Image Processing
M. Fallah; E. Ghanbari Parmehr
Abstract
IntroductionRice is one of the most important main food sources in Iran and the world. The correct identification of the type of pest in the early stages of preventive action has a significant role in reducing the damage to the crop. Traditional methods are not only time-consuming but also provide inaccurate ...
Read More
IntroductionRice is one of the most important main food sources in Iran and the world. The correct identification of the type of pest in the early stages of preventive action has a significant role in reducing the damage to the crop. Traditional methods are not only time-consuming but also provide inaccurate results, As a result, precision agriculture and its associated technology systems have emerged. Precision agriculture utilizes information technology such as GPS, GIS, remote sensing, and machine learning to implement agricultural inter-farm technical measures to achieve better marginal benefits for the economy and environment. Machine learning is a division of artificial intelligence that can automatically progress based on experience gained. Deep learning is a subfield of machine learning that models the concepts of using deep neural networks with several high-level abstract layers. This capability has led to careful consideration in agricultural management. The diagnosis of disease and predicting the time of destruction, with a focus on artificial intelligence, has been the subject of much research in precision agriculture. This article presents, in the first step, a trained model of the Chilo suppressalis pest using data received from the smartphone, validated with the opinion of experts. In the second step, we introduce the developed system based on the smartphone. By using this system, farmers can share their pest images through the Internet and learn about the type of pest on their farm, and finally, take the necessary measures to combat it. This operation is done quickly and efficiently using the developed artificial intelligence. In the continuation of the article, the second part introduces the materials and methods, and the third part presents the results. The fourth section also discusses and concludes the research.Materials and MethodsChilo suppressalis is one of the most important pests of rice in temperate and subtropical regions of Asia. The conventional approach employed by villagers to gather the Chilo suppressalis pest entails setting up a light source above a pan filled with water infused with a pesticide. At sunset, these insects are attracted to the light and fall into the water in the pan. This method is known as optical trapping. After catching the pest using optical traps, they are collected from the water surface, and their photo is taken with a mobile phone based on the location of the optical trap.The proposed method in this research consists of three main steps. Firstly, the farmer utilizes the software provided by the extended version known as Smart Farm. The farmer captures an image of the Chilo suppressalis pest and sends it along with its location to the system. The Smart Farm software program carries out image processing and pest range detection operations. The user then verifies the accuracy of the pest detection. In the second step, the images sent by the farmer are processed by the pre-trained model within the system. The model analyzes the images and determines the presence of the pest. Finally, after identifying the type of pest, the results, along with recommended methods for pest control, are sent back to the farmer.In summary, In this method, farmers employ the Smart Farm software to capture and transmit images of the Chilo suppressalis pest. The captured images then undergo image processing and pest range detection as the next steps in the process. The results, including pest identification and control methods, are then returned to the farmer.Results and DiscussionThe model has been designed with 400 artificial neural network processing units (APCs), achieving accuracy percentages of 88% and 92%. To conduct a more detailed study of the proposed model, the statistical criteria of recall and F-score were used. Based on the calculations, the trained model demonstrated a recall score of 91%. This criterion shows that the model was able to identify a large percentage of what was expected to be identified by the model. Additionally, the F-score, with an acceptable percentage of 88%, confirmed the accuracy of the trained model.ConclusionResearchers have always been highly interested in the valuable data freely provided by farmers for their studies and analyses. In this study, an intelligent system was designed for identifying types of pests such as worms and stalk eaters, which can automatically determine the pest type from the image sent by the farmer using artificial intelligence and deep learning. By utilizing the developed system, farmers can be informed of the type of pest present on their farm in the shortest possible time, with minimal required software training.
