Apple Bruise Research Articles

The Development of Mechanical Apple Harvesting Technology: A Review

Harvest is one of the most challenging production tasks in apple production. It is a labor-intensive operation, and mechanization has been slow in development for a myriad of reasons. With increasing labor costs and decreasing availability of harvest employees, researchers have been focusing on mechanical apple harvest technologies. Studies on semi-automatic harvesters, harvest robots, and harvest-assist platforms target development of mechanical apple harvesting. Semi-automatic harvesters for fresh market apples have not been commercialized due to unacceptably high incidence of apple bruising. Harvest robots have not been commercialized due to their high costs and low efficiency. Apple harvest-assist platforms are a technology that has the potential to be more widely commercialized based on the current research.

Fast demodulation of pattern images by spiral phase transform in structured-illumination reflectance imaging for detection of bruises in apples

A structured-illumination reflectance imaging (SIRI) system was recently developed in our laboratory for enhanced quality evaluation of horticultural products. It was implemented using a digital camera to acquire reflectance images from food products subjected to sinusoidal patterns of illumination, instead of conventional diffuse or uniform illumination. The reconstruction of amplitude images is a key step in implementing SIRI technique. Conventional methods require acquisition and subsequent demodulation of three phase-shifted pattern images, which limits the speed of image acquisition. This study proposed the use of spiral phase transform (SPT) for demodulation of pattern images acquired by SIRI. Three SPT-based methods involving only one or two images were investigated through numerical simulation, followed with experiments on the detection of fresh bruises in apples. Compared to conventional three-phase based and two-phase based Gram-Schmidt (GS) orthonormalization demodulation methods, the two-phase SPT method achieved the same or even higher demodulation accuracy, which applies to two pattern images that can be arbitrarily phase-shifted. SPT also allowed single-image based demodulation, although its performance still needs to be improved. This study demonstrated that SPT for amplitude demodulation can increase the imaging speed of SIRI by using one or two pattern images, which is a significant step towards real-time implementation of the technique.

Non-destructive detection of blackspot in potatoes by Vis-NIR and SWIR hyperspectral imaging

Blackspot is a subsurface potato damage resulting from impacts during harvesting. This type of bruising represents substantial economic losses every year. As the tubers do not show external symptoms, bruise detection in potatoes is not straightforward. Therefore, a nondestructive and accurate method capable of identifying bruised tubers is needed. Hyperspectral imaging (HSI) has been shown to be able to detect other subsurface defects such as bruises in apples. This method is nondestructive, fast and can be fully automated. Therefore, its potential for non-destructive detection of blackspot in potatoes has been investigated in this study. Two HSI setups were used, one ranging from 400 to 1000 nm, named Visible-Near Infrared (Vis-NIR) and another covering the 1000–2500 nm range, called Short Wave Infrared (SWIR). 188 samples belonging to 3 different varieties were divided in two groups. Bruises were manually induced and samples were analyzed 1, 5, 9 and 24 h after bruising. PCA, SIMCA and PLS-DA were used to build classifiers. The PLS-DA model performed better than SIMCA, achieving an overall correct classification rate above 94% for both hyperspectral setups. Furthermore, more accurate results were obtained with the SWIR setup at the tuber level (98.56 vs. 95.46% CC), allowing the identification of early bruises within 5 h after bruising. Moreover, the pixel based PLS- DA model achieved better results in the SWIR setup in terms of correctly classified samples (93.71 vs. 90.82% CC) suggesting that it is possible to detect blackspot areas in each potato tuber with high accuracy.

Susceptibility of apples to bruising inside ventilated corrugated paperboard packages during simulated transport damage

The incidence of fruit postharvest losses and waste due to mechanical damage during handling is a major problem in the fresh produce industry Among the various range of force loading conditions experienced during handling and transportation, vibration is one of the key factors which may result in fruit bruise damage and the type of package used during handling of fruit could significantly affect the physical quality of the fruit. A simulated transport study was used to assess the susceptibility of apple fruit inside two ventilated corrugated paperboard (VCP) packages (MK4 and MK6) commonly used in fresh produce industry for packing apple fruit. An electro-dynamic shaker was used to excite vibrations at three frequencies (9, 12 and 15Hz) and 0.9g amplitude for four hours, which is usually adopted for truck transport simulation. Packaging transmissibility and incidence of bruise damage were measured at different frequencies. Results showed that both the incidence and severity of apple bruising were affected by package design and frequency. For both package designs at the three vibration frequencies investigated, packaging transmissibility ranged from 100 to 250%, with the highest transmissibility observed on the MK6 package with a lower length–to–height ratio at 12Hz compared to the MK4 package. Apple fruit inside the MK4 package with higher length–to–height ratio had less damage than fruit inside the MK6 package. Irrespective of the package design, apple fruit on the top layer were more susceptible to bruising and the range of the proportion of bruised apples was between 50 and 74% at all the three frequencies, which are rather extreme conditions that usually occur when loads of packed fruit damage during transport.

