Mahmoud Omid

University of Tehran, Biosystems Engineering, Faculty Member

University of Tehran, Agricultural Machinery Engineering, Emeritus

Followers

552

Following

Co-authors

Public Views

I received my PhD in Telecommunications from University of Electro-Communications (Japan) in 1997. Currently, I am a full professor at the University of Tehran (Iran). My special fields of interest include artificial neural networks, fuzzy logic and machine vision. My current research interests include computational intelligence and machine vision in Biosystems ٍٍEngineering.
Phone: +98-263-2808138
Address: Homepage: http://can.ut.ac.ir/member/omid.aspx
My Google Scholar: https://scholar.google.com/citations?user=1LnABgMAAAAJ&hl=en

less

InterestsView All (7)

Uploads

Papers by Mahmoud Omid

Feasibility of using smart phones to estimate chlorophyll content in corn plants

New spectral absorption photometry methods are introduced to estimate chlorophyll (Chl) content o... more New spectral absorption photometry methods are introduced to estimate chlorophyll (Chl) content of corn leaves by smart phones. The first method acquires light passing through a leaf by smartphone camera, compensating for differences in illumination conditions. In order to improve performance of the method, spectral absorption photometry (SAP) with background illumination has been considered as well. Data were acquired by smartphone camera in Iowa State University maize fields. Various indices were extracted and their correlation with Chl content were examined by Minolta SPAD-502. Hue index in SAP reached R 2 value of 0.59. However, with light-aided SAP (LASAP), R 2 of 0.97 was obtained. Among traits, the vegetation index gave the most accurate indication. We can conclude that the high performance of LASAP method for estimating Chl content, leads to new opportunities offered by smart phones at much lower cost. This is a highly accurate alternative to SPAD meters for estimating Chl content nondestructively.

Download

Development of an android app to estimate chlorophyll content of corn leaves based on contact imaging

Computers and Electronics in Agriculture

A new android app for smartphones to estimate chlorophyll content of a corn leaf is presented. Co... more A new android app for smartphones to estimate chlorophyll content of a corn leaf is presented. Contact imaging was used image acquisition from the corn leaves. In this method, the light passing through the leaf is captured directly by a smartphone camera. This approach would eliminate the needs for background segmentation and other pre-processing tasks. To estimate SPAD (Soil Plant Analysis Development) values, various features were extracted from each image. Then, superior features were extracted by stepwise regression and sensitivity analysis. The selected features were finally used use as inputs to the linear (regression) and neural network models. Performance of the models was evaluated using the images taken from a corn field located in West of Ames, IA, USA, with Minolta SPAD 502 Chlorophyll Meter. The R2 and RMSE values for the linear model were 0.74 and 6.2. The corresponding values for the neural network model were 0.82 and 5.10, respectively. Finally, these models were suc...

Download

Determination of orange volume and surface area using image processing technique

A b s t r a c t. In this paper, an accurate image processing algorithm for determination of volum... more A b s t r a c t. In this paper, an accurate image processing algorithm for determination of volume and surface area of orange is developed. The proposed machine vision system consists of two CCD cameras, an appropriate lighting system and a personal computer. The cameras are placed at right angle to each other in order to give two perpendicular views of the image of the orange. Initially, the algorithm segments the background and divides the image into a number of frustums of right elliptical cone. The volume and surface area of each frustum are then computed by the segmentation method. The total volume and surface area of the orange is approximated as the sum of all elementary frustums. The difference between the computed volumes and surface areas obtained by the image processing method and measured by water displacement and tape method, respectively, are not statistically significant at the 5% level. The Bland-Altman results show that the orange size has no effect on the accuracy of estimated volume and surface area found by the image processing technique. The regression formula, M=0.68V IP +44.6, between the computed volume and the measured mass of oranges is found to be highly correlated with R 2 =0.93. K e y w o r d s: orange, volume, surface area, mass, image processing, segmentation method

