جستجوی مقالات مرتبط با کلیدواژه « image processing » در نشریات گروه « صنایع غذایی »

The improper use of chemical fertilizers in crop production can result in unsafe food sources for consumers. This research focuses on estimating the accumulation of nitrate in tomatoes by analyzing images of tomato tissues. The experiments were conducted using a completely randomized design with four nitrogen levels: 400, 800, 1200, and 1600 kg.ha-1. Fifty samples were randomly selected from each treatment to create images for feature processing and develop a prediction model. The samples were sliced to a consistent thickness, and their images were prepared. The nitrate contents of the same samples were then measured in the laboratory. Color features, including R, G, and B color components, as well as non-color features such as white pixel area (WPA), total slice surface area (TSA), and the ratio of white pixel area to total slice surface area (WPA/TSA), were extracted from the images. The results showed that the nitrate content of the samples increased significantly (P<0.05) in response to the applied nitrogen fertilizer, with measurements of 1.6%, 2.7%, 2.8%, and 3.3%, respectively. Moreover, a strong correlation was found between the color components, WPA, TSA, WPA/TSA, and nitrate accumulation in the samples. Multiple regression and multilayer perceptron neural network (MLP) models were employed to predict the nitrate content. The best subset method was used to build an appropriate regression model. Various topologies and transform functions were applied to identify the best MLP model. The results indicated that an MLP model with a 3-15-1 topology and the lowest mean relative percentage error (MRPE) was the most accurate neural network model. The final regression and neural network models were validated using 60 intact samples. The neural network model achieved a MRPE of approximately 3.5%, demonstrating its precise estimation of nitrate contents compared to the regression model with an MRPE of around 5.2%.

 Due to the importance of product appearance quality in product grading and the impact of factors such as area, uniformity, and various defects on the product quality, and also, the ability to recognize these features at a very low cost, image processing techniques, is one of the methods used to evaluate food quality. Therefore, in this study, a non-destructive image processing method was used to investigate the factors affecting the color and shrinkage of apple slices during drying.

 Golden delicious apples were used in this research. The central part of the apple (including the rivet, seeds, and tail) was removed by a kernel separator and sliced into 3, 5, and 7mm thickness and approximately 7 mm diameter slices using a hand slicer without separating the skin. Three temperatures of 60, 70, and 80 °C were used to dry the samples. To determine the moisture content of a sliced apple, the samples were first weighed on a digital scale, then placed in a dryer, and the experiment was continued until the samples reached equilibrium mass. Due to the high importance of moisture ratio in controlling the drying process, moisture rate (MR) and moisture content (MC) were calculated, and samples were taken to investigate the amount of surface shrinkage, general color changes and browning index. After extracting L*, a*, and b* values, total color changes and browning index (to show the intensity of brown color in the product) for all samples before and after drying were calculated and evaluated to describe color changes after drying.

 The drying kinetics results showed that the drying process significantly depends on the thickness of the samples. According to drying curves, at the early stages of drying, the decrease in humidity occurs more severely and the graph has a steeper slope, but as the process continues and the moisture content of the product decreases, the slope of the curve decreases. In the early stages of drying, due to the presence of water inside the fresh fruit cells, there is a pressure balance between the fruit and the surrounding environment, which causes the fruit to remain swollen. However, as the drying time progressed, contractile stresses are created, which cause superficial shrinkage. In this study, it was observed that increasing the thickness from 3mm to 7mm, reduced the final shrinkage on the surface of apple slices by 11% at 60 °C, 12% at 70 °C, and 13% at 80 °C. After moisture leaves the surface of the product and heat penetrates into the product, moisture begins to leave the product by conducting interstitial convection. When moisture moves to the surface, the mechanical balance and consequently the textural structure of the sample is disturbed due to the creation of different spaces in thickness. According to the results, increasing drying time and thus decreasing the moisture content, increases the percentage of apple shrinkage. On the other hand, at a certain thickness, with increasing temperature, the percentage of shrinkage changes in the thickness of the product decreases. Therefore, at thicknesses of 3, 5, and 7 mm, the increase in temperature from 60°C to 80°C, decreased the amount of shrinkage thickness by 16, 12, and 8%, respectively. It is in higher thicknesses that react with heat and change the color of the fruit due to the Maillard reaction. After complete drying of apple samples, the highest amount of color change was related to the thickness of 7 mm and a temperature of 80°C, which was equal to 1.254. Also, the lowest rate of discoloration of apple slices in a thickness of 3 mm and a temperature of 60 °C was 0.889. The browning index (Bi) in the high thickness of apple slices is less affected by the process temperature due to the increase in moisture level. For this reason, the rate of browning was very low among the experimental samples and the highest rate of browning was related to the thickness of 7 mm and the temperature of 80 °C was 585/2559. Also, the lowest rate of browning of apple slices was observed in the thickness of 3 mm and the temperature of 60 °C was 584.254.

