Disease detection of apple leaf with combination of color segmentation and modified DWT

Hasan, Sharad; Jahan, M. Sarwar; Islam, Md. Imdadul

doi:10.1016/j.jksuci.2022.07.004

Cited by 31 publications

(15 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The traditional way is manual identification, relying on experience, high cost and low accuracy. In recent years, the recognition based on computational image processing is more efficient and accurate, the processing steps include: image preprocessing, image segmentation, feature extraction and recognition, and the higher accuracy of image segmentation, the higher accuracy of recognition ( Xue et al., 2021 ; Hasan et al., 2022 ). However, segmentation accuracy and efficiency directly affect the application of segmentation technology in plant applications.…”

Section: Introductionmentioning

confidence: 99%

Hybrid improved capuchin search algorithm for plant image thresholding

et al. 2023

Front. Plant Sci.

View full text Add to dashboard Cite

With the development and wider application of meta-heuristic optimization algorithms, researchers increasingly apply them to threshold optimization of multi-level image segmentation. This paper explores the performance and effects of Capuchin Search Algorithm (CAPSA) in threshold optimization. To solve problems of uneven distribution in the initial population of Capuchin Search Algorithm, low levels of global search performance and premature falling into local optima, this paper proposes an improved Capuchin Search Algorithm (ICAPSA) through a multi-strategy approach. ICAPSA uses chaotic opposite-based learning strategy to initialize the positions of individual capuchins, and improve the quality of the initial population. In the iterative position updating process, Levy Flight disturbance strategy is introduced to balance the global optimization and local exploitation of the algorithm. Finally, taking Kapur as the objective function, this paper applies ICAPSA to multi-level thresholding in the plant images, and compares its segmentation effects with the original CAPSA, the Fuzzy Artificial Bee Colony algorithm (FABC), the Differential Coyote Optimization Algorithm (DCOA), the Modified Whale Optimization Algorithm (MWOA) and Improved Satin Bowerbird Optimization Algorithm (ISBO). Through comparison, it is found that ICAPSA demonstrates superior segmentation effect, both in the visual effects of image segmentation and in data comparison.

show abstract

Section: Introductionmentioning

confidence: 99%

Hybrid improved capuchin search algorithm for plant image thresholding

et al. 2023

Front. Plant Sci.

View full text Add to dashboard Cite

show abstract

“…By utilizing fewer resources, including water and fertilizer, and by permitting more precise application of these inputs based on actual crop demands, this strategy can also assist in lessening the impact of agriculture on the environment. More than 100 apple diseases have been identified [6], with Black Rot [7], Apple Scab [7], Cedar Apple Rust [8], and other common illnesses being the most well-known. These diseases reduce fruit quality and output.…”

Section: Introductionmentioning

confidence: 99%

Apple Leaf Disease Recognition with Segmentation Research Trend: A Systematic Analysis Using VoSViewer

Bonkra

Bhatt

Kaur

et al. 2023

Preprint

View full text Add to dashboard Cite

The study’s goals were to examine the effects of unforeseen weather circumstances on agricultural productivity and to test artificial intelligence-based strategies for feature extraction and segmentation for plant leaf disease identification. A bibliometric analysis was used in the study to look into current trends, publications, citation structures, patterns of ownership and collaboration, production patterns, and other aspects connected to the early detection of apple diseases. While there have been many studies on recognising apple illnesses, there have been few attempts to develop a thorough multidisciplinary science map because disease detection is not exclusive to any one field of study. The study’s objectives were to combine knowledge frameworks and identify the current state of the research field. A scientometric examination of 200 papers from the Scopus database between 2017 and 2022 was done by the researchers in order to accomplish this goal. VOSviewer was utilised for the research, and its automated workflow was used to pick significant journals, authors, nations, articles, and themes. To find patterns and trends, social network studies, citation and co-citation checks, and citation counts were all carried out. The study revealed changes in the cognitive and social structure of the area and concluded that the interdisciplinary field of sickness detection employing segmentation has expanded over time. The study also revealed areas that need additional investigation and clarified the intellectual underpinnings of the topic.

show abstract

“…Pujari et al (2016) calculated the colour distribution and pixel relationship of diseased leaf images based on global and local features to quantify the severity of soybean rust. Hasan et al (2022) proposed a method for apple leaf disease detection and recognition based on the fusion of improved wavelet transform and colour histogram features. Li, Chen et al (2022) proposed a maize leaf disease recognition method based on k‐means and a feature extraction algorithm.…”

Section: Introductionmentioning

confidence: 99%

Tomato leaf disease recognition based on improved convolutional neural network with attention mechanism

Zhou

Zhao

et al. 2023

Plant Pathology

View full text Add to dashboard Cite

Plant diseases are common factors restricting crop yield and quality. For individuals without training, it is still difficult to identify various diseases accurately because many leaf diseases are similar in colour, shape and other aspects. Requiring an expert diagnosis can cause delays and lead to increasing costs. Therefore, this paper proposes an improved convolutional neural network for recognition of tomato leaf diseases. The experimental dataset was from the publicly available dataset PlantVillage. Based on the original ResNet18 model, a new convolutional neural network, TomatoNet, was constructed by adding a squeeze‐and‐excitation module and modifying the classifier structure. The results show that the average recognition accuracy of the TomatoNet network is 99.63%, which is 0.53% higher than the ResNet18 network. In addition, the recognition accuracy improved from 88.97% to 98.35% after the improvement of the AlexNet network. Finally, the superiority of TomatoNet was verified by comparison with other advanced models. This experiment verifies the feasibility of a deep learning algorithm for plant leaf disease recognition, which can provide a more efficient and convenient solution for detecting plant leaf disease.

show abstract

Disease detection of apple leaf with combination of color segmentation and modified DWT

Cited by 31 publications

References 24 publications

Hybrid improved capuchin search algorithm for plant image thresholding

Hybrid improved capuchin search algorithm for plant image thresholding

Apple Leaf Disease Recognition with Segmentation Research Trend: A Systematic Analysis Using VoSViewer

Tomato leaf disease recognition based on improved convolutional neural network with attention mechanism

Contact Info

Product

Resources

About