Download

Environmental impact assessment of tomato and cucumber cultivation in greenhouses using life cycle assessment and adaptive neuro-fuzzy inference system

by Mahmoud Omid and Sean Clark

Journal of Cleaner Production, 2013

This study was carried out in Isfahan province, Iran, to assess the environmental impact of green... more This study was carried out in Isfahan province, Iran, to assess the environmental impact of greenhouse cucumber and tomato production using life-cycle assessment (LCA) methodology. In this study a cradle-to-farm-gate approach using data from greenhouse operators and two distinct functional units, one mass-based and the other land-based, were selected to analyze the impact categories. Data for production of inputs were taken from EcoInvent Ò 2.0 database, and SimaPro software was employed for analysis. Ten impact categories including Abiotic Depletion potential, Acidification potential, Eutrophication potential, Global Warming potential for time horizon 100 years, Ozone Depletion potential, Human Toxicity potential, Freshwater and Marine Aquatic Ecotoxicity potential, Terrestrial Ecotoxicity potential, and Photochemical Oxidation potential were selected based on the CML 2 baseline 2000 V2/world, 1990/characterization method. In addition, adaptive neuro-fuzzy inference system (ANFIS) was employed to predict the environmental impact of both crops on the basis of input materials. The results indicated that greenhouse tomato production had a lower environmental impact than cucumber due to less total energy input and correspondingly lower environmental burdens in all impact categories. Almost all impact categories were dominated by natural gas, electricity and nylon (as cover of greenhouses). Furthermore, the results revealed that ANFIS was capable of forecasting the environmental indices of greenhouse production with a high degree of accuracy and minimal error.

Download

Artificial neural network based modeling of tractor performance at different field conditions

Application of tractors in farming is undeniable as a power supply. Therefore, performance model ... more Application of tractors in farming is undeniable as a power supply. Therefore, performance model for evolving parameters of tractors and implements are essential for farm machinery, operators and manufacturers alike. The objective of this study was to assess the predictive capability of several configurations of ANNs for performance evaluating of tractor in parameters of drawbar power, fuel consumption, rolling resistance and tractive efficiency. A conventional tillage system which included a moldboard plow with three furrows was used for collecting data from MF285 Massey Ferguson tractor. To predict performance parameters, ANN models with back-propagation algorithm were developed using the MATLAB software with different topologies and training algorithms. For drawbar power, the best result was obtained by the ANN with 6-7-1 topology and Bayesian regulation training algorithm with R2 of 0.995 and MSE of 0.00024. The ANN model with 6-7-1 structure and Levenberg-Marquardt training algorithm had the best performance with R2 of 0.969 and MSE of 0.13427 for TFC prediction. The 6-8-1 topology shows the best power for prediction of AFC with R2 and MSE of 0.885 and 0.01348, respectively. Also, the 6-10-1 structure yielded the best performance for prediction of SFC with R2 of 0.935 and MSE of 0.012756. The obtained result showed that the 6-7-1 structured ANN with Levenberg-Marquardt training algorithm represents a good prediction of TE with R2 equal to 0.989 and MSE of 0.001327. The obtained results confirmed that the neural network can be able to learn the relationships between the input variables and performance parameters of tractor, very well.

Download

Energy use patterns and econometric models of major greenhouse vegetable productions in Iran

Energy, 2011

This paper examines the energy use patterns and energy inputeoutput analysis of major greenhouse ... more This paper examines the energy use patterns and energy inputeoutput analysis of major greenhouse vegetable productions in Iran. Data from 43 farmers were obtained using a face-to-face questionnaire method. The majority of farmers in the surveyed region were growing cucumber and tomato. Total input energy was found to be 141493.51 and 131634.19 MJ ha À1 for cucumber and tomato productions, respectively. Among input energy sources, diesel fuel and fertilizers contained highest energy with 54.17 e49.02% and 21.64e24.01%, respectively. The energy ratio was found to be 0.69 and 1.48 for cucumber and tomato productions, respectively. Econometric model evaluation showed the impact of human labor for cucumber and chemicals for tomato was significant at 1% levels. Sensitivity analysis indicated that the MPP value of energy inputs were between À5.87 and 7.74. RTS (returns to scale) values for cucumber and tomato yields were found to be 1.29 and 0.76; thus, there prevailed an IRS of cucumber for estimated model. The net return was found positive, as 22651.13 and 78125.08 $ ha À1 for cucumber and tomato, respectively. The benefitecost ratios from cucumber and tomato productions were calculated to be 1.68 and 3.28, respectively. Among the surveyed greenhouses, the result indicated tomato cultivation was more profitable.

