causing bloating defect early in the fermentation. It is concluded that effective manipulation of the microbiota, reduction of dissolved oxygen levels and the use of adequately selected starter cultures may enable cucumber fermentations of acceptable quality without purging.     

Application of near infrared spectroscopy to peanut grading and quality analysis: overview

Techniques using near infrared (NIR) spectroscopy for quality measurements are becoming more popular in food processing and quality inspection of agricultural commodities. NIR spectroscopy has several advantages over conventional physical and chemical analytical methods of food quality analysis. It is a rapid and non destructive method and provides more information about the components and its structure present in the food products. It can measure more than one parameter simultaneously. The NIR spectrum includes wavelengths from 750 to 3000 nm that follow immediately after the visible region (400–700 nm). Many organic compounds can be well-defined by NIR reflectance, transmittance or diffuse reflectance system. This paper reviews the application of NIR spectroscopy to several oil seeds and examines the feasibility of using this technique for peanut quality analysis. The NIR spectroscopic instrumentation has been explained briefly for a better understanding. Also needs and limitations in use of NIR spectroscopy for peanut quality analysis and grading were explained.     

TEXTURE OF FRESH-PACK WHOLE CUCUMBER PICKLES: CORRELATION OF INSTRUMENTAL AND SENSORY MEASUREMENTS*

Correlations were determined between Texture Profile Analysis parameters of brittleness, hardness or total work of compression obtained with the Instron testing machine and sensory responses of firmness or crispness in evaluating texture of fresh-pack processed whole cucumbers (1-in. diam) of three ‘firm’ pickling cultivars (Explorer, Chipper, GY 3), two ‘soft’ pickling cultivars (Green F, Mincu) and a parthenocarpic slicer (MSU 6902 G). Further, correlations were determined between the TPA parameters and Magness-Taylor fruit pressure test (FPT) firmness. TPA hardness and total work correlated well with sensory responses; FPT firmness correlated satisfactorily with sensory firmness. Mean textural values from the various methods were compared with those obtained in the same manner for raw cucumbers. TPA brittleness tended to disappear in the processed fruit. Processing reduced mean TPA values across the six varieties to 35-58% of raw fruit values; it decreased mean FPT firmness to only 88%.     

利用反射和半透射高光谱图像检测水蜜桃早期冷害

研究了应用高光谱图像技术检测‘霞晖5号’水蜜桃早期冷害的方法。通过分析桃果实采后贮藏期间出汁率的变化,确定冷害发生的初始时间。进而针对早期冷害桃果实的400～1 000 nm波段的高光谱反射和半透射图像,应用独立主成分分析方法优选出冷害的特征波长,反射条件下为656、674 nm和704 nm,半透射条件下为640、745 nm和811 nm,并通过提取每个特征波长下的光谱平均值作为Fisher判别方法建模的特征集,所建水蜜桃早期冷害判别模型的预测准确率分别为83.0%和94.0%。结果表明,高光谱技术可以检测桃果实早期冷害,且半透射照射方式的判别结果优于反射方式。     

Identification of wheat classes at different moisture levels using near-infrared hyperspectral images of bulk samples

Wheat classes at different moisture levels need to be identified to accurately segregate, properly dry, and safely store before processing. This paper introduces a new method using a near infrared (NIR) hyperspectral imaging system (960–1,700 nm) to identify five western Canadian wheat classes (Canada Western Red Spring (CWRS), Canada Western Extra Strong (CWES), Canada Western Red Winter (CWRW), Canada Western Soft White Spring (CWSWS), and Canada Western Hard White Spring (CWHWS)) and moisture levels, independent of each other. The objectives of this research also included identification of each wheat class at specific moisture levels of 12, 14, 16, 18, and 20%. Bulk samples of wheat were scanned in the 960–1,700 nm wavelength region at 10 nm intervals using an Indium Gallium Arsenide (InGaAs) NIR camera. Spectral feature data sets were developed by calculating relative reflectance intensities of the scanned images. Principal components analysis was used to generate scores images and loadings plots. The NIR wavelengths in the region of 1,260–1,360 nm were important based on the loadings plot of first principal component. In statistical classification, the linear and quadratic discriminant analyses were used to classify wheat classes giving accuracies of 61–97 and 82–99%, respectively, independent of moisture contents. It was also found that the linear discriminant analysis (LDA) and quadratic discriminant analysis (QDA) could classify moisture contents with classification accuracies of 89–91 and 91–99%, respectively, independent of wheat classes. Once wheat classes were identified, classification accuracies of 90–100 and 72–99% were observed using LDA and QDA, respectively, when identifying specific moisture levels. Spectral features at key wavelengths of 1,060, 1,090, 1,340, and 1,450 nm were ranked at top in classifying wheat classes with different moisture contents. This work shows that hyperspectral imaging techniques can be used for rapidly identifying the wheat classes even at varying moisture levels.