 Finally, it was found that the thickness and temperature factors can have an effect on the quality of product during drying process. The results of this study can provide a cheap and fast way to control the quality of fruits during drying and help producers of these products select the main process factors that affect the final quality.

Raisins are one of the most important agricultural products obtained from drying grapes. At present, grading raisins and determining the percentage of different types of raisins in a sample, as well as identifying or not having a tail in it is done manually, and therefore requires a lot of time. In this study, the aim is to provide effective and powerful algorithms using image processing techniques in the field of machine vision for grading raisins as well as detecting and determining the percentage of tailed and tailless raisins. In order to analyze the proposed algorithm, the performance of the algorithm is evaluated by preparing photos of different samples of raisins and implementing the proposed algorithms on these samples in MATLAB software and comparing the results obtained with manual methods. To evaluate the performance of the proposed methods, the criteria of total accuracy, sensitivity and accuracy of positive output were calculated that the findings obtained from the evaluation of the proposed method for rating raisins total accuracy 98/65%, sensitivity 98/47% and positive output accuracy 97/83% as well as the findings of the proposed method for Determination of raisin tailing percentage showed total accuracy of 98%, sensitivity of 92/32% and positive output accuracy of 98/69%, indicating the optimal and reliable performance of these methods with low cost (low software calculations) compared to traditional methods.

In recent years, the non-destructive and fast method of image processing has been successfully used for quantitative and qualitative evaluation of the characteristics of food products. In this study, the effect of sugarcane bagasse as a source of fiber enrichment (0-25%), soybean water-soluble polysaccharide (0-2%) and frying time (2-5 minutes) on the image characteristics of donuts such as color, number , density and size of bubbles, porosity, energy, homogeneity, contrast and entropy were investigated. The findings of this research showed that the increase of sugarcane bagasse fiber increases the a* index and decreases the L* and b* components of the crust and crumb and porosity. On the other hand, increasing the frying temperature increases the redness of the crust and decreases the lightness of the crust and the porosity of the texture. Meanwhile, the polysaccharide soluble in soybean water had no significant effect on the characteristics of the treatments. The optimization results also showed that if 8.58% sugarcane bagasse and 0.36% soybean soluble polysaccharide are added to the formula and the sample is fried within 5 minutes, the best quality will be obtained.

Dehydration of Noughl, as a sugar-based confectionary product, negatively affects its texture which can be hindered by increasing relative humidity (RH) of atmosphere of storage container. In this research, glucose syrup (GS) and its mixture with salt at different ratios (8:1, 4:1 and 2:1) was utilized as RH-modifier inside the storage container in order to prevent hardness of Noughl. The effect of RH-modifiers on moisture, hardness, area and color of samples was investigated during 30 days. Color and area changes of samples were measured using image processing. According to the findings, the lowest change in moisture content, color and area of saffron Noughls was observed when GS-salt mixture was used at the ratio of 8:1. It is found that the RH-modifier could re-increase the RH of container internal space after opening and reclosing lid of the container for 29 times. Furthermore, hardness of Noughls was hindered since the average hardness values were 32.40 and 23.38 N on zero and 30 days, respectively. However, hardness of control sample reached to 149.85 N on day 5. Based on sensory evaluation, there was no significant difference between the overall acceptability of fresh Noughls and those stored for 30 days (P</em><0.05). The introduced low-cost RH-modifier can be applicable for different foodstuffs to prevent dehydration.