Structured-illumination reflectance imaging (SIRI) for enhanced detection of fresh bruises in apples

A structured-illumination reflectance imaging (SIRI) system was developed for the detection of fresh bruises in apples. The system consisted of a high-performance digital camera, a broadband DC-regulated light source, and a digital light engine for generating specific patterns of illumination. Sinusoidal patterns of illumination at a series of spatial frequencies were created to illuminate test samples. Experiments were first conducted on a strongly scattering nylon sample embedded with foreign objects at different depths and then on apples of three cultivars with fresh bruises. The acquired images were demodulated into two separate sets of direct component (representing uniform diffuse illumination) and alternating component (or amplitude) images for each spatial frequency. The amplitude images were found to be effective for ascertaining the sub-surface defects, and the detection resolution and depth depended on the spatial frequency of illumination. SIRI technique was able to detect fresh bruises in apples immediately after they were induced, which, otherwise, could be difficult to achieve by conventional uniform illumination-based imaging techniques. The technique is promising for effective detection of defects, like bruise, in fruit.

Real-time pixel based early apple bruise detection using short wave infrared hyperspectral imaging in combination with calibration and glare correction techniques

High speed data processing for online food quality inspection using hyperspectral imaging (HSI) is challenging as over hundred spectral images have to be analyzed simultaneously. In this study, a real-time pixel based early apple bruise detection system based on HSI in the shortwave infrared (SWIR) range has been developed. This systems consists of a novel, homogeneous SWIR illumination unit and a line scan camera. The system performance was tested on Jonagold apples bruised less than two hours before scanning. Partial least squares-discriminant analysis was used to discriminate bruised pixel spectra from sound pixel spectra. As the glossiness of many fruit and vegetables limits the accuracy in the detection of defects, several reflectance calibrations and pre-processing techniques were compared for glare correction and maximizing the signal to noise ratio. With the best combination of first derivative and mean centering, followed by image post-processing, this system was able to detect fresh bruises in thirty apples with 98% accuracy at the pixel level with a processing time per apple below 200 ms.

Quantity assessment of plastic deformation energy under impact loading conditions of selected apple cultivars

This paper presents a new method for plastic deformation energy calculation under impact loading conditions. It consisted in determination of the difference between the values of the absorbed energy from both force-deformation course and the formulae for kinetic energy before and after the impact. Using a high speed camera and a piezoelectric force sensor as two independent measuring systems made it possible. This enabled direct recording of deformation and force response during the apple impact against a rigid, flat surface. For the tested cultivars the increasing relationship between the plastic deformation energy and the impact velocity was obtained. The coefficient of restitution was an appropriate parameter which allowed to determine the initial apple bruising. The increase of apple bruise susceptibility with the increasing impact velocity was also found.

Low cost measurement setup based on a piezoelectric microphone for estimating apple bruising using Shannon entropy

This study presents a low cost measurement setup for estimating apple bruise volume during drop impact tests. The proposed measurement system consists of three main stages namely recording impact sound, signal processing, and estimating bruise volume. In the recording stage, the impact sound occurred when striking the apple on the surface was recorded by a piezoelectric microphone into computer. The impact sound was converted into Shannon entropy signals based on the Kernel density approach, and two measurable quantities namely entropy peak and pulse-width time were extracted from Shannon entropy signals in the signal processing stage. In the bruise volume estimating stage, the regression curves that map entropy peak and pulse-width features into bruise volume are estimated using measurements data. To evaluate the performance of the proposed method, we conducted several drop experiments with six different drop heights and two different temperatures (1 and 19°C). Experimental results showed that bruise volume was exponentially proportional to the entropy peak and it was inversely proportional to pulse-width time as power functions, and all the curves were fitted with coefficients of determination of more than 0.98. Moreover, it was found that colder apples developed less bruise volume then warmer ones.

Quantifying the Diffuse Reflectance Change Caused by Fresh Bruises on Apples

<abstract><title><italic>Abstract.</italic></title> The effect of recent impacts (less than 5 min old) on the light diffusely reflected from the surface of eleven apple cultivars was investigated under carefully controlled conditions. Although such fresh damage shows little of the browning typically associated with bruises, near-infrared measurements between 700 and 1100 nm could non-destructively distinguish between sound and damaged tissue. The largest change in reflectance occurred at 970 nm; following impacts of between 40 and 360 mJ, the reflectance from damaged tissue was about 8% less (median) than from sound tissue at 970 nm. Although cultivar made a small but significant (99.9% confidence) contribution to the observed change in reflectance, clear discrimination between sound and bruised tissue was possible for all cultivars studied. These results will aid design of instruments and algorithms for rapid identification of fresh bruises in apples to contain and ameliorate handling and grading problems.

