A Review of Image Processing Techniques Common in Human and Plant Disease Diagnosis

Abstract

Image processing has been extensively used in various (human, animal, plant) disease diagnosis approaches, assisting experts to select the right treatment. It has been applied to both images captured from cameras of visible light and from equipment that captures information in invisible wavelengths (magnetic/ultrasonic sensors, microscopes, etc.). In most of the referenced diagnosis applications, the image is enhanced by various filtering methods and segmentation follows isolating the regions of interest. Classification of the input image is performed at the final stage. The disease diagnosis approaches based on these steps and the common methods are described. The features extracted from a plant/skin disease diagnosis framework developed by the author are used here to demonstrate various techniques adopted in the literature. The various metrics along with the available experimental conditions and results presented in the referenced approaches are also discussed. The accuracy achieved in the diagnosis methods that are based on image processing is often higher than 90%. The motivation for this review is to highlight the most common and efficient methods that have been employed in various disease diagnosis approaches and suggest how they can be used in similar or different applications.

Plant disease diagnosis using image processing techniques -A review on machine and deep learning approaches

“…Remote sensing tools such as proximal, airborne, and/or satellite hyperspectral imaging tools are nowadays commonly used to assess agricultural conditions, and these (particularly proximal and/or air-borne hyperspectral imaging) could be utilized for plant disease diagnosis techniques (Barbedo, 2013;Renugambal and Senthilraja, 2015). Prospective of such imaging tools along with their processing approaches for plant disease identification and monitoring have meticulously reviewed by many researchers (Barbedo, 2013(Barbedo, , 2016Golhani et al, 2018;Martinelli et al, 2015;Ngugi et al, 2020;Petrellis, 2018).…”

“…Iqbal et al (2018) have summarized several Classifiers techniques with their advantages and limitations. Literature review shows that considerable developments have been made in the image processing and machine learning algorithms to diagnose diseased plants (Golhani et al, 2018;Ngugi et al, 2020;Petrellis, 2018;Singh et al, 2021;Sun et al, 2018). Along with imaging techniques, Innovative approaches such as machine and deep learning algorithms have been explored for accurate detection and diagnosis of diseased plants.…”

Plant pest surveillance: from satellites to molecules

“…Most types of crop pests and diseases cause visible symptoms that can be recognized by a trained person, but few such people are accessible to farmers, particularly in the developing world. To overcome this, a smartphone can be used to capture an image of the symptoms which is then sent via the internet to a platform where human experts can make the diagnosis [40][41][42]. An alternative strategy is based on artificial intelligence and machine learning methods that enable direct detection and identification of pests on-site.…”

Deep Learning Detected Nutrient Deficiency in Chili Plant

“…The result can obtain an effective accuracy of 87.1%. One branch of computer vision is image processing, which is used to diagnose human and plant diseases [7]. This study uses 876 samples, and the accuracy is more than 90%.…”