Nowadays, citrus fruits, especially oranges, is very important in the human nutrition regime, and its quality characteristics assessment is very important. This study aimed to predict some biochemical characteristics of blood orange, using machine vision and artificial neural networks. In this experiment, the amount of vitamin C content, sugar content, and acidity (pH) were obtained using destructive laboratory methods. Images of blood orange samples were captured and 108 texture features and 57 color features were extracted on CIElab, RGB, HSV, and HIS color spaces and finally, the artificial neural networks method has been used to estimate the desired properties. To evaluate and select the most optimal artificial neural network, a feed-forward neural networks with Levenberg-Marquardt learning algorithm, the different number of neurons, and different transfer functions in the hidden and output layers was used. Finally, using the best neural network and 165 textural-color features, the amount of vitamin C content, sugar content, and pH were estimated with a correlation coefficient of 0.950, 0.968, and 0.884, respectively. Therefore, considering the appropriate correlation coefficient, machine vision and image processing technology can estimate some biochemical characteristics of blood oranges accurately.

In the current study, a simple image processing method based on a RGB images using machine vision system has been designed to evaluate the color and texture features of low-calorie doughnut crumb. The effect of maltodextrin substitution with margarine at the levels of 25, 50, 75 and 100% (w/w) was evaluated on vision properties. These features were crumb color (L*, a* and b*), pore area fraction, number of cells/cm2, pore shape, Euler number, fractal dimension of pore boundaries and crumb texture (contrast, entropy, correlation, energy and homogeneity). Results revealed that the addition of maltodextrin increased L* value and decrease a* value of crumb color significantly. The contrast, entropy and Euler number of doughnut crumb containing 75 and 100% maltodextrin were considerably higher than control, 25% and 50% samples. Correlation, energy, homogeneity, mean pore area and diameter, number of cells per square centimeter and pore area fraction decreased after maltodextrin addition (75 or 100%) but no significant difference observed between control, 25% and 50% samples. The fractal dimension value of pore boundaries in doughnut containing 100% maltodextrin were the highest which indicates that the addition of maltodextrin caused more irregular and tortuosity porous boundaries.