Supervised classification of bruised apples with respect to the time after bruising on the basis of hyperspectral imaging data

Apple bruising, as a mechanical damage, occurs due to impact, compression, vibration or abrasion during handling. However, the symptoms of this damage, browning and softening of the tissue, appear not immediately but after a certain period of time after bruising. For sorting and grading systems, the information about how long the bruise exists in affected fruit can be valuable. VNIR (visible and near-infrared) and SWIR (short wavelength infrared) spectral characteristics of sound and bruised apple tissues were analyzed during a two week period after bruising. Supervised classification methods, including support vector machines, linear logistic regression, neural networks and decision trees, were used and compared to check their effectiveness for distinguishing time after bruising with respect to five varieties of apples. The detection system included hyperspectral cameras equipped with sensors working in the visible and near-infrared (400–1000nm) and short wavelength infrared (1000–2500nm) ranges. The results of supervised classification revealed good applicability of hyperspectral imaging in VNIR and SWIR spectral ranges for detecting the number of days after bruising. The linear logistic regression neural networks models were found to be the best classifiers in the majority of models developed. Prediction accuracies higher than 90% were obtained for classification models on spectral data pretreated with the second derivative.

The effect of drop height on bruising of selected apple varieties

This paper presents an analysis of fruit impact in time and the results of the relationships between the bruise size and various impact parameters. The measuring device allows simultaneously analysis of the three basic quantities: impact velocity, rebound velocity and force response in time, and testing the momentum conservation law for a body such as an apple. In the experiments, the impact velocity 0.25ms−1 was the maximum velocity at which bruises for all tested apple varieties did not develop. The parameters which were the most strongly correlated with apple bruise volume were maximum force response and dissipated energy, which can be used to predict direct impact effects.

Predictions of apple bruise volume using artificial neural network

Bruise damage is a major cause of fruit quality loss. Bruises occur under dynamic and static loading when stress induced in the fruit exceeds the failure stress of the fruit tissue. In this article the potential of an artificial neural network (ANN) technique has evaluated as an alternative method for the prediction of apple bruise volume. Neural bruise estimation models were constructed to calculate Golden Delicious apple bruise volume with respect to fruit properties. The neural models were built based upon impact force and impact energy as the main input parameters including fruit curvature radius, temperature and acoustical stiffness. Optimal parameters for the network were selected via a trial and error procedure on the available data. In this paper, the performance of Basic Backpropagation (BB) training algorithm was also compared with Backpropagation with Declining Learning Rate Factor algorithm (BDLRF). It was found that BDLRF has a better performance for the prediction of apple bruise volume. It is concluded that ANN represents a promising tool for predicting apple bruise volume in comparison to regression model.

Detection of early bruises in apples using hyperspectral data and thermal imaging

The early detection of bruises in apples was studied using a system that included hyperspectral cameras equipped with sensors working in the visible and near-infrared (400–1000nm), short wavelength infrared (1000–2500nm) and thermal imaging camera in mid-wavelength infrared (3500–5000nm) ranges. The principal components analysis (PCA) and minimum noise fraction (MNF) analyses of the images that were captured in particular ranges made it possible to distinguish between areas with defects in the tissue and the sound ones. The fast Fourier analysis of the image sequences after pulse heating of the fruit surface provided additional information not only about the position of the area of damaged tissue but also about its depth. The comparison of the results obtained with supervised classification methods, including soft independent modelling of class analogy (SIMCA), linear discriminant analysis (LDA) and support vector machines (SVM) confirmed that broad spectrum range (400–5000nm) of fruit surface imaging can improve the detection of early bruises with varying depths.

COMPARISON OF 'CRIPPS PINK' APPLE BRUISING

ISHS International Symposium Postharvest Pacifica 2009 - Pathways to Quality: V International Symposium on Managing Quality in Chains + Australasian Postharvest Horticultural Conference COMPARISON OF 'CRIPPS PINK' APPLE BRUISING

Effect of Impact Level and Fruit Properties on Golden Delicious Apple Bruising

Problem statement: Bruise damage is a major cause of fruit quality lo ss. Bruises occur under dynamic and static loading when stress induce d in the fruit exceeds the failure stress of the fr uit tissue. Statistical bruise estimation models were c onstructed to calculate Golden Delicious apple brui se volume with respect to fruit properties. Approach: The regression models were built based upon impact force and impact energy as main independent variable with other parameters including fruit curvature radius, temperature and acoustical stiffn ess. An instrumented pendulum was constructed as a tool to perform three levels of controlled impact o n apple fruit. Results: Significant effects of acoustical stiffness, temperature and the curvature radius and some interactions on bruising were obtained at 5% probability level with the coefficie nt of determination of 0.93 and 0.98 for force mode l and energy model respectively. Conclusion: It was demonstrated that increasing the temperatur e and curvature radius and lowering acoustical stiffness will reduce the bruise damage of the golden delicious apple fruit.

