Machine Vision Based Plant Disease Classification Through Leaf Imagining

Rehman, Hamza Ur; Anwar, Shahzad; Tufail, Muhammad

doi:10.18280/isi.250405

Cited by 5 publications

(4 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When Table 5 is examined, it is seen that 100% classification success is achieved for all classes and all core functions with wavelet features. It is seen that a higher success value is obtained compared to the results obtained in the previous study [30] and manual examination. Also, it seems that kernel functions do not have a direct effect on classification success.…”

Section: Resultscontrasting

confidence: 57%

“…In the studies conducted with the SVM algorithm, the effect of different kernel functions on classification success was investigated. In some studies, the RBF kernel function-based classifier was found to be more successful, and in some studies, the polynomial kernel-function classifier was more successful [25][26][27][28][29][30]. Therefore, in this study, the success of both core functions in classification was measured.…”

Section: Svm Classificationmentioning

confidence: 99%

See 1 more Smart Citation

An Industrial Application Towards Classification and Optimization of Multi-Class Tile Surface Defects Based on Geometric and Wavelet Features

Coskun¹,

Yi̇ği̇t²,

Üncü³

et al. 2022

View full text Add to dashboard Cite

It is possible to detect visual surface defects with software in industrial tile production and increase productivity by automating the quality control process. In this process, low error rate and low cost are important indicators. In order to eliminate this negativity and the effect of the human factor, error detection software has been developed in an artificial intelligence-based industrial artificial vision environment. Spots, scratches, cracks, pore defects, which are the most common surface defects, are classified according to 6 different geometric and wavelet transform attributes. Firstly, an industrial artificial vision environment was created. In this environment, a total of 150 tile images, equal numbers from each class, were obtained on the real-time production line. The resulting images were converted into binary images by preprocessing and filtering. For classification, the support vector machines method, which performs high in two-class classifications, is used with the one versus all approach. In classifications made using RBF kernel function using wavelet features as classification performance, a higher success was achieved in all defect classes than geometric features. Real-time application software for all these processes has been developed with the Python language on Ubuntu operating system.

show abstract

Section: Resultscontrasting

confidence: 57%

Section: Svm Classificationmentioning

confidence: 99%

An Industrial Application Towards Classification and Optimization of Multi-Class Tile Surface Defects Based on Geometric and Wavelet Features

Coskun¹,

Yi̇ği̇t²,

Üncü³

et al. 2022

View full text Add to dashboard Cite

show abstract

“…With its advanced design that uses deep layers of convolutional neural networks, the DL model outperforms the SVM by a fairly large margin when it comes to how well it can classify things [70]. For linear and RBF kernels, the accuracy was 96.33% and 97%, respectively, which was even closer to that of DL.This algorithm needs data to learn from the training data, which comes from feature vectors and data outputs, which [71]. These features and labels are used to teach the SVM, which is also called the prediction model.…”

Section: Machine Learning Based Classifier Techniquesmentioning

confidence: 97%

Symptoms Based Image Predictive Analysis for Citrus Orchards Using Machine Learning Techniques: A Review

Dinesh,

Lakshmanan

2023

IJRITCC

View full text Add to dashboard Cite

In Agriculture, orchards are the deciding factor in the country’s economy. There are many orchards, and citrus and sugarcane will cover 60 percent of them. These citrus orchards satisfy the necessity of citrus fruits and citrus products, and these citrus fruits contain more vitamin C. The citrus orchards have had some problems generating good yields and quality products. Pathogenic diseases, pests, and water shortages are the three main problems that plants face. Farmers can find these problems early on with the support of machine learning and deep learning, which may also change how they feel about technology. By doing this in agriculture, the farmers can cut off the major issues of yield and quality losses. This review gives enormous methods for identifying and classifying plant pathogens, pests, and water stresses using image-based work. In this review, the researchers present detailed information about citrus pathogens, pests, and water deficits. Methods and techniques that are currently available will be used to validate the problem. These will include pre-processing for intensification, segmentation, feature extraction, and selection processes, machine learning-based classifiers, and deep learning models. In this work, researchers thoroughly examine and outline the various research opportunities in the field. This review provides a comprehensive analysis of citrus plants and orchards; Researchers used a systematic review to ensure comprehensive coverage of this topic.

show abstract

“…Rehman et al [8] developed image processing and segmentation techniques to identify plant diseases, which is then carried out by classifying plant diseases with multi-class SVM. The results of the method developed have the ability to identify three types of diseases in plants by showing an accuracy value of 95%.…”

Section: Introductionmentioning

confidence: 99%

Deep Learning-based Regional Plant Type Recommendation System for Enhancing Agricultural Productivity

Aradea,

Rianto,

Mubarok

et al. 2023

ISI

View full text Add to dashboard Cite

Recommendation systems serve as pivotal components in the agricultural domain, significantly contributing to global economic growth. One particular application, the recommendation of region-specific plant types, can mitigate losses in unfavorable conditions and optimize yields when growth conditions are ideal. However, accurately identifying the specific parameters of a field location and the diverse characteristics of plant types can pose a challenge. Deep learning has demonstrated efficacy as a predictive model within recommender systems, including those for plant type matching. However, building such models necessitates the identification of optimal solutions, taking into account the complexities of the problem scope and the unique characteristics of the domain. This paper introduces the development of a deep learning model architecture designed to recommend plant types best suited to specific regions. The model was constructed based on an extension of the Convolutional Neural Network (CNN), a deep learning model recognized for its robust pattern recognition capabilities, making it suitable for classification tasks. It has the ability to discern patterns from datasets with a limited number of input features, thus making it an ideal choice for a plant type recommendation system. The Adagrad optimizer was employed for its advantage of partitioning the learning rate into smaller units, which significantly impacts the speed of the training process. Evaluation of this model was undertaken in a two-step process. First, the learning model's performance was assessed using a confusion matrix. Subsequently, the model's functionality was evaluated using real data from a city in Indonesia, investigating its ability to provide relevant recommendations based on the city's unique contextual characteristics. The results demonstrated a substantial accuracy level of 90%, underscoring the model's potential to effectively recommend suitable plant types for specific regional contexts.

show abstract

Machine Vision Based Plant Disease Classification Through Leaf Imagining

Cited by 5 publications

References 20 publications

An Industrial Application Towards Classification and Optimization of Multi-Class Tile Surface Defects Based on Geometric and Wavelet Features

An Industrial Application Towards Classification and Optimization of Multi-Class Tile Surface Defects Based on Geometric and Wavelet Features

Symptoms Based Image Predictive Analysis for Citrus Orchards Using Machine Learning Techniques: A Review

Deep Learning-based Regional Plant Type Recommendation System for Enhancing Agricultural Productivity

Contact Info

Product

Resources

About