Grape is a non-climacteric fruit with a low rate of physiological activity but is subject to serious physiological and parasitic disorders after harvest and during long term storage (Ciccarese et al., 2013). Currently, Edible coatings have been studied as potential substitutes for conventional plastics in food packaging. Edible coating is a thin layer of edible material formed as a coating on a food product. Edible coating can offer several advantages to the fresh fruit and vegetable industry such as improvement in the retention of color, acids, sugar and flavor components, the maintenance of quality during shipping and storage, the reduction of storage disorders and improved consumer appeal (Antoniou et al., 2015; Cazon et al., 2017; Fakhouri et al., 2015; Galus & Kadzińska, 2015). Farsi gum as a novel source of polysaccharides has drawn much attention in a wide range of various fields such as pharmaceutics, food and cosmetics industries. Functional properties of Farsi gum are influenced by its structure and molecular weight (Hadian et al., 2016; Joukar et al., 2017). By inclusion of bioactive compounds in the Farsi gum network the aforementioned impairments could be overcome and moreover, new protective and functional valences could be added. The inclusion of lipid-based component in Farsi gum gives it excellent light and moisture barrier properties. The benefic impact on human health of hemp seed oil is worldwide recognized. A recent study demonstrated the antimicrobial properties of hemp seed oil. Due to their abundance in biologically active compounds, hemp seed oil is promising natural alternatives that may extend the shelf-life, microbiological safety and nutritional values of food (Cozmuta et al., 2015; Leizer et al., 2000; Salarnia et al., 2018). Growing awareness of the quality of fruit has necessitated increasing effort to develop rapid and non-destructive methods for evaluating fruit quality (Bhargava & Bansal, 2020; Rachmawati et al., 2017; Tao & Zhou, 2017; Wu & Sun, 2013). The aim of this study was the consideration of image processing application for grape sorting based on visual surface characterize.  Coating emulsion was prepared using (Farsi gum (0%, 1.5% and 3%), hemp seed oil (0%, 0.075% and 0.15%) and glyceride (0.3%)). grape fruit were coated by immersion in coating dispersion for 5 min. Samples were then allowed to loss the excess coating dispersion. Coatings were developed at room temperature during an hour. Samples were refrigerated at 4± 1°C for 28 days and analyses were performed at days 0 and 28. Defect identification and maturity detection of grape fruits are challenging task for the computer vision to achieve near human levels of recognition. The image acquisition was performed in a homogenously controlled lighting condition. Considering the camera lens’s focal length, the samples were placed 25 cm under the camera’s lens to be under camera’s field of view. The images of grape were segmented from the background using thresholding of the high contrast images via MATLAB software (R2019a, image processing toolbox). The optimum threshold value was obtained to be 0.35, 0.45 and 0.30 for R, G and B channel, respectively.  The proposed techniques can separate between the defected and the healthy grape fruits, and then detect and classify the actual defected area. Classification is performed in two manners which in the first one, an input grape is classified with two different algorithms (RGB and binary). The Result showed that the accuracies for detecting the surface defects on grape were 97.73% and 96.30% using RGB and binary algorithms, respectively. Proposed method can be used to detect the visible defects of coated grape, and to grade the grape in high speed and precision.  The results of this research and similar ones can provide helpful recommendations in grading fruits for fresh consumption. The simplicity and the efficiency of the proposed techniques make them appropriate for designing a low-cost hardware kit that can be used for real applications.

The presence of various impurities leads to the problems in storage time, transmission, selling and consumption process of any product. Thus it is necessary to separate the impurities from the product for industrial processing. Descurainia Sophia is a tiny grain seed in light brown color with elliptical shape and it grown up in humid climate. Electrostatic method is a proper way for separation and purification of materials which is based on the absorption and diffusion of charged particles in an electrical field with high voltage. An experimental research was carried out for recycling the plastic waste with tribo-electric system. The result of the research on plastic separation of waste materials showed that by increasing the voltage of the system the purification fold increases. The results of the effect of the applied voltage for recycling the plastic particles showed that by increasing the applied voltage in the electrodes the mass and purity of the polycarbonate (PC) increased and the mass and purity of polyamide (PA) decreased. There is a little information about separation and purification of fine grain seeds and this study is about separating of Descurainia Sophia seed and the effect of the parameters using regression analysis.   Descurainiaseed samples were collected from the farms located in Mahan city of Kerman province, Iran. Tribo-airo-electrostatic system contains of funnel and feeding container, the charger unit, the separating unit, air transmission channels and gathering unit. Charging unit consists of two aluminum electrode connected to a high voltage DC power supply adjustable between 0-100 kV. A blower was used to suspend material and increase the exposure time of particles in the electric field. The gathering is a box with different partitions divided by wooden sheets. Separated particles fall in the gaps based on the amounts of charges, weight and shape. The separating process takes place by considering physical properties. There are two important forces that acts on the falling of the object in electric field; the electric force acts in the horizontal direction, gravitational force acts in the vertical direction. Considering the purity of the separated seeds in the box, only four sections of the box were selected for size and frequency analysis. For obtaining gathered seed impurity, the digital pictures of the gathered samples imported in Matlab6.5 software and were analyzed using Image processing toolbar based on the differences between seed and impurity color. For regression analysis of the parameters voltage in the electrodes, the distance of the electrodes, the angle of the electrode and the mass of the boxes was considered. Laser diffraction method used for determination the size of separated particles and for this purpose FRITSCH Laser Particle Size Analyser -ANALYSETTE 22 NanoTec system was used.   The results illustrated that the Descurainiaseed takes negative charge and moves to the positive electrode and impure particles takes positive charge and moves to the negative electrode. The purity calculations of the experiments showed that the average percentage of box No.1 is more than 98%, box No.2 is between 65%-75%, box No.3 is between 30% to 50% and box No.4 is less than 50%. The values of correlation coefficient of the effective parameters for box No.1 was 90% and this means that 90% of the parameters of equation affected on the weight of the box No.1 for about 90%. By increasing the applied voltage and the angle of the electrodes of the separating unit and decreasing the distance of the electrodes, the purity of box increases. The size analysis of Descurainiaseed showed that the particles with larger dimensions take more negative charge and moves to negative electrode. The results of the study showed that tribo-airo-electrostatic system separated Descurainiaseed from waste particles properly. By considering the optimum value of separating parameters the purification increased by 98%. According to the results it can be stated that this system can be used for separation and purification of small grains such as alfalfa and clover.

