Random forest based classification of diseases in grapes from images captured in uncontrolled environments

Biswas, Sandika; Avil, Saunshi; Sarangi, Sanat; Pappula, Srinivasu

doi:10.1109/icsp.2016.7878133

Cited by 46 publications

(17 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In cases where the dataset is limited, shