Mahmood Reza Golzarian; Ali Mohammadzadeh; Mohammad Hossein Abaspour fard
Abstract
Introduction: Every year about 600 million tons of fruits and vegetables are produced in Asia and around 35% out of it is wasted during production, postharvest, processing, distribution and consumption (FAO, 2011). In most cases, the sale rate of agricultural products is affected by their internal quality. ...
Read More
Introduction: Every year about 600 million tons of fruits and vegetables are produced in Asia and around 35% out of it is wasted during production, postharvest, processing, distribution and consumption (FAO, 2011). In most cases, the sale rate of agricultural products is affected by their internal quality. Although consumers are unable to detect product’s internal quality and freshness while buying, their negative perceptioncan be formed against their next buy if the internal quality of what they bought does not meet their satisfaction (Leemans et al., 2002). For assessing fruits quality factors some destructive and non-destructive tests are performed. The qualityfactors are categorized into external quality and internal quality factors. With the visual inspection methods, the external features of Bio-materials (e.g. shape, color and texture) can be evaluated (Shiranita et al., 1998) while the internal quality factors, including freshness, cannot be determined from these apparent visual characteristics (Jha et al., 2002). Therefore, the shelf life of agricultural products that are internally defective is less as they perish sooner and the infection expands quicker (Ohali, 2011). Among the common nondestructive methods for assessing internal quality parameters, MRI, X-RAY, Ultrasonic and NMR can be named (Du et al., 2004; Mery et al., 2011). In fruits, vegetables and fruits, the status of freshness is affected by the changes occurred in their physical, chemical and biological structures. These changes and, therefore, freshness, conventionally, is quantified by parameters such as product’s mechanical stress, moisture content, temperature and pH.Recently, some advanced technologies such as thermography have been used in quality assessment of agricultural products. Thermography is performed in two types: active and passive. In passive thermography, the heat emitted from the objects is recorded by the camera while in active thermography, which is more common in post-harvest applications, there is an external energy source to produce a thermal contrast between the sample product and the background. The objectives of this research areto use thermography in order to study the effects of time after harvest on the distribution of arils surface temperature and to relate the thermal properties to the freshness of arils.Materials and methods: Freshly harvested pomegranate fruits of Khazar variety were provided from Kashmar gardens. The arils were extracted from 35 randomly selected fruits. The arils of each fruit were kept for 15 days at 5°C. The arils were thermally and visibly imaged and their physical and mechanical properties were measured every 5 days: first day, fifth day, tenth day and fifteenth day after openingthe fruit to have variations in freshness. The size of thermals images was 320×240 pixels with the temperature resolution of 0.08°C. The images were taken with the emissivity set at 0.95, which was obtained from masking method (using a high-emissivitypatch). This emissivity value was within the range documented for biological products, i.e. 0.93-0.99 (Hellebrand et al., 2006). The thermal images were taken from the arils every 10 seconds for 180 seconds after imposing thermal shock by placing the arils in a freezer compartment at -2°C for 60 seconds. The distance from the thermal camera to the arils was 30cm and the room temperature was 22.5°C. The images were processed and analyzed in Matlab (MathworksInc, US) and the thermal features were extracted from the histogram of each thermal images, which included: mean temperature, variance, third moment, smoothness, homogeneity and entropy.Linear Discriminant Analysis (LAD) was employed for classification based on the mentioned features. The validity of input data was examined using Leave-one-out method. Statistical analysis was carried out using stepwise regression method in SPSS ver. 16.Results and discussion: The temperature extraction from the aril regions was done using the fusion of the segmented red/green ratio and the thermal image. The results showed that the temperature gradient with respect to time for one-day was the same as that for the five-day arils. This behavior was probably because the sound and fresh part of these arils was still large enough so that it causes less sensitivity with respect to the temperature change. However, the temperature gradient for ten-day and fifteen-day arils was relatively large. The analysis of temperature variations on arils surface showed that the less fresh the arils were,the more thermally sensitive they were with respect to their surroundings. The less fresh arils were cooler than the one-day and five-day arils. This might be due to the extended evaporation from the surface and the larger emissivity of older arils than fresher ones. The larger emissivity in less fresh tissues cause quicker heat penetration inwards or quicker heat loss from inside out, thus, the tissue become cool or hot quicker. Conversely, the fresh tissues have reduced heat transfer.They release heat in a cold environment or becomes warm it a warmer environment at a slow pace rate.The extracted temperature features were used in a Linear Discriminant Analysis (LDA) model for quality assessment and classification of pomegranate arils stored for three 60-second periods. The mean accuracy of classification of arils for three 60-second periods of imaging were obtained to be 62.1%, 72% and 79.8%. The optimum classification results were obtained from the third 60s. In this range, the accuracy of classification ofone-day, five-day, ten-day and fifteen-day arils were 98.7%, 69.23%, 65.4% and 89.8%, respectively. Conclusion: Twelve thermal features were extracted from thermal images of arils for classification in terms of freshness. The results confirm that thermography can be used as a non-destructive method for determining the freshness status of pomegranate arils during storage periods.