Many foods have a structures base on foam; hence their stability has a key role in their textural, structural and acceptance properties. In food industrials, polysaccharides such as gums and gelatin use as stabilizer in foam-based food system. In this research effect of gelatin (1, 2, 3%) on foaming properties of albumin and sodium caseinatate (1 and 2%) has been investigated. Overrun, foam value fraction and drainage have been measured and also image processing used for evaluate porosity, fractal count, entropy and sphericity. Result showed that adding gelatin decreased porosity, entropy, fractal count, drainage, foam value fraction on and overrun. Adding protein caused porosity, overrun, fractal count and circularity increased while bubble size decreased. Therefore, we can use various amount of gelatin for stabilizing foam-base food.

Fruit fibre have better quality due to higher total and soluble fibre content, water and oil holding capacity and colonic fermentability, as well as lower phytic acid content and caloric value (Sharoba et al., 2013). In the fresh mass of the pumpkin (Cucurbita moschata), total carotenoid content, a major contributory factor in the high nutritional value of pumpkins, ranges from 2 to 10 mg/100 g, the content of vitamins C and E accounting for 9–10 mg/100 g and 1.03–1.06 mg/100 g, respectively (Hosseini Ghaboos et al., 2016; Nawirska et al., 2009). Pumpkin fruit is also a valuable source of other vitamins, e.g., vitamin A, B6, K, thiamine, and riboflavin, as well as minerals, e.g., potassium, phosphorus, magnesium, iron and selenium (Mirhosseini et al., 2015; Obradović et al., 2015). Since pumpkin is a valuable micronutrients source, dried pumpkin could be processed into powder for foods to increase fibers, vitamin A and mineral contents. In addition, pumpkin powder can be used in bakery products because of its highly-desirable flavour, sweetness and deep yellow-orange colour (Salehi, 2020). The influence of replacement of wheat flour with pumpkin powder (at five levels of 0, 2.5, 5.0 7.5 and 10 %) on textural properties and sensory qualities of biscuit was studied by Kulkarni and Joshi (2013). As the replacement level of wheat flour with pumpkin powder increased, the firmness and fracturability values were increased. Biscuits with more pumpkin powder had a more yellow colour than those with less pumpkin powder. According to the sensory evaluation results, biscuits containing 2.5 % dried pumpkin powder had the highest total acceptance score. The iron and β-carotene content of biscuits increased with increasing pumpkin powder levels. Spinach is a good source of minerals (Fe, Mn, Zn and Mg), vitamins (E, A, C, K, B1, B6 and B2), protein, fibers and antioxidants, making it a suitable ingredient to be used in the formulation of food products with high nutritional and biological values (Slavin and Lloyd, 2012). El-Sayed (2020) studied the effect of spinach nano-powder (0.5-2%) addition on the quality of ultra-filtered soft cheeses. The author demonstrated that by increasing of spinach powder concentration with retentate, the content of fibers, minerals, total phenolic content, and antioxidant activity of samples was enhanced. In this study, pumpkin and spinach powders were used to improve and enhance the quality of sponge cake due to their high nutritional value, fiber, β-carotene and minerals (calcium and iron).

