roya farhadi; Amir Hossein Afkari Sayyah; Bahareh Jamshidi; ahmad mousapour gorji
Abstract
Potato storage is essential to ensure the continued supplying of potatoes to consumers and the potato processing industry. During storage, physiological changes and water loss lead to changes in color, shape, size, and texture of potatoes. Therefore, there is a need for a quick and accurate method to ...
Read More
Potato storage is essential to ensure the continued supplying of potatoes to consumers and the potato processing industry. During storage, physiological changes and water loss lead to changes in color, shape, size, and texture of potatoes. Therefore, there is a need for a quick and accurate method to measure the quality of the product. In this study, machine vision and neural network methods were used in classification and modeling of two stored potato samples (Agria and Clone 8-397009) under constant and variable conditions. Among 29 measured parameters relating to color, texture and morphological features of potato, some features were selected as the main parameters to monitor the chnges in product during storage period: Major Axis Length, Compactness, and area (morphological features), L* and b* (color features) and Average contrast (Ac) and Average gray level (Agl) (texture features). Among the training algorithms, Levenberg–Marquardt (LM) training algorithm with the lowest root mean square error (RMSE=0.012) and the highest coefficient of determination (R2=95.01) were considered as an optimal model for classification of two samples stored in non-technical and technical storage. The accuracy of identification of the Agria genotype was 89.2% and 87.6%, and the accuracy of the genotype Clone 8-397009 was 92.4% and 90.3%, in non-technical and technical storage respectively.
Sajad Sabzi; Yousef Abbaspour-Gilande; Hosein Javadikia
Abstract
The weeds must be removed from the field due to their competition with principal crops to use water, nutrients, sunlight, etc. There are different methods to remove the weeds: mechanically, manually or chemically (applying herbicides). For farmers, applying herbicides is a usual way, but brings some ...
Read More
The weeds must be removed from the field due to their competition with principal crops to use water, nutrients, sunlight, etc. There are different methods to remove the weeds: mechanically, manually or chemically (applying herbicides). For farmers, applying herbicides is a usual way, but brings some concerns, from the point of environmental issues, due to equal application of chemicals all over fields, regardless the presence or absence of weed. For this reason, a machine vision system based on video processing was proposed to recognize Secale cereale L. (as a weed) from potato plant (as principal crop) to make herbicide application more accurate. Nine hundred sixty five objects were recognized after taking videos, pre-processing and segmentation. Fourteen features were extracted from each object. Using the hybrid artificial neural network-genetic algorithm, of 14 extracting features, only 6 features were selected as effective ones: average, the third moment, autocorrelation, correlation, dissimilarity, and entropy. Data were classified into two groups: training data (70% of the total data) and testing data (30% of the total data). The classification was performed using hybrid of artificial neural network - Bio-geography Based Optimization (BBO) algorithm. Performance of classification system was evaluated through analysis of confusion matrix and Receiver Operating Characteristic (ROC). Sensitivity, specificity, and accuracy were calculated using confusion matrix. The results showed that the sensitivity, accuracy and specificity of classification system reached to an acceptable level: 99.49 %, 99.65% and 98.91%, respectively. Our conclusion is that it is possible to manufacture the machine vision system with mentioned aims that work as online.
H. Orak; S. Abdanan-Mehdizadeh
Abstract
A large amount of herbicide is being used for controlling weeds in agricultural, lawns, sport fields on yearly basis. This causes environmental pollution and economic concerns. To reduce the use of herbicides, hand labor may be the best way of removing weeds. It is, however, costly and time consuming. ...
Read More
A large amount of herbicide is being used for controlling weeds in agricultural, lawns, sport fields on yearly basis. This causes environmental pollution and economic concerns. To reduce the use of herbicides, hand labor may be the best way of removing weeds. It is, however, costly and time consuming. In this paper, two methods of distinguishing weeds from lawns using computer vision techniques are proposed. Due to the fact that the weeds have different colors and identification of them from grass is not possible; therefore, an algorithm was developed based on the assumption that the grass area should contain more edges while the weed area is smoother than the grass area. For identification of weed/grass two methods were used, namely: Bayesian Classifier (BO) and morphology (MO. Results indicated that correct weed identification rates for MO and BO methods were 89.58% and 80.42% respectively. Furthermore, from results obtained it can be concluded that herbicide usage was reduced more than 70%, which from economical point of view as well as reduction of environmental pollution is of great importance.
Amir Hossein Afkari Sayyah; Hamid Reza Mohammad Doust Chaman Abad; Mansour Rasekh; Mahsa Sadat Razavi
Abstract
Machine vision technology can be used to detect the location of weeds around the main crop in a field as the machine moves, in order to decrease the losses of using herbicides. The purpose of this research is to determine the accuracy of image processing method in discriminating weeds from potato crop ...
Read More
Machine vision technology can be used to detect the location of weeds around the main crop in a field as the machine moves, in order to decrease the losses of using herbicides. The purpose of this research is to determine the accuracy of image processing method in discriminating weeds from potato crop according to color features. Therefore, by performing a research which conducted in university of Mohaghegh Ardabili research field, three factors including: environmental light condition, type of weed (Shalambig, Pichack and Wheat), and level of crop growth, were investigated on discrimination accuracy. The results of this research were showed that there are no significant differences between two types of environmental light conditions. However, the main and interactive effects of two factors of type of weeds and level of crop growth was significant on discriminating system performance. According to this study, the first stage of crop growth is the best time for the visual tests (middle of the June) and among the three types of popular weed in the region, it is possible to discriminate the wheat from potato leaves with a reasonable accuracy according to RGB color model. By this method, it is possible to determine the location of weeds around the main crop by maximum accuracy of 95% dependent to different condition of treatments.
Abstract
The current study developed and tested machine vision and automatic control systems to improve performance and reduce rice loss during paddy husking. This system was optimally adjusted for paddy type, moisture content of paddy, roller spacing and rotational speed of the motor. The percentage of breakage ...
Read More
The current study developed and tested machine vision and automatic control systems to improve performance and reduce rice loss during paddy husking. This system was optimally adjusted for paddy type, moisture content of paddy, roller spacing and rotational speed of the motor. The percentage of breakage of rice kernels was determined using a machine vision system and a singulation device. If rice breakage was greater than a set point, the husker device was adjusted as necessary. The variables of paddy moisture content, roller spacing, and motor rotational speed were used to determine the working conditions of the husker for two paddy varieties. The dependent variables were husking index and rice kernel breakage percentage. An image processing algorithm was coded and evaluated in MATLAB software to determine the percentage of rice kernel breakage. The results showed that selection of proper treatment for the medium-sized kernel paddy, the average husking index was 82.65% and the average rice breakage was 3.88%. For the long kernel paddy, the average husking index and rice breakage were 51.4% and 27.46%, respectively. Without use of the system and with improper selection of motor rotational speed and roller spacing in the medium-sized kernel paddy produced a husking index of 61.58% and rice breakage of 7.51%. For the long kernel paddy, the husking index was 19.14% and rice breakage was 35.03%. Results from the algorithm showed that its accuracy was 91.81%. Evaluation of the singulation device showed that a suction of -45 to -50 mmHg yielded an appropriate 81.3% separation efficiency. The best combination of the machine parameter levels were programmed into the system, which operated to make the proper adjustments automatically. This resulted in the most appropriate working conditions for husking in accordance with paddy variety, paddy moisture content, roller spacing, and motor rotational speed.