Download

Energy input–output analysis and application of artificial neural networks for predicting greenhouse basil production

In this study, various Artificial Neural Networks (ANNs) were developed to estimate the productio... more In this study, various Artificial Neural Networks (ANNs) were developed to estimate the production yield of greenhouse basil in Iran. For this purpose, the data collected by random method from 26 greenhouses in the region during four periods of plant cultivation in 2009e2010. The total input energy and energy ratio for basil production were 14,308,998 MJ ha À1 and 0.02, respectively. The developed ANN was a multilayer perceptron (MLP) with seven neurons in the input layer, one, two and three hidden layer(s) of various numbers of neurons and one neuron (basil yield) in the output layer. The input energies were human labor, diesel fuel, chemical fertilizers, farm yard manure, chemicals, electricity and transportation. Results showed, the ANN model having 7-20-20-1 topology can predict the yield value with higher accuracy. So, this two hidden layer topology was selected as the best model for estimating basil production of regional greenhouses with similar conditions. For the optimal model, the values of the models outputs correlated well with actual outputs, with coefficient of determination (R 2 ) of 0.976. For this configuration, RMSE and MAE values were 0.046 and 0.035, respectively. Sensitivity analysis revealed that chemical fertilizers are the most significant parameter in the basil production.

Download

Developing a GIS-based Fuzzy AHP Model for Selecting Solar Energy Sites in Shodirwan Region in Iran

The objective of this study is to use a Fuzzy Analytic Hierarchy Process (Fuzzy AHP) and geograph... more The objective of this study is to use a Fuzzy Analytic Hierarchy Process (Fuzzy AHP) and geographical mapping models using Geographical Information System (GIS) to locate the most appropriate sites for solar energy farms in Shodirwan region in Iran. GIS interpolation showed that annual solar insolation in Shodirwan is very good and can be used for potential solar farm locations. The average of solar insolation in the region is 5.12 kWh/m2/day annually. Results showed that 18.25% of the Shodirwan area is exploitable as solar farms. With a conversion efficiency of 10% and area factor of 70%, annual electricity production for the exploitable area is roughly 16100 GWh. Land suitability analysis for solar farms implementation was carried out and overlay results obtained from the analysis of the resultant maps showed that 13.98% and 3.79% of the total land area demonstrate high and good suitability levels, respectively. The total electricity generation potential from both highly and good suitability levels in Shodirwan region was about 15,690 GWh annually.

Download

Green Supplier Selection Using Fuzzy Group Decision Making Methods: A Case Study from the Agri- Food Industry

The incorporation of environmental criteria into the conventional supplier selection practices is... more The incorporation of environmental criteria into the conventional supplier selection practices is essential for organizations seeking to promote green supply chain management. Challenges associated with green supplier selection have been broadly recognized by procurement and supplier management professionals. The development and implementation of practical decision making tools that seek to address these challenges are rapidly evolving. This article contributes to this knowledge area by comparing the application of three popular multi-criteria supplier selection methods in a fuzzy environment. The incorporation of fuzzy set theory into TOPSIS, VIKOR and GRA methods is thoroughly discussed. The methods are then utilized to complete a green supplier evaluation and selection study for an actual company from the agri-food industry. Our comparative analysis for this case study indicates that the three fuzzy methods arrive at identical supplier rankings, yet fuzzy GRA requires less computational complexity to generate the same results. Additional analyses of the numerical results are completed on the normalization functions, distance metrics, and aggregation functions that can be used for each method.

Download

Some physical properties of full-ripe banana fruit (Cavendish variety)

Physical properties of fruits and vegetables are the subject of many researches because of its im... more Physical properties of fruits and vegetables are the subject of many researches because of its importance in designing of agricultural machinery. Banana fruit is one of important fruit. In this study some physical properties of banana fruit (Cavendish variety) were determined. Properties which were measured included weight of whole fruit peel and pulp weight, dimensions, surface area and projected area. The actual surface area and projected area were measured by image processing technique. The calculated attributes were geometric mean diameter, sphericity, radius of curvature, assumed ellipsoidal volume, surface area and projected area. The diameters of fruit varied as quadratic form. High correlation was observed among assumed ellipsoidal attributes and measured properties. The highest correlation was between estimated projected area and measured projected area as R 2 = 0.978. [Mahmoud Soltani et al. Some physical properties of full-ripe banana fruit (Cavendish variety).

