A Survey on Diseases Detection and Classification of Agriculture Products using Image Processing and Machine Learning

Abstract

Quality agriculture production is the essential trait for any nation's economic growth. So, recognition of the deleterious regions of plants can be considered as the solution for saving the reduction of crops and productivity. The past traditional approach for disease detection and classification requires enormous amount of time, extreme amount of work and continues farm monitoring. In the last few years, advancement in the technology and researchers' focus in this area makes it possible to obtain optimized solution for it. To identify and detect the disease on agriculture product various popular methods of the fields like machine learning, image processing and classification approaches have been utilized. This paper presents various existing techniques used to detect the disease of agriculture product. Also, paper surveys the mythologies utilized for disease detection, segmentation of the affected part and classification of the diseases. It also includes the summary of various feature extraction techniques, various segmentation techniques and various classifiers along with benefits and drawbacks.

Convolutional Neural Networks for Texture Feature Extraction. Applications to Leaf Disease Classification in Precision Agriculture

“…In [6], colour information is used along with GLCM -derived features and Gabor characteristics for the classification of mango leaves. Deep-learning methods are also mentioned for the classification of plant diseases in [7]- [9].…”

“…Until recently, [7], [9], the problem of image classification has been addressed as a two-stage approach: the extraction of handcrafted features and machine-learning classification. The feature extraction step is regarded as the most important stage because the subsequent classification task is based on the derived image descriptors.…”

“…However, lately, [7], [9], impressive results were obtained with the use of deep-learning methods, revolutionising the image and object classification field. Rather than relying on handcrafted features, these methods can be used as end-to-end approaches because they work by automatically learning the relevant features themselves, without the need of expertise, from the raw data provided as input.…”

“…The Convolutional Neural Network (CNN) is a deeplearning technique that has been widely used in the past years with great success for many computer vision tasks, [1], [7], [9], [16]. The architecture of a CNN is composed of several types of layers: convolutional, nonlinear, pooling, fully connected, normalization and others.…”

A Survey on the New Generation of Deep Learning in Image Processing

“…technique to be used in medical images, remote sensing image and nature image [4] (see Fig.1), and generally, is used because it is not only the most versatile method but also the cheapest [5]. Image processing has been playing a more vital and essential role in various information access systems to enhance the cognition level and facilitate decisionmaking process [6]. In pattern recognition and machine learning, the commonly used image processing includes image generation, image compression and encoding, image deblurring, super-resolution, image segmentation, classification and object recognition, change detection, image annotation, and image retrieval, etc.…”