Papers by Yousef Abbaspour-Gilandeh
Each variety has own special advantages; so variety recognition or ensuring from validity of pres... more Each variety has own special advantages; so variety recognition or ensuring from validity of presented variety is very important in all farming stages and most importantly in postharvest stage; because it is effective immediately in harvested yield and the quality of processed products. Available techniques for rice variety identification are time consuming and expensive; also there are destructive. So study and presentation of new methods sounds necessary. Therefor the aim of this reaserch was extraction of color, morphological and texture properties for thirteen common varieties of Iranian rice and classification them using computational intelligence. In this research, digital images of twelve common rice varieties in Iran acquisitioned at three states including paddy, brown rice and white rice. After the preprocessing and segmentation processes on images using MATLAM software ninety two properties extracted for each rise seed; contain sixty color properties, fourteen morphological properties and eighteen texture properties. After checking for normality of data, probability of significant of differences between varieties evaluted by analysis of variance (ANOVA) for all properties; and used from least significant difference(LSD) test to compare varieties with more accurate. Principal component analysis(PCA) used for reduction of data dimensions and concentrate on effective components in varieties identification. Separating accuracy of paddy, brown rice and white rice varieties using discriminant analysis (DA) was obtained 89.2%, 87.7% and 83.1% respectively. A multi-layer perceptron neural network desiged based on principal components for identification and classification of rice varieties, and it has trained with levenberg-marquardt algorithm. Resultes show that this artificial neural network classified all varieties in accuracy of 100% with the regression coefficient of 0.9998. So it can be said that combining image processing techniques with different pattern recognition methods shch as statistics classifiers and artificial neural networks is very useful in identification and classification of rice varieties.
Resources
The energy crisis and depleting fossil fuel resources have always been the focus of researchers. ... more The energy crisis and depleting fossil fuel resources have always been the focus of researchers. Fuel consumption of agricultural tractors is not an exception. Researchers have used different methods to predict fuel consumption. With the development of artificial intelligence in the last decade, all re-searchers’ attention has been directed towards it. Deep learning is a subset of machine learning, which was inspired by the data processing patterns in the human brain. The deep learning method has been used in research due to the advantages of high accuracy and generalization. So far, no research has used this method to predict fuel consumption. In this research, field experiments were carried out in sandy clay loam and clay soils to model the temporal fuel consumption and specific fuel consumption of an agricultural tractor using a convolutional neural network (CNN), while having some parameters such as the soil type, soil conditions, tool parameters, and operation pa-rameters. The ...
Horticulturae
Currently, destructive methods are often used to measure the quality parameters of agricultural p... more Currently, destructive methods are often used to measure the quality parameters of agricultural products. These methods are often complex, time consuming and costly. Recently, studying to find a solution to the disadvantages of destructive methods has become a major challenge for researchers. Non-destructive methods can be useful for the rapid detection of the quality parameters of agricultural products. In this study, hyperspectral imaging was used to evaluate the non-destructive quality parameters of Red Delicious (Red Delicious) and Golden Delicious (Golden Delicious) apples, including pH, soluble solids content (SSC), titratable acid (TA) and total phenol (TP). In order to predict the quality characteristics of apples, the partial least squares (PLS) method with different pre-processing was used. The developed models were evaluated using the root mean square parameters of RMSECV validation error, correlation coefficient (Rcv) and standard deviation ratio (SDR). The results showe...
Acta Technologica Agriculturae
The final yield of agricultural products depends on the effective factors during the growing seas... more The final yield of agricultural products depends on the effective factors during the growing season of plants, especially the size of soil aggregates and proper size distribution of aggregates. Therefore, it is very important to select appropriate tillage implement and to provide a suitable seedbed in terms of aggregate size with the least energy consumption. It is a new idea to use paraplough and winged-paraplough as tools for seedbed preparation. To measure and determine the factors affecting the mean weight diameter (MWD) of aggregates and percentage of crop residues on the soil surface, a series of field trials were performed in a randomized complete block design (RCBD) with five replications. The trials were conducted at three forward speeds of 2, 5 and 7 km·h−1 and three operating depths of 0–10; 0–20; 0–30 cm using the mouldboard plough and the paraplough with different wing configurations (without wings, with forward wings, with backward wings). The main impacts of implement...