At first, the pumpkin and spinach were dried and powdered in controlled conditions. Fresh pumpkins (Cucurbita moschata) were purchased from local market. The pumpkin slices with 5 mm thickness were dried in an oven (65°C). The dried pumpkins were milled, powdered and passed thru a 125 mesh screen (Hosseini Ghaboos et al., 2016). The ingredients used in the formula of sponge cakes were cake flour (100 g), sucrose (70 g), sunflower oil (60 g), fresh eggs (70 g), whey (4 g), baking powder (1.5 g), vanilla (0.5 g), water (40 g) and nonfat dry milk (20 g) powder. Sucrose and sunflower oil were poured into a bowl, and mixed for 10 min. Whole egg was added to the bowl, and then mixed for 4 min. The sifted cake flour, whey, baking powder, vanilla, water and nonfat dry milk powder was gradually poured into a bowl, and mixed for 3 min. Water was added to the bowl, and then mixed for 1 min. For each cake, 45 g of cake batter was poured into a cake pan and baked at 195°C for 25 min in a oven toaster. The cakes were allowed to cool for 20 min, and then were removed from the pans. The cooled cakes were packed in polypropylene bags at room temperature before physico-chemical and sensory evaluation analyses. The test sponge cake samples prepared with 0% (control), 5%, 10%, 20 and 30% replacement of cake flour with blend of pumpkin and spinach powder. The blend of pumpkin and spinach at concentrations of 0, 10, 20 and 30% were used in sponge cake formulation and the dough viscosity and physicochemical, color, texture and sensory properties of the product were studied. The texture profile analysis of sponge cake samples from the midsection of the cakes were performed using a texture analyzer (TA-XT Plus, Stable Micro Systems Ltd., Surrey, UK) with a 36 mm diameter cylindrical probe, 50% compressing and a test speed of 1.0 mm s−1 . The crust of cake samples was removed in cake texture determination. A double cycle was programmed and the texture profile was determined using Texture Expert 1.05 software (Stable Microsystems). Other parameters were defined as: pre-test speed 2.0 mm s−1, post-test speed 2.0 mm s−1 and trigger force 5 g. The texture parameters recorded were firmness, cohesiveness, springiness and resilience, and the texture parameter of cake was averaged from 3 replications. Statistical analysis was performed in factorial arrangement based on completely randomized design and comparing was performed at the average at 5% level using Duncan's multiple range test.

With increasing percentage of pumpkin and spinach powder in sponge cake formulation showed that fiber, iron and calcium percentages of samples were increased from 1.60 to 10.04%, 9.78 to 50.93 ppm and 0.19 to 0.42, respectively and there was a significant difference between treatments (p < 0.05). Also, β-carotene, protein, moisture and density of cakes increased significantly with increasing percentage of powder replacement (p < 0.05). By increasing the percentage of substitution of powders in sponge cake formulation from 0 to 30%, the viscosity of cake batters at shear rate of 90 s-1 was significantly increased from 16.72 to 30.82 Pa.s (p < 0.05). According to the results of image processing, as the percentage of pumpkin and spinach powder increased in the formulation, the a* index decreased and became negative indicating that the samples became greener with increasing replacement percentage.

The firmness of cakes enriched with pumpkin and spinach powder was obtained in the first day and on the 14th day in the range of 2.071-5.427 N and 3.354-6.207 N, respectively. Based on the sensory evaluation results, the sample containing 20% pumpkin and spinach powder had the highest overall acceptance score.

