Название: Computer Vision and Machine Learning in Agriculture
Автор: Mohammad Shorif Uddin, Jagdish Chand Bansal
Издательство: Springer
Год: 2021
Страниц: 180
Язык: английский
Формат: pdf (true), epub
Размер: 41.6 MB

This book discusses computer vision, a noncontact as well as a nondestructive technique involving the development of theoretical and algorithmic tools for automatic visual understanding and recognition which finds huge applications in agricultural productions. It also entails how rendering of Machine Learning techniques to computer vision algorithms is boosting this sector with better productivity by developing more precise systems. Computer vision and machine learning (CV-ML) helps in plant disease assessment along with crop condition monitoring to control the degradation of yield, quality, and severe financial loss for farmers.

Significant scientific and technological advances have been made in defect assessment, quality grading, disease recognition, pests, insects, fruits, and vegetable types recognition and evaluation of a wide range of agricultural plants, crops, leaves, and fruits. The book discusses intelligent robots developed with the touch of CV-ML which can help farmers to perform various tasks like planting, weeding, harvesting, plant health monitoring, and so on. The topics covered in the book include plant, leaf, and fruit disease detection, crop health monitoring, applications of robots in agriculture, precision farming, assessment of product quality and defects, pest, insect, fruits, and vegetable types recognition.

Chapter “Detection of Rotten Fruits and Vegetables Using Deep Learning” describes a computer vision-based deep convolutional neural network for the detection of rotten fruits and vegetables. It performs experimentation with a dataset containing enough number of images of fresh and rotten fruits and confirms that the proposed deep learning architecture outperforms the existing approaches. Chapter Deep Learning-Based Essential Paddy Pests’ Filtration Technique for Economic Damage Management” illustrates a region-based deep convolutional neural network known as Faster R-CNN to perform the detection and identification of both beneficial and non-beneficial paddy pests from the images. It has investigated three models of Faster R-CNN based on ResNet-101, VGG-16, and MobileNet and has obtained the highest accuracy from the ResNet-101-based Faster R-CNN. Besides, it developed an extensive dataset of paddy pests. Chapter “A Deep Learning-Based Approach for Potato Disease Classification” investigates an early detection of potato disease through different deep CNN strategies by developing a dataset containing 7870 images of various diseases. Based on accuracy, precision, recall, and F1 score it finds that the ResNet is the best model for this particular application.