Bruising Profile of Fresh Apples Associated with Tissue Type and Structure

Bruising of apples results in millions of dollars in loss annually. To reduce economic loss, a greater understanding of the mechanisms involved is necessary. Our objective was to visualize damage due to bruising, using different methods of microscopy, as an aid to substantiating which mechanisms were most viable. 'Golden Delicious' apples at different maturity levels were similarly bruised with an artificial silicon finger attached to an Instron machine. Bruising was induced on freshly harvested fruit and examined after 48 h at room temperature. We used fluorescence microscopy with Calcofluor (to identify cell walls) and CDFA (to identify intact cell membranes) in the bruised and discolored tissue. Together with scanning electron microscopy (SEM), different breakage mechanisms were observed in the bruised volume. These techniques revealed that bruised tissue was comprised of both live cells, and dead cells that appeared burst, crushed or without apparent damage. The greater the amount of intercellular space present in the tissue, the more tissue damage from bruising occurred. Because airspaces weakened the tissue, damage initiated close to these sites. As apples matured, there was an increase in damaged cells surrounding larger intercellular spaces.

Measurement of impact pressure and bruising of apple fruit using pressure-sensitive film technique

Impact pressure and bruising of apple fruit were measured by means of a pressure-sensitive film technique, in order to develop methods for assessing and predicting bruising of apples resulting from impact loads during the course of transport and handling. Results of impact tests with apples indicate that when the fruits are dropped from different heights onto different impacting surfaces, the bruise area and volume could be assessed and predicted by regression models based on the impact force obtained from the pressure-sensitive film ( F PSF). The coefficients of determination ( R 2) for bruise area and bruise volume were found to be 0.91 and 0.95, respectively.

Detection of early apple bruises using pulsed-phase thermography

The study is based on a hypothesis that internal defects and physiological disorders of fruit lead to changes in tissue thermal properties. During thermal stimulation, heterogeneities of thermal properties lead to the occurrence of thermal contrasts on the surface of fruit material, which can be successfully registered with the use of a thermographic device. A method was developed to detect apple bruising early using pulsed-phase thermography (PPT). In PPT the studied object is heated with an individual thermal pulse (most frequently a rectangular pulse) and the temperature decay on the surface is analysed on a pixel-by-pixel basis as a mixture of harmonic waves, thus enabling the computation of phase and amplitude images. The fast Fourier transform was used to obtain ampligrams and phasegrams of fruit heat response to defects occurring at different depths. The automatic segmentation procedure made it possible to select areas of bruised tissue in thermograms. A comparison of PPT results and visual inspection of bruising was performed, indicating high possibilities of the active thermography method for detecting defects up to several millimetres.

The effect of fruit factors on the bruise susceptibility of apples

Bruise prediction models which are essential for the applicability of the discrete element method (DEM) to simulate bruise damage during fruit transport and handling are discussed. Bruise prediction models relate the contact force during impact, as calculated by DEM through contact force models, with the real bruise damage. Apart from DEM, bruise prediction models can provide useful information about the influence of fruit factors (e.g. ripeness) on bruise susceptibility, leading to recommendations for fruit handling. Regression models were built with impact energy or peak contact force as independent variables. Advantages and disadvantages of both models are discussed. Bruise prediction models were constructed for the apple cultivar ‘Jonagold’, with impacts controlled by a pendulum. Multiple linear and nonlinear regression models were built to link fruit factors such as ripeness, acoustic stiffness, fruit temperature, radius of curvature and harvest date, with bruise damage. Bruise volume was used as a measure for apple bruising. Significant main effects and significant interactions between fruit factors were identified. Interactions between fruit factors (e.g. interaction between harvest date and stiffness), along with interactions between fruit factors and the degree of bruising, were identified. Most of the effects of those fruit factors on bruise damage could be explained by applying theoretical bruise models described in the literature.

Development of engineering design tools to help reduce apple bruising

A large percentage of apples are wasted each year due to damage such as bruising. The apple journey from orchard to supermarket is very complex and apples are subjected to a variety of static and dynamic loads that could result in this damage occurring. The main aim of this work was to carry out numerical modelling to develop a design tool that can be used to optimise the design of harvesting and sorting equipment and packaging media to reduce the likelihood of apple bruise formation resulting from impact loads. An experimental study, along with analytical calculations, varying apple drop heights and counterface material properties, were used to provide data to validate the numerical modelling. Good correlation was seen between the models and experiments and this approach combined with previous work on static modelling should provide a comprehensive design tool for reducing the likelihood of apple bruising occurring.