International Journal of Fruit Science
Journal of Terramechanics
Applied Sciences
There are many methods to detect plant pests and diseases, but they are primarily time-consuming ... more There are many methods to detect plant pests and diseases, but they are primarily time-consuming and costly. Computer vision techniques can recognize the pest- and disease-damaged fruits and provide clues to identify and treat the diseases and pests in their early stages. This study aimed to identify common pests, including the apple capsid (Plesiocoris rugicollis)/AC, apple codling moth (Cydia pomonella)/ACM, Pear lace bug (Stephanitis pyri)/PLB, and one physiological disease-apple russeting/AR in two cultivars, Golden Delicious and Red Delicious, using the digital image processing and sparse coding method. The Sparse coding method is used to reduce the storage of the elements of images so that the matrix can be processed faster. There have been numerous studies on the identification of apple fruit diseases and pests. However, most of the previous studies focused only on diagnosing a pest or disease, not on computational volume reduction and rapid detection. This research focused o...
Applied Sciences
To use machine vision technology in visual quality control of cereal seeds, sufficient knowledge ... more To use machine vision technology in visual quality control of cereal seeds, sufficient knowledge is necessary. In this work, the capability of machine visual systems, equipped with industrial digital cameras for the identification and classification of seven-grain groups in wheat seed samples, was studied. Two statistical models and three support vector machines were employed in this study. Through image processing of 21,000 single grains, the shape, colour, and textural features of each grain were determined. Ninety-one features were ranked through the ReliefF method. The shape features were the most prominent, followed by the textural and colour features. Among the five models tested, the highest classification accuracy was obtained using quadratic support vector machine (QSVM) and the first 35 features. In the test run of this model with independent data, the classification accuracy for sound white wheat, small white wheat, broken white wheat, shrunken white wheat, red wheat, bar...
Processes
The purpose of this work was to investigate the detection of the pesticide residual (profenofos) ... more The purpose of this work was to investigate the detection of the pesticide residual (profenofos) in tomatoes by using visible/near-infrared spectroscopy. Therefore, the experiments were performed on 180 tomato samples with different percentages of profenofos pesticide (higher and lower values than the maximum residual limit (MRL)) as compared to the control (no pesticide). VIS/near infrared (NIR) spectral data from pesticide solution and non-pesticide tomato samples (used as control treatment) impregnated with different concentrations of pesticide in the range of 400 to 1050 nm were recorded by a spectrometer. For classification of tomatoes with pesticide content at lower and higher levels of MRL as healthy and unhealthy samples, we used different spectral pre-processing methods with partial least squares discriminant analysis (PLS-DA) models. The Smoothing Moving Average pre-processing method with the standard error of cross validation (SECV) = 4.2767 was selected as the best model...
: The research was divided into three main sections. In first part, the effect of tine type, forw... more : The research was divided into three main sections. In first part, the effect of tine type, forward speed and wing type were investigated on the draft, vertical and lateral forces, disturbance area, specific draft, tractor fuel consumption, furrow compactness, soil fragmentation and buried residue with conventional subsoiler, Paraplow and bentleg. Moreover, due to more vast application of conventional subsoiler when compared to the Paraplow and bentleg in Iran and in the Middle East, the effect of conventional tine depth and its forward speed were investigated on draft, disturbance area, specific draft, tractor fuel consumption, wheel slippage, drawbar power, traction efficiency and overall energy efficiency. In the third stage, the imposed forces on dual bentleg tines were investigated at different speeds in comparison with the single tine. For conducting trials, factorial statistical design based on randomized complete blocks design was applied at four replications. In first part, the tine in three tine types (subsoiler, Paraplow and bentleg), forward speed in four levels (1.8, 2.3, 2.9 and 3.5 km/h) and different wings in six types (no wing, conventional wing, forward and backward wing with 10 and 20 degree tilt angle) were investigated. In the second stage, the conventional subsoiler at four forward speeds of 1.8, 2.3, 2.9 and 3.5 km/h and two depths of 40 and 50 cm was evaluated. In the third stage, dual shanks of bentleg at mentioned forward speeds were examined. The results of first trial showed that bentleg and conventional subsoiler had the best and worst performance, respectively in terms of measured performance parameters. Lower speeds showed better subsoiling results; furthermore, wing application in specific condition and in accordance with the tillage goals is advised. Evaluation of different wings showed that 10 degrees forward bent wing had the best performance and is a suitable alternative instead of conventional wing. The second trials results showed that the optimal tillage depth and speed for conventional subsoiler were 40 cm and 2.9 km/h, respectively. Energy saving was obtained with suitable combination of tractor and implements and operation conditions. The results of the third trial approved that use of dual tine implement was more suitable than single shank implement especially for the balance of implements like Paraplow and bentleg.
Machine vision is a way of converting an image digitally and performing operations on it to get a... more Machine vision is a way of converting an image digitally and performing operations on it to get an improved image or to extract some important information from it. This technology is hundreds times more accurate, faster and more functional than the human eye with the least error. Therefore, it is very practical in various industries and agriculture, and it is also much considered in biosystem. so there is a lot of research on various issues in this field and is still expanding. In the present study, the ability of this system has been exploited. For this purpose, the analysis of red delicious apple has been considered and using the color model and texture indices have been investigated using MATLAB software image processing toolbox. On the other hand, two important laboratory indicators in the analytical analysis, which include the index of brix and product rigidity, have been evaluated. Finally, the results of image processing and the results of the Brix and firmness index were ana...
