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.
Seyyed Mohammad Emam; Amirmohammad Rezaiepoor; Aboalfazl Foorginejad
Abstract
Introduction: Pistachio cereals are one of the most important products in the export sector. Therefore, accurate grading of pistachios is very important. By counting the number of pistachios in 100gr according to the national standard of Iran, this product is classified into three categories of large, ...
Read More
Introduction: Pistachio cereals are one of the most important products in the export sector. Therefore, accurate grading of pistachios is very important. By counting the number of pistachios in 100gr according to the national standard of Iran, this product is classified into three categories of large, medium and small. Materials and methods: In this paper, the image of some pistachio cereals with different random size and shape was taken and stored in computers using the machine vision technique. Then, the image processing operations consisted of improving the pistachio images to increase the accuracy of edge detection was done. The exact calibration process was performed with a chessboard plate was conducted to extract the geometrical dimensions including the largest diameter and area. In the national standard of Iran, intact or broken pistachios are not considered to grade this product. Therefore, in this research, Fourier series method is used to extract morphological characteristics of pistachio cereals including roundness, elongation, asymmetry, triangularity and squareness using the low order descriptors. According to the results of the calibration operation, the dimensional measurement of pistachios with an average error of 0.09 mm is possible Results & Discussion: According to the experimental results, it is possible to improve the current standard of pistachio using image processing and fourier series techniques in terms of increasing measurement speed, reducing costs, and adding the shape characteristics of pistachios to determine the amount of intact or broken pistachios.
Mehran Nouri; Behzad Nasehi; Vahid Samavati; Saman Abdanan
Abstract
Introduction: Fried foods such as donuts enjoyed worldwide for their taste, distinctive flavor, aroma and crunchy texture. There is, however, grave health concern over large fat content of fried foods (Melito and Farkas, 2013). There are several ways to lower fat content in deep-fried foods. One method ...
Read More
Introduction: Fried foods such as donuts enjoyed worldwide for their taste, distinctive flavor, aroma and crunchy texture. There is, however, grave health concern over large fat content of fried foods (Melito and Farkas, 2013). There are several ways to lower fat content in deep-fried foods. One method is to reformulate the product by adding hydrophilic ingredients such as dietary fibers to reduce oil uptake during frying. Another method to reduce fat content is to partially cook the food using another heating method (Melito and Farkas, 2012). There is an increasing interest in microwaving foods for several reasons: it is faster than conventional methods, the energy consumption is often lower and foods cooked by microwaving maintain nutritional integrity.vIn foods, the appearance is a main criterion in making purchasing decisions. Appearance is used throughout the production –storage-marketing-utilization chain as the key means of judging the quality of individual units of product. The appearance of unities of products could be assessed by considering their color and surface texture. The use of computer-vision technology has quickly increased in the fields of quality inspection, classification and evaluation in processing a large number of food products (Brosnan and Sun, 2004). Therefore the aim of this study was to study the effects of microwave pre-treatment on sensory and appearance properties of donut.
Materials and methods: Response surface methodology and Box- Behnken design were applied to evaluate the effects of independent variable include microwave power (300-900 W), microwave time (30-90 s) and frying time (70-130 s) on sensory and appearance properties of donuts. Donuts were prepared according to the formulation by Melito and Farkas (2012) with some modifications. Ingredients used in donuts formulation were consisted of 100 g of wheat flour (9 g/100g), 52 g of water, 9.75 g of Shortening, 14 g of Egg, 14 g of water for yeast, 6.80 g of sugar, 6.80 g of nonfat dried milk powder, 3.25 g of active dried yeast, 1.70 g of Vanilla extract, 1.7 g of baking powder, 1.70 g of Salt, 1.3 g of Persian gum and 7.00 g of carrot pomace powder. The dough was cut into squares approximately 50 mm on each side. Then, the dough pieces were allowed to proof for 30 min at 27 ºC. The proofed samples were pre-treated using a microwave oven at different levels of microwave power and microwave time in accordance with the experimental design. Formerly, the per-treated donuts were deep-fat fried in a Moulinex deep-fat fryer (model F18-RA, France) filled with 1.5 L of vegetable frying oil (A mixture of Sunflower, palm, and soybean oil; Behshahr CO., Tehran, Iran) at different levels of frying time in accordance with the experimental design. The oil was preheated for 30 min prior to frying and replaced with fresh oil after every frying process. After frying, donuts were removed from the fryer and allowed to cool for 30 min on paper towels. They were then stored in coded sealed polyethylene bags.The evaluation of the crumb grain and crust color of donuts was performed using an image analysis system consisted of a Canon digital camera (model SX60 HS, Japan) and a personal computer with a Pentium(R) Dual-Core processor and Windows 7 Ultimate. The samples were photographed at a fixed distance of 30 cm from the crumb of samples, which were sitting inside a black box. The captured images were analyzed using the MATLAB R2014a software (The MathWorks Inc., Natick, Mass, USA).The CIE L*a*b* (or CIELAB) color model was used for determination of the crust color of donuts. Crumb grain features of the donut samples were obtained with described digital image analysis system. After imaging, each image was converted from RGB format to 8 bits (grey level) using the MATLAB software. In this format, an area of 3 × 3 cm2 was selected at the center of the captured image. After contrast enhancement of image, the image segmented using the Otsu algorithm, which produces highly uniform binary images (Otsu, 1979). Finally, crumb grain properties of donuts were studied by determination of cells densities and area of cells. Sensory evaluation of donut samples was carried out by assigning scores for crust appearance, crumb appearance, crust color, aroma, texture, taste and overall acceptance parameters based on a nine-point hedonic scale. (Stone et al., 2012).
Results and discussion: Results showed that roughness of the donuts surface increased significantly (p