Download

Detection of red ripe tomatoes on stem using Image Processing Techniques

Journal of American …, 2011

Image Processing Techniques are being used increasingly in the field of agricultural and food pro... more Image Processing Techniques are being used increasingly in the field of agricultural and food products for quality assurance purpose. The system offers the generation of precise descriptive data and reduction of tedious human involvement. Image segmentation based on color difference between mature fruits and backgrounds under natural illumination condition is a difficult task. By processing images in three color space of RGB, HSI and YC b C r from CCD camera, tomato fruit, stems, leaves and a stem-supporting pole were recognized. Then the processed images were compared in three color spaces in order to identify ripe tomatoes with more than 50% redness. The average of error between actual number of red tomatoes and estimated number in 3 images of each 28 tomato trees was 3.85%.

Download

Development of an Automated Machine for Grading Raisins based on Color and Size

In this paper, design and testing of a machine vision based raisin sorter is presented. The propo... more In this paper, design and testing of a machine vision based raisin sorter is presented. The proposed MV system consists of electronic, pneumatic and mechanical parts. The hardware is made up of a conveyor belt, eight pneumatic valves, a compressor and a control unit. The controller, which has a microcontroller as its main core, is used for the communication between the PC and the pneumatic valves via RS232 series port. By using the capture card, the camera sends images of raisins to the computer to be processed and have the raisins sorted accordingly. By a suitable combination of length and RGB color values raisins are graded it two classes. The PC sends proper commands, via the microcontroller, to actuators (valves) in order to reject defected raisins. The image processing algorithm has been implemented in Visual Basics environment. The developed program allows the user to easily configure the GUI in order to get high quality sorting results. To evaluate the performance of the sorter under various densities and impurities of raw raisins, as two factors affecting the accuracy of the sorter, some statistical tests were performed. The results of statistical analysis showed that with the existing number of valves, the optimum distance between two consecutive raisins should be 5 mm and the changes in the percentages of impurity does not have a significant effect on the overall performance of the machine on the level of 5%. Therefore, the sorter can provide a 99% pure output with less than 2% of loss.

Download

Adulteration detection in olive oil using dielectric technique and data mining

Olive oil is one of the most important agricultural crops due to its digestive properties and eco... more Olive oil is one of the most important agricultural crops due to its digestive properties and economic status. However , olive oil production is a costly process which causes an expensive price of the final product. The most job-bery ways during olive oil production consist of mixing other oils such as maize, sunflower and soya oil into the olive oil. So, the aim of this study was to develop a dielectric-based system to detect adulteration in olive oil using cylindrical capacitive sensor. For categorizing of fake olive oil by using frequency specification, Linear Discrimi-nant Analysis (LDA) was developed. A set of 15 samples of olive oil, sunflower oil and canola oil which mixed with different ratio of adulteration, were used for calibration and evaluation of developed system. For each sample , 25 iterations were performed. Regarding results, the highest error rate was for a sample containing 60% olive oil-40% canola oil. In general, 7 iterations failed to be properly recognized. Regarding to accuracy indexes, spec-ificity and sensitivity, the system had the minimum error for a mixed sample (60% olive oil-40% canola oil), spec-ificity and sensitivity were obtained as 98% and 100%, respectively and accuracy was obtained as 72%, which was the weakest value. Finally, regarding mean value table for all sample, accuracy reached to 97%. Results showed the developed technique has a good capability of detecting impurities in olive oil. It is concluded from obtained results that the developed system revealed an acceptable adulterated detection in oil production.

Download

Spatial and technological variability in the carbon footprint of durum wheat production in Iran

The purpose of this study was to quantify the spatial and technological variability in life cycle... more The purpose of this study was to quantify the spatial and technological variability in life cycle greenhouse gas (GHG) emissions, also called the carbon footprint, of durum wheat production in Iran. Methods The calculations were based on information gathered from 90 farms, each with an area ranging from 1 to 150 ha (average 16 ha). The carbon footprint of durum wheat was calculated by quantifying the biogenic GHG emissions of carbon loss from soil and biomass, as well as the GHG emissions from fertilizer application and machinery use, irrigation, transportation, and production of inputs (e.g., fertilizers, seeds, and pesticides). We used Spearman’s rank correlation to quantify the relative influence of technological variability (in crop yields, fossil GHG emissions, and N2O emissions from fertilizer application) and spatial variability (in biogenic GHG emissions) on the variation of the carbon footprint of durum wheat. Results and discussionThe average carbon footprint of 1 kg of durum wheat produced was 1.6 kg CO2-equivalents with a minimum of 0.8 kg and a maximum of 3.0 kg CO2-equivalents. The correlation analysis showed that variation in crop yield and fertilizer application, representing technological variability, accounted for the majority of the variation in the carbon footprint, respectively 76 and 21%. Spatial variation in biogenic GHG emissions, mainly resulting from differences in natural soil carbon stocks, accounted for 3% of the variation in the carbon footprint. We also observed a non-linear relationship between the carbon footprint and the yield of durum wheat that featured a scaling factor of −2/3. This indicates that the carbon footprint of durum wheat production (in kg CO2-eq kg−1) typically decreases by 67% with a 100% increase in yield (in kg ha−1 year−1). Conclusions Various sources of variability, including variation between locations and technologies, can influence the results of life cycle assessments. We demonstrated that technological variability exerts a relatively large influence on the carbon footprint of durum wheat produced in Iran with respect to spatial variability. To increase the durum wheat yield at farms with relatively large carbon footprints, technologies such as site-specific nutrient application, combined tillage, and mechanized irrigation techniques should be promoted.