Application of variable rate technology (VRT) of fertilizer on the farm is a major pillar of prod... more Application of variable rate technology (VRT) of fertilizer on the farm is a major pillar of production accurate management that increases fertilization efficiency and reduces environmental pollution. The main purpose of this study is to investigate the possibility of determining of tomato nitrogen deficiency during the growing season using a digital camera and digital image processing. Using these methods causes less damage to the plant. Though, using this technology requires accurate and continuous determination of plant nitrogen status on the farm during of growth stages. Therefore 18 plots of Spring tomato by six different levels of fertilization (0, 60, 120, 180, 240, 300 Kg/ha) with three repetition in completely randomized designs were sown in plastic pots with a diameter of 25 cm. It was attempted to be fertilized after the growing wheat in generative step of plant. The nitrogen content of leaves was measured by two methods; 1-using chlorophyll meter (SPAD) and 2- doing Kjel...
Chickpea (Cicer arietinum) is one of crops with high protein that have high consumption in Iran a... more Chickpea (Cicer arietinum) is one of crops with high protein that have high consumption in Iran and world. There are five popular species of chickpeas in Iran: Adel, Arman, Azad, Bevanij and Hashem. Each type has a price and special applications in food industry. A machine vision system for chickpea classification, alternative to the traditional manual methods, would be able to increase accuracy and speed in packing. In order to design the classifiers for this system, samples of these five species were prepared from Kermanshah. 1019 images were taken using an industrial camera DFK23GM021 (CMOS, 120 fps) from a 10 cm fixed height above the samples level. Lighting was performed by white color LED lamps with intensity of 327 lx. From each image 126 color-based, and 80 texture-based on the gray level co-occurrence matrix (GLCM) were extracted. Using hybrid artificial neural network particle swarm optimization (ANN-PSO) 6 effective features were selected: information measure of correlati...
Tomato maturity is one of the most important factors associated with the quality of processed tom... more Tomato maturity is one of the most important factors associated with the quality of processed tomato products. Tomato maturity has been related to quantifiable parameters, which reflect the biochemical changes during ripening. During ripening, tomato fruit go through a series of highly ordered physiological and biochemical changes. Biochemical changes, such as increased respiration, chlorophyll degradation, biosynthesis of carotenoids, starch degradation, and increased activity of cell wall degrading enzymes, bring on changes in color, firmness, and development of aromas and flavors. Lycopene, as a major carotenoid pigment found in tomato, is responsible for its red color and its amount is related to its ripening. The purpose of this study was to determine the correlation between tomato color with lycopene and rigidity and its TSS, which is an indicator of tomato maturity. If a correlation can be established between the color index of the product and its physical and chemical parame...
Moisture content of cereal grains is one of the most important characteristics for determining qu... more Moisture content of cereal grains is one of the most important characteristics for determining quality of grains. In this research, image features of five varieties of wheat provided by the Natural Resources and Agricultural Research Center of Ardabil province were characterized in five moisture levels ranging 8-14% to develop a moisture prediction model. A specially designed metallic dome as a light scatterer and a 10 MP, DSLR camera on top of it were used for the purpose of imaging. MATLAB R2013a was used for extracting the image features. Three sets of image features were extracted from the wheat imags, including color features: RGB, HSV and Lab, morphological features: area, perimeter, major and minor axis, eccentricity, solidity, compactness, roundness, area ratio and aspect ratio and texture features: mean, standard deviation, histogram symmetry, intensity, uniformity and anthropy. Then the statistical analysis were conducted using MSTATC software. The results showed that the ...
Rice is among the oldest cereals, constituting the basic food for the large number of our country... more Rice is among the oldest cereals, constituting the basic food for the large number of our country population. This crop is influenced by a large number of static and dynamic forces during harvest, transport and other stages of the process. Mechanical properties of paddy rice affects greatly on the milling process. Grain moisture content is an effective factor on the mechanical properties of the grain. During grain drying process, increasing grain strength decreases the grain waste. At this study, compressive strength, maximum normal and shear stress of two paddy rice varieties (Hashemi and Alikazemi), at two levels of grain moisture content (8 and 12% w.b.), under different angles between applied force and straight posed grain on surface (15, 30, 45, 60, 75, and 90 degrees) and two grain positions on tilted surface (at straight of tilted surface and perpendicular to first straight), were determined and analyzed. The results of variance analysis showed that the effects of grain moist...
Uploads
Papers by Yousef Abbaspour-Gilandeh