Omid Doosti Irani; Abbas Rohani; Mahmood Reza Golzarian; Mansoureh Shamili; Peyman Azarkish
Abstract
Introduction: The diversity and abundance in quality properties of agricultural products are leading factors to develop non-destructive methods. Machine vision and artificial intelligence are powerful techniques in detection of many physical, mechanical and chemical properties of agricultural products. ...
Read More
Introduction: The diversity and abundance in quality properties of agricultural products are leading factors to develop non-destructive methods. Machine vision and artificial intelligence are powerful techniques in detection of many physical, mechanical and chemical properties of agricultural products. Prior to exporting, fruits are sorted in terms of their shapes, volumes or weights. Non-destructively taste-based sorting can be of importance in terms of markability and application. Artificial Neural Network (ANN) has been introduced as a new method to predict quality parameters such as firmness, total sugar content (TSC) and pH of agricultural products and to grade the products accordingly. Material and Methods: In this research, the quality properties of Mango (Kelke- Sorkh var) were predicted using the combination of image processing and artificial intellect techniques. The mango samples were harvested from the orchard in Minab, Hormozgan province in Iran. The samples were transferred to computer vision lab, room temperature of 24°C and 22% RH. The samples were divided into three groups for temperature treatment. They were kept at three temperature levels of 5°C, 15°C and 24°C (control group) for 48 hours. The sample were then placed in room temperature and were imaged every second day for 14 day period. After imaging, each sample was undergon destructive tests for determining their quality attributes including sugar content, firmness and pH. The images were taken by a digital camera in visible spectrum (Nickon Coolpix p510, Nikon Inc, Japan). The taken images were, then, transferred to Matlab software environment (Mathworks Inc, US) for analysis and processing. The color factors from regions of intrest were extracted from the images in L*a*b* color space. The segmentation of images was performed by thresholding (threshhold value of 0.3) the image of difference between red and blue channels of taken RGB images. The conversion of RGB color space to L*a*b* was done by converting RGB image to XYZ basic color space first and before converting X, Y, and Z basic color components to L*, a*, b* color factors. The L* represent the lightness in the image from black (0) to white (100). In this project, a multilayer perceptron neural network with a hidden layer was used. The optimum number of neurons in the hidden layer was found to be 25. The maximum iterations was set as 1000 and the learning rate was set as 0.001. Results and discussions: The input variables to the network were temperature treatment at three levels (control, 5°C and 15°C), the color factors (L*, a* and b*) and the variations of three color factors across the regions of interest (standard deviations of L*, a* and b*). The output variables were sugar content, pH and texture firmness. The results showed that the accuracy of the ANN model on the prediction of pH, sugar content and firmness were 45%, 85 and 88%, respectively. Although the accuracy of ANN model for predicting pH from color factors was rather low, this model was able to predict firmness and sugar content with highly accurately. The histogram of errors among three ANN models also showed the ANN model for predicting firmness and sugar content performed better than that for predicting pH. The MAPE prediction error were 9.53, 22.74 and 6.14, respectively, for predicting firmness, pH and sugar content. Comparing the results from the network in training and testing stages showed that ANN can be considered as a reliable method for estimating quality factors of firmness and sugar content with high accuracy and estimating pH with rather non-applicable accuracy.
Maryam Naghipouzade Mahani; Mohammad Hosein Aghkhani; Khalil Behzad; Abbas Rohani
Abstract
Introduction: Conventional technology of sugar production from sugar beet roots consists of the next subsequent steps: sugar beet slicing, thermal denaturation of the sliced beet roots followed by diffusion in hot water at 70–75 _C, purification of extracted juice by lime, concentration of purified ...