Download

Temperature and relative humidity changes inside greenhouse

Better growing conditions are achieved in greenhouses by maintaining a higher internal ambient a... more Better growing conditions are achieved in greenhouses by maintaining a higher internal ambient as compared with external ambient temperature. A computer-based control and monitoring system which provides visualization, control and coordination of temperature and humidity in a greenhouse was recently developed. To validate the system performance, a number of experiments were carried out during the autumn of 2003. In this paper, one of the experimental results conducted from 10 to 12 a.m. on December 7, 2003, in the city of Karaj, is presented and discussed. The system was tested for two modes of operation: the uncontrolled mode of operation and the controlled mode. Four sensors, three for temperature measurements and one for relative humidity measurements, were installed inside and outside. During the first hour and a half the system was tested as a data-acquisition system, ie, only data from the sensors were recorded and monitored on the screen with no operation of fans, sprayer and other installed environmental systems in the greenhouse. For the last 20 min of the experiment, inside air temperature was controlled by the system. The result on temperature measurements shows that external ambient temperature, Tout, is always less than the inside temperature. This is attributed to the solar radiation entering the greenhouse through transparent plastic and being trapped there. We also observed fluctuations on temperature profile inside the greenhouse. This is caused by natural conditions such as surface evaporation within the greenhouse, solar radiation, external ambient temperature and rapid weather changes during the time of the experiment. It was also found that the rate of change of temperature increase in the upper part, Tup, ie near plastic cover, is higher than that of the plants height, Tmid. This rise in vertical temperature gradient is partly due to the different amount of solar incident radiation being received at the locations of sensors. This trend proves the effectiveness of our polytube system, a re- circulating fan with an attached perforated polyethylene tube, in guiding the air toward the plant root zone. For the last 20 min of the experiment, the controller was put into action. The overall per- formance of the system in maintaining the temperature within a given range, around the set point, is found to be satisfactory. The time constant of the fan and heater combination was short, about 10 min, in reaching the desired set point temperature.

Download

A review of macroalgae production, with potential applications in biofuels and bioenergy

This review discusses biofuel and bioenergy production from seaweed, and ranges from cultivation ... more This review discusses biofuel and bioenergy production from seaweed, and ranges from cultivation to final product, and investigates opportunities, problems, advantages, disadvantages and other issues of this emerging industry. High levels of structural polysaccharides and low lignin contents make seaweed attractive feedstocks for production of liquid biofuels via fermentation and biogas production via anaerobic digestion. Since macroalgae can be grown in water (oceans and lakes), they will not compete with land-based crops, and thus will not be in competition with human foods. And biofuel and bioenergy production from macroalgae has some environmental benefits. Electricity produced from biogas derived from macroalgae can be cost-competitive to solar thermal, solar photovoltaic and biomass generated electricity. Biofuel and bioenergy production from macroalgae, however, will entail higher costs than terrestrial biomass feedstocks due to higher costs of cultivation and higher costs to remove harmful content such as sulfur and nitrogen from the resulting fuel or heavy metals from the residues. Economic production of biofuels and bioenergy will be available by increasing the scale and efficiency of production of this emerging resource.

