The excessive use of pesticides poses significant environmental and health risks. A real-time disease detection system can help mitigate this issue by identifying early infections and applying treatment only to affected areas. Building on the work of (P. P. Than), who conducted an exhaustive study on chilli anthracnose and the pathogenicity of Colletotrichum species, we utilize disease severity and spread indicators to enhance dataset annotation. Specifically, we classify infection levels based on affected areas, enabling precise disease detection. In this paper, we evaluate our method on a dataset of 6010 images, implementing a three-class classification system to determine the severity of fruit infections. This classification aids in calculating the optimal pesticide quantity required for specific areas. We assess the performance of YOLOv8 and YOLOv9 models in detecting infection levels, even in cases of minor disease spots. Among them, YOLOv8 demonstrated superior accuracy, achieving a mean average precision (mAP) of 92.7%, compared to YOLOv9’s 83.5%. The proposed method reduces pesticide usage by enabling targeted treatment and containment of infected areas. Furthermore, this enrichment improves plant disease understanding, optimizes workflows, and supports more informed decision-making in precision agriculture.
8 July 2024 in International Journal of Multimedia Information Retrieval
Recovering the original printed texts from a document with added handwritten annotations in the marginal area is one of the challenging problems, especially when the original document is not available. Therefore, this paper aims at salvaging automatically the original document from the annotated document by detecting and removing any handwritten annotations that appear in the marginal area of the document without any loss of information. Here a two stage algorithm is proposed, where in the first stage due to approximate marginal boundary detection with horizontal and vertical projection profiles, all of the marginal annotations along with some part of the original printed text that may appear very close to the marginal boundary are removed. Therefore as a second stage, using the connected components, a strategy is applied to bring back the printed text components cropped during the first stage. The proposed method is validated using a dataset of 50 documents having complex handwritten annotations, which gives an overall accuracy of 89.01% in removing the marginal annotations and 97.74% in case of retrieving the original printed text document.