Detection of Chilling Injury in Pickling Cucumbers Using Dual-Band Chlorophyll Fluorescence Imaging

Pickling cucumbers are susceptible to chilling injury (CI) during postharvest refrigerated storage, which would result in quality degradation and economic loss. It is, thus, desirable to remove the defective fruit before they are marketed as fresh products or processed into pickled products. Chlorophyll fluorescence is sensitive to CI in green fruits, because exposure to chilling temperatures can induce detectable alterations in chlorophylls of tissues. This study evaluated the feasibility of using a dual-band chlorophyll fluorescence imaging (CFI) technique for detecting CI-affected pickling cucumbers. Chlorophyll fluorescence images at 675 nm and 750 nm were acquired from pickling cucumbers under the excitation of ultraviolet-blue light. The raw images were processed for vignetting corrections through bi-dimensional empirical mode decomposition and subsequent image reconstruction. The fluorescence images were effective for ascertaining CI-affected tissues, which appeared as dark areas in the images. Support vector machine models were developed for classifying pickling cucumbers into two or three classes using the features extracted from the fluorescence images. Fusing the features of fluorescence images at 675 nm and 750 nm resulted in overall accuracies of 96.9% and 91.2% for two-class (normal and injured) and three-class (normal, mildly and severely injured) classification, respectively, which are statistically significantly better than those obtained using the features at a single wavelength, especially for the three-class classification. Furthermore, a subset of features, selected based on the neighborhood component feature selection technique, achieved the highest accuracies of 97.4% and 91.3% for the two-class and three-class classification, respectively. This study demonstrated that dual-band CFI is an effective modality for CI detection in pickling cucumbers.

siritool: A Matlab Graphical User Interface for Image Analysis in Structured-Illumination Reflectance Imaging for Fruit Defect Detection

HIGHLIGHTSA Matlab GUI, siriTool, was developed for structured-illumination reflectance imaging.siriTool enables image preprocessing, feature extraction, and classification.siriTool was demonstrated for detection of spot defects on pickling cucumbers.Abstract. Structured-illumination reflectance imaging (SIRI) is an emerging imaging modality that provides more useful discriminative features for enhancing detection of defects in fruit and other horticultural and food products. In this study, we developed a Matlab graphical user interface (GUI), siriTool (available at https://codeocean.com/capsule/5699671/tree), to facilitate image analysis in SIRI for fruit defect detection. The GUI enables image preprocessing (i.e., demodulation, object segmentation, and image enhancement), feature extraction and selection, and classification. Demodulation is done using a three-phase or two-phase approach depending on the image data acquired, object segmentation (or background removal) is implemented based on automatic unimodal thresholding, and image enhancement is achieved using fast bi-dimensional empirical decomposition followed by selective image reconstructions. For defect detection, features of different types are extracted from the enhanced images, and feature selection is performed to reduce the feature set. Finally, the full or reduced set of features are then input into different classifiers, e.g., support vector machine (SVM), for image-level classifications. An application example is presented on the detection of yellowish subsurface spot defects in pickling cucumbers. SIRI achieved over 98% classification accuracies based on SVM modeling with the extracted features, which were significantly better than the accuracies obtained under uniform illumination. Keywords: Defect detection, Demodulation, Image enhancement, Machine learning, Matlab, Structured illumination.

Deep Feature Representation with Stacked Sparse Auto-Encoder and Convolutional Neural Network for Hyperspectral Imaging-Based Detection of Cucumber Defects

It is challenging to achieve rapid and accurate processing of large amounts of hyperspectral image data. This research was aimed to develop a novel classification method by employing deep feature representation with the stacked sparse auto-encoder (SSAE) and the SSAE combined with convolutional neural network (CNN-SSAE) learning for hyperspectral imaging-based defect detection of pickling cucumbers. Hyperspectral images of normal and defective pickling cucumbers were acquired using a hyperspectral imaging system running at two conveyor speeds of 85 and 165 mm s-1. An SSAE model was developed to learn the feature representation from the preprocessed data and to perform five-class (normal, watery, split/hollow, shrivel, and surface defect) classification. To deal with a more complicated task for different types of surface defects (i.e., dirt/sand and gouge/rot classes) in six-class classification, a CNN-SSAE system was developed. The results showed that the CNN-SSAE system improved the classification performance, compared with the SSAE, with overall accuracies of 91.1% and 88.3% for six-class classification at the two conveyor speeds. Additionally, the average running time of the CNN-SSAE system for each sample was less than 14 ms, showing considerable potential for application in an automated on-line inspection system for cucumber sorting and grading. Keywords: Convolutional neural network, Defect detection, Hyperspectral imaging, Pickling cucumber, Representation learning, Stacked sparse auto-encoder.

Phosphorus, Potassium and Nitrate Contents in Fruit of Pickling Cucumbers Grown in a High Tunnel

Pickling cucumbers are highly important both for fresh consumption and for canning industry. This study aimed to compare differences in yield and quality of eight pickling cucumber cultivars, including ‘Cor 12004’, ‘IGG 2010’, ‘IGG 2020’, ‘SM 5322’, ‘SM 5323’, ‘Zayin 201’, ‘Zayin 175201’ and ‘Trilogy’. The cucumber cultivars were laid out in a high tunnel crop and evaluated for vegetative traits (i.e. vine length, nodes per vine and branches per vine), yield attributes (i.e. fruits per main stem, average weight of fruit and fruits weight per plant) and fruits quality components (nitrate, phosphate and potassium mg kg-1). The results showed significant differences (P<0.05) in vegetative traits and yield attributes among cultivars. The analysis of correlation coefficients revealed that total yield (kg ha-1) was positively correlated with two out of three vegetative traits (with exception nodes per plant) and with all yield attributes. The highest total yield (101.17 t ha-1) was reached by ‘SM 5322’ cultivar, followed by the ‘IGG 2010’ and ‘SM 5323’ cultivars. The nitrates content in fruits, assessed on three categories of length (6-9 cm, 9-12 cm and >12 cm), revealed a declining value with increase in the cucumber length. The study findings suggest that irrespective of the cultivar, the amount of nitrate was higher in shorter cucumbers (6-9 cm length) although allrecorded values (between 192.7 and 364.3 mg kg-1 fresh matter) being under maximum accepted limit concentrations. The amount of phosphate was higher in medium to long cucumbers, while the amount of potassium was higher in shorter cucumbers.

Multi-Criteria Assessment of Vegetable Production Business Alternatives

Purpose: Organic and integrated production of vegetables are the two most common production systems in Slovenia. The study analyzed two production systems with different cultures as alternatives with purpose to find the most appropriate variants. Design/Methodology/Approach: The study based on the development and integration of developed specific technological- economic simulation models for the production of vegetables (salad, growing peppers, salad cucumbers, pickling cucumbers, round and cherry tomato) in greenhouse and multi-criteria decision analysis. The methodology of the study based on the DEX methodology and the analytical hierarchy process (AHP) of organic (ECO) and integrated production (IP) in greenhouse. Results: The evaluation results show that both cultivation methods of commercially attractive vegetables in greenhouse are variable. In the case of integrated production, the assessment of multi-criteria decision analysis EC and DEXi showed that salad (Donertie F1) proved to be the best possible alternative. In the case of organic production, the multi-criteria analysis assessment of pickling cucumbers (Harmony F1) is the best possible business alternative. Conclusion: For the further production planning process by decision maker is the ranking with Expert Choice (EC) more useful and precise, while the DEX evaluations are more descriptive.