Comparing data mining classifiers for grading raisins based on visual features

Computers and Electronics in Agriculture, 2012

In this study, quality grading of raisins using image processing and data mining based classifier... more In this study, quality grading of raisins using image processing and data mining based classifiers was investigated. Images from four different classes of raisins (green, green with tail, black, and black with tail) were acquired using a color CCD camera. After pre-processing and segmentation of images, 44 features including 36 color and eight shape features were extracted. Correlation-based feature selection was used to select best features for grading the raisins. Seven features were found superior. To classify raisins, four different data mining-based techniques including artificial neural networks (ANNs), support vector machines (SVMs), decision trees (DTs) and Bayesian networks (BNs) were investigated. Results of validation stage showed ANN with 7-6-4 topology had the highest classification accuracy, 96.33%. After ANN, SVM with polynomial kernel function (95.67%), DT with J48 algorithm (94.67%) and BN with simulated annealing learning (94.33%) had higher accuracy, respectively. Results of this research can be adapted for developing an efficient raisin sorting system.

Download

Principles and Applications of Light Backscattering Imaging in Quality Evaluation of Agro-food Products: A Review

Food and Bioprocess Technology, 2012

Abstract In recent years, due to the increasing consciousness of quality in the food and health s... more Abstract In recent years, due to the increasing consciousness of quality in the food and health sector, much progress has been made in developing non-invasive techniques for the evaluation or inspection of internal qualitative parameters of fruits, vegetables, and processed foodstuffs considering, eg, moisture content, soluble solid content, acidity, and mechanical properties. This paper reviews the theoretical and technical principles as well as the recent achievements and applications of light backscattering imaging for ...

Data mining-based wavelength selection for monitoring quality of tomato fruit by backscattering and multispectral imaging

International Journal of Food Properties, 2014

ABSTRACT The aim of this research was to predict quality factors of tomato fruit during storage u... more ABSTRACT The aim of this research was to predict quality factors of tomato fruit during storage using backscattering and multispectral imaging techniques. To gather the required information for developing prediction models, batches of 200 tomatoes (cv. Pannovy) harvested at two maturity stages, were stored at standard condition up to four weeks. During storage, the modulus of elasticity, moisture content (MC), soluble solid content (SSC), titratable acidity (TA), hyperspectral data, and backscattering images were acquired on forty tomatoes at regular intervals of one week. After extracting the spectral data from forty points on each sample, they were subjected to preprocessing operations. Several feature selection techniques, including filter (ReliefF, Fisher-Score, and t-Score) and wrapper (genetic algorithm) methods were used to find the sensitive wavelengths for each fruit quality parameter. With the novel strategy used, the wavelengths found by the fusion of genetic algorithm and t-Score techniques showed good prediction performance for all considered qualitative parameters. In order to verify the usefulness of selected wavelengths, backscattering and multispectral imaging techniques were applied. The ANN produced the calibration models which gave a reasonably good correlation for estimating the modulus of elasticity, SSC and TA at 660 nm and MC at 830 nm of tomato from backscattering images. The correlation coefficient between the multispectral and backscattering imaging prediction results and reference measurement results were 0.952 and 0.891 for modulus of elasticity, 0.727 and 0.539 for MC, 0.736 and 0.561 for SSC, and 0.811 and 0.706 for TA, respectively. It can thus be concluded that proposed wavelength selection strategy is potentially useful for assessing quality of horticultural products by multispectral and backscattering imaging techniques.

Analysis of texture-based features for predicting mechanical properties of horticultural products by laser light backscattering imaging

Computers and Electronics in Agriculture, 2013

ABSTRACT Light backscattering imaging is an advanced technology applicable as a non-destructive t... more ABSTRACT Light backscattering imaging is an advanced technology applicable as a non-destructive technique for monitoring quality of horticultural products. Because of novelty of this technique, developed algorithms for processing this type of images are in preliminary stage. The present study investigates the feasibility of texture-based analysis and coefficients from space-domain analysis to develop better models for predicting mechanical properties (fruit flesh firmness or elastic modulus) of horticultural products. Images of apple, plum, tomato, and mushroom were acquired using a backscattering imaging setup capturing 660 nm. After segmenting the backscattering regions of images by variable thresholding technique, they were subjected to texture analyses and space domain techniques in order to extract a number of features. Adaptive neuro-fuzzy inference system models were developed for firmness or elasticity prediction using individual types of feature sets and their combinations as input for prediction model applicable in real-time applications. Results showed that fusion of the selected feature sets of image texture analysis and space domain techniques provide an effective means for improving the performance of backscattering imaging systems in predicting mechanical properties of horticultural products. The maximum value of correlation coefficient in the prediction stage was achieved as 0.887, 0.790, 0.919, and 0.896 for apple, plum, tomato, and mushroom products, respectively.

Mahmoud Omid

Uploads

Papers by Mahmoud Omid

Log In