Ali Mohammadzadeh; Mohammad Hossein Abaspour fard; Mahmood Reza Golzarian
Abstract
Introduction: Pomegranate fruit as one of the most popular fruits native to Iran, belongs to Punica family (Punica granatum L). Iran with an annual production of about 700 tons is the largest producer of pomegranate fruits in the world. Colorfulness and healthiness are two important features of pomegranates, ...
Read More
Introduction: Pomegranate fruit as one of the most popular fruits native to Iran, belongs to Punica family (Punica granatum L). Iran with an annual production of about 700 tons is the largest producer of pomegranate fruits in the world. Colorfulness and healthiness are two important features of pomegranates, which cannot easily be controlled. Some negative characteristics of this fruit such as sun burning, cracking and scratchingcan reduce its economic value. Moreover, separating the arils from membrane (flesh) and sorting them based on their color and size is a laborious task which still is a challenging concern (Blasco et al., 2003). Despite these challenges, the demand for “ready-to-eat” of arils is increasing. Up to now several devices have been proposed to remove the arils from membrane with different operation principles. However, these devices leave some membrane segments with arils and also makeit difficult to sort the arils from color and size points of view (Khazaei et al., 2008; Singh et al., 2007). With the visual inspection methods, the external features of Bio-materials (e.g. shape, color and texture) can be evaluated. While for assessing their internal parameters, nondestructive methods such as MRI, X-RAY and NMR are preferred. To classify and identify bio-materials (e.g. fruits), several methods have been examined including Fuzzy technique (Hu et al., 1998), Multilayer (Luo et al., 1999) and Linear Discriminant Analysis (LAD) (Manickavasagan et al., (2010). The primary objective of this research wasto discriminate arils from membrane segments. Subsequently, the fruit components were classified into red, pink, white arils and membrane segments, using LAD method. Ultimately, the accuracy of classifications based on different images’ features was evaluated. Materials and methods:Pomegranate fruits of Khazar variety were provided from Kashmar gardens. Prior to imaging step the fruits were categorized in four groups each of 50 samples. The arils were ranked as red, pink and white using human sensory. The images of arils samples were prepared using a Nikon Coolpix digital camera (Nikon co, Japan), in a chamber having six LED lamps, from a distance of 15 cm. During image processing, the images were first converted into grayscale format and then transformed into binary images. Subsequently, several morphological (see table 2) and textural image (see Table 3) features were extracted for classification purpose. For color features three color spaces including RGB, HSI and L*a*bwere examined (see Fig 3). The arils were classified and discriminated from membrane using 12 morphological, 10 color and six textural features. Linear Discriminant Analysis (LAD) was employed for classification based on the mentioned features. The validity of input data was examined using theleave-one-out cross validation method. Statistical analysis was carried out using SPSS ver. 16.Results and discussion: The classification accuracy of arils based on morphological features was about 97.53% and the membrane segments were discriminated from arils with accuracy of 95.06% (Table 4). The classification with color features provided the accuracy of 45% when the “R” component of the images was considered (Table 5). This is mainly due to similar red band of the arils classes.The accuracy of classification improved whenHSI components were used andthe accuracy of 84% was achieved (Table 6). The best accuracy of classification with color features observed using L*a*b* color space. In this case the accuracy was 89.1% (Table 6). In the final stage of classification, six textural features obtained from statistical moments including mean grayscale, standard deviation, third moment, evenness, entropy and homogeneity were used. As shown in Table 7 with these components the accuracy of classification improved up 93.3%. Considering the classification with different features (morphological, color and textural) it can be said that, in general, the accuracy of discriminating membranes from arils is less accurate than the accuracy of discrimination between different arils (red, pink and white). This was observed in all methods of classifications with different image features. With regard to the specific functionality of each extracted feature, the combination of the features was used for classification. Due to the increasing number of input features, the stepwise method was used for rankingof input features.Out of 26 input features of classification model, 14 superior features were selected using stepwise method. The results of classificationwith the combination of different features are shown in Table 8. As it can be seen, the average accuracy of classification with the combination of features improved up to 99%. Fig. 4 shows the classification of the pomegranate components based on the combination of the features, using Linear Discriminant Analysis (LDA) method.Conclusion: A classification model was employed to classify pomegranate arils and membranes, using Linear Discriminant Analysis method. To improve the accuracy of classification, different image features were extracted and examined. In order to achieve a higher accuracy, the combination of features wasalso tested. This improved the accuracy of classification up to 99%. Since the combination of features is a costly and time-consuming process, the stepwise method was used to rank and select the superior features before their use in classification step.