In the present study, in the first step, the effect of Aloe vera gel (75% v/v) coating containing different concentrations of hemp seed oil (1-5% v/v) on some physicochemical properties of cherry tomatoes during storage at room temperature was investigated. The results revealed the ability of hemp seed oil to improve the physicochemical properties of cherry tomatoes during storage, although no significant difference was observed between 3 and 5% levels of hemp seed oil (p> 0.05). Slope change in the ripening index trend occurred for A. vera gel (75% v/v) coated sample on day 12 and for A. vera gel containing 3% hemp seed oil coated sample on day 16. Using an image processing system, the changes of the coated samples were evaluated based on the color statistical and color texture features extracted from the images and were graded through different procedures. The results showed that the principal component analysis (PCA) and artificial neural network (ANN) methods were able to divide the cherry tomatoes into intact and blemished grades which the ANN method was graded samples using color texture features with higher accuracy (97.41%). The adaptive neuro-fuzzy inference system (ANFIS) method had higher diagnostic power than the other two methods and was able to grade the samples into three grades including intact, grade 2 and unusable with accuracy of 98.96%.

The control pests and diseases is considered one of the most important operations of Citrus in the protection stage. Today, a lot of research has been done in various fields of agriculture, including the diagnosis of plant pests and diseases by using machine vision methods. One of the problems that reduce the accuracy of the machine for detecting pests in farm conditions is the presence of adverse factors such as shade and changes in light intensity at different times of the day. In this study, in order to find the appropriate light intensity at different times of the day and increase the brightness of the shady parts of the trees, lighting by a lamp at the imaging site has been used. For detect pest-infected trees (in this snail study) has been used to Deep learning method which has been studied and evaluated by various optimization algorithms such as RMSProp, Adam and SGDm. To evaluate and test the algorithm used, 8000 images were examined in 9 farm conditions and one laboratory state In farm conditions, the lowest detection accuracy of algorithms with 64.32% related to imaging in cloudy days with light intensity of 350 to 700 lux was obtained using RMSProp algorithm, which Detection accuracy was improved up to 95.25% using SGDm algorithm by creating a light intensity controlled by a lamp (approximately 9000 lux). In laboratory conditions where the images were prepared in a controlled environment with constant light intensity, the detection accuracy was Obtained 98.73% with SGDm algorithm.

In this study, the effects of Farsi gum (0, 1.5% and 3%) coating containing hemp seed oil (0, 0.075% and 0.15%) on mass and volume changes of grape were investigated during storage at 4°C for 28 days. Machine vision system with learning machine methods was used to detect coated grapes from an image and estimate their mass and volume based on the image features (length, width, height and area). Four machine learning models, including linear regression (LR), artificial neural networks (ANN), radial basis function support vector regression (RBF-SVR) and Linear basis function support vector regression (LBF-SVR) were developed to predict the mass and volume of the single grape. The estimated grape mass and volume by these methods was compared statistically with actual values. The mass and volume in all treatments showed a decreasing pattern during the cold storage. The results indicated that mass and volume change decrease with Farsi gum and hemp seed oil increasing. Furthermore, according to the model evaluation results, the prediction performance of RBF-SVR model had achieved better predictive accuracy compared with the results of LR, ANN and LBF-SVR models, with R2 of 0.998 and 0.989 for mass and volume estimation, respectively, which also showed a good agreement between actual and predicted values. These results revealed that SVR model was a promising tool for estimating the mass and volume of grape during storage.

Nowadays, in modern agriculture, the combination of image processing techniques and intelligent methods has been used to replace smart machine instead of humans. In this study, an artificial image processing and artificial neural network (ANN) method was used to classify strawberry fruit of Parus variety. In the first step, the fruit was divided into 6 classes (ANN outputs) by the expert, and 100 samples were randomly collected from each class. In the next step, the images of the samples were captured and three geometric properties with twelve color properties (as ANN inputs) were extracted. Optimum artificial neural network structures considering root mean squared error (RMSE) and correlation coefficient (R2) were investigated to classification process of the strawberry samples. Finally, the perceptron neural network with a structure of 6-18-15 was selected with an average accuracy of 83.83%.