Read More
Introduction: Conventional technology of sugar production from sugar beet roots consists of the next subsequent steps: sugar beet slicing, thermal denaturation of the sliced beet roots followed by diffusion in hot water at 70–75 _C, purification of extracted juice by lime, concentration of purified juice and crystallization. The diffusion process is one of the most important steps that effect on product yield. The quality of cossettes is too important that increase extraction yield. Therefore the main function of the beet-slicing operation is to improve the diffusion operation. The most important factors in producing quality cossettes are the type of knives. Most knives have a V shape that cause increase of the surface area of the beets. At slicing operation, Amount of the sucrose of beet extract directly. Considering the blade edge causes the rupture of beet cell so it effects on quality of juice and yield of extraction. Also the different blades edge causes different surface areas that effect on osmotic operation. In this work, the effect of two kinds of blades (serrate and flat edge) is studied on extraction process and the juice quality. Material and method: Fresh sugar beets (Beta vulgaris) were obtained from Ferdowsi university farm and storage at 5C°. For each test run, 300gr of cossette 4mm thickness and 8cm in length were cut by cutting device with ability of blade change. The sucrose content of cossetttes was measured in ICUMSA method. These tests were organized as follows 4 steps. The first step was washing. Considering amount of sucrose of sugar beet extract directly at slicing operation, the decrease of sucrose content of cossettes and the sucrose of washing juice should be measured. For this stage, 120gr of cossettes were washed with 320gr of distilled water. After washing the cossettes, the sucrose content of cossettes was measured again and the decrease of suocrose content of cossettes was calculated and sucrose of washing juice was measured. For the thermal-pretreatment step, 130gr of sugar beet cossettes were treated with 260gr of distilled water 70C° at 7min and the sucrose of thermal-pretreatment juice was measured. In the diffusion step, 130gr of these cossettes were immersed in 260gr of distilled water 73C°. The solute concentration (Brix, g solubles 100 g_1 juice) was measured by digital refractometre (PR-101, Atago, 50 Kyo, Japan) every 5 to 10 min up to equilibrium conditions. The final step was pulp pressing. The pulps were compressed by laboratory press (2 bar) at 15min. following by the pressed pulp was weight then the sucrose content of them was measured. In the following, purity and nonsucrose of juice were determined for washing, thermal-pretreatment and diffusion steps. These parameters were measure in ICUMSA unit which is based on polarimeter method. Also extraction yield of diffusion, mass of extraction sucrose and extraction sucrose at diffusion, pressed pulp yield, extraction degree and energy were calculated. The data were analyzed in 2-sample t-test at minitab17 and the graphs were drew in excel. Results and discussion The results showed that the edge of the baled had significant effect on the juice purity (washing and thermal-pretreatment steps), non-sucrose content and sucrose of juice, extracted sucrose at cutting operation, extracted sucrose at diffusion, degree of extraction, yield of pulp, time and energy (P<0.05). The most juice purity was obtained from flat blade with 78.33%, 84.86% and 85.52% at washing, pretreatment and diffusion steps respectively. Also the least of non-sucrose content was obtained from this blade with 0.1%, 0.55% and 0.51% at washing, pretreatment and diffusion steps respectively. The serrate blade increase the tearing (rupturing) of the beet cells at slicing operation. Torn cells allow more impurities (nonsugars) to be diffused into the surrounding juice, causing an increase in nonsugars and, consequently, a reduction in juice purity. For the serrated blade, The most extracted sucrose at cutting operation and diffusion step, mass of sucrose of diffusion juice and degree of extraction were obtained 14.5%, 94.4%, 7.22 gr and 0.19 respectively that compare to another blade is more. The edge of serrate blade increases the surface aria of cossettes compare to use of flat blade. The surface area is one of the most important parameter to improve osmotic operation. The more contact area between the beet cells and the water in the diffuser cause the more movement of sugar from the cells to the diffusion juice. Therefore the use of the serrate blade improves the osmotic operation and enhances the extracted sucrose. The least of pulp yield, extraction time and energy were obtained 27.97%, 40 min and 1.7 Kw/h respectively for this blade. The increase of sucrose extraction reduces the pulp yield. As regards osmotic operation improve whit the increase of surface area cossettes, therefor the sucrose extract at lees time and the total energy decrease. Regarding to the results, both of blades improve some of the extraction parameters.
Saeideh Fayyazi; Mohammad Hossein Abaspour fard; Abbas Rohani; Hassan Sadrnia; Seyed Amir Hasan Monadjemi
Abstract
Due to variation in economic value of different varieties of rice, reports indicating the possibility of mixing different varieties on the market. Applying image processing and neural networks techniques to classify rice varieties is a method which can increase the accuracy of the classification process ...
Read More
Due to variation in economic value of different varieties of rice, reports indicating the possibility of mixing different varieties on the market. Applying image processing and neural networks techniques to classify rice varieties is a method which can increase the accuracy of the classification process in real applications. In this study, several morphological features of rice seeds’ images were examined to evaluate their efficacy in identification of three Iranian rice varieties (Tarom (Mahali), Fajr, Shiroodi) in the mixed samples of these three varieties. On the whole, 666 images of rice seeds (222 images of each variety) were acquired at a stable illumination condition and totally, 17 morphological features were extracted from seed images. Fisher's coefficient (FC), Principal component analysis (PCA) methods and a combination of these two methods (FC-PCA) were employed to select and rank the most significant features for the classification. The so called LVQ4 (Learning Vector Quantization) neural network classifier was employed for classification using top selected features. The classification accuracy of 98.87, 100 and 100% for Fajr, Tarom and Shiroodi, 100 and 100% for Fajr and Shiroodi, 100 and 100% for Tarom and Shiroodi and 97.62 and 95.74% for Fajr and Tarom were obtained, respectively. These results indicate that image processing is a promising tool for identification and classification of different rice varieties.
