Preprocessing of leaf images using brightness preserving dynamic fuzzy histogram equalization technique

Abstract

Agriculture serves as the backbone of many countries. It provides food and other essential materials as per our requirement. Various kinds of diseases are affecting the agricultural crops which in turn reduce the quantity and quality of the agricultural sector. This can also lead to the decrease in food production thereby affecting the economic growth and development. Even though the symptoms and other impacts of the diseases are outwardly visible, manual identification of diseases and rectification is a tedious and time-consuming process. Therefore, detecting the diseases using an automatic computer-based model will be an effective solution. Image processing methods in conjunction with machine learning algorithms provide greater assistance in the field of plant disease detection. In the proposed work, plant leaf images of 10 crops are collected as the dataset. The images after acquisition are preprocessed using brightness preserving dynamic fuzzy histogram equalization (BPDFHE), an advanced version of histogram equalization and Gaussian filtering. The results are calculated and compared using the parameters such as peak signal to noise ratio (PSNR), structural similarity index (SSIM) and mean square error (MSE). This method performs more accurately than the existing preprocessing approaches.

Encouraging hygiene permanence in tomato leaf and applying machine learning techniques

“…But plant diseases are also majorly caused by the pathogenic organisms such as fungi, bacteria, viruses, protozoa, insects and parasitic plants which are termed as infectious plant diseases. These diseases may affect various parts of the plant which include leaf, root, and stem [1]. When leaves get affected by pests or pathogens or environmental stress, they end up getting affected.…”