An investigation was conducted to evaluate the effects of feed composition, feed moisture content and screw speed variables on the physicochemical, textural, visual, acoustic and sensory properties of flaxseed puffed snacks, produced by the extrusion processing. The flaxseed mixed with corn grits at three ratios: 7, 14 and 21 percent, the water was added to the mixture to bring the moisture content of the samples of feeding to 12, 15 and 18%. The mixtures were extruded at screw speeds of 120, 150 and 180 rpm, at 140°C. Experiments on the samples showed that increasing in moisture content of the samples led to increase in water absorption, particle density and hardness, and also led to decrease water solubility and texture sensory scores.  Increasing in screw speed led to increase the water solubility and to reduce particle density, radial expansion, hardness, and sensory scores of appearance, color, texture, and overall acceptance of samples. Increasing the ratio of flaxseed in samples, led to increase particle density and to reduce radial expansion and sensory scores for the appearance, color and overall acceptance of the samples. In order to produce the optimum sample with the highest expansion ratio and brightness and the lowest hardness and density, containing 14% of flaxseed, the screw speed and feed moisture content must be  selected at  180 rpm and 14.42%, respectively.

Kichi is a local sweet bread that is cooked in the west of Iran, especially in Chaharmahal and Bakhtiari Province. This product is traditionally produced and has a low shelf life and hard texture. Therefore, the aim of this study was to investigate the effect of xanthan gum (0, 0.1, 0.3 and 0.5%) to improve the quality of Kichi sweet bread. Also mean size area, porosity, fractal dimension, and color parameters of Kichi bread were evaluated. The results showed that addition of xanthan led to improving WHC. The results of the texture analysis showed that softer samples were obtained in the low concentrations of xanthan gum (0.1% based on flour) and gumminess in this sample was significantly less than other samples (p < /em><0.050). Also, the porosity of the product in the low concentrations of xanthan (0.1%) was similar to the control, but in the high concentration of xanthan gum, the porosity of the product reduced. On the other hand, the results showed that the addition of xanthan gum did not affect the fractal dimension of the product texture. In the case of product color, the xanthan had a significant effect on the L* and b* values of the texture. Finally, it can be stated that using 0.1% of xanthan gum in the formulation of this local bread led to the production of a quality product regarding color and texture. The sensory evaluation results of the samples showed that the addition of xanthan improves the sensory properties of the samples. In general, samples containing 0.1% xanthan had better texture and sensory properties.

In this study, three levels of flour extraction rate (80, 88 and 96 %) and amylase and xylanase (50ppm) were used in barbari bread. The moisture, specific volume, porosity, firmness (2, 24 and 72 hours after baking), crust color and sensory properties of breads were evaluated. The result showed, the moisture and a* value were increased and firmness (during 72 hours) and L* value were decreased by increasing flour extraction rate. The sample containing 80% extraction rate and amylase and xylanase had the highest specific volume and porosity. Amylase and xylanase had the positive effect on texture, specific volume, porosity and sensory properties of bread. The flour extraction rate and enzymes didn’t have significant effect (P<0.05) on b* value of samples. Finally, the evaluation of sensory properties showed the samples containing 80 and 88 % extraction rate and enzymes had the highest overall acceptability.

It is important to control the ripening stages of agricultural products during storage and their quality grading based on their ripening stage. Edible coatings can prolong the storage life of agricultural products and protect them through the handling, storage, processing and marketing. The purpose of the current study was to develop an artificial vision system for quality control and segregation of cherry tomatoes in two different conditions including with and without Aloe vera gel coating. For this purpose, physicochemical properties including titrable acidity, total soluble solids and firmness of cherry tomatoes were measured in both conditions. Based on these properties, the ripening index (RPI) was determined and the samples were classified to MS1 and MS2 according to the ripening stage. Subsequently, the samples were classified using color features, color texture features separately and their combination through principal component analysis (PCA) and back propagation neural network (BPNN). Classification results showed that the use of color and color texture features combination made the classification more accurate; PCA and BPNN methods were able to segregate the samples with high accuracy (85.72 and 98.21, respectively) using the 21 color and color texture features. The higher accuracy of the BPNN method is due to its nonlinear performance. The results of this study indicate that Aloe vera gel is promising in delaying the ripening process of cherry tomatoes and artificial vision system can be used as a non-destructive method for evaluation of cherry tomato ripening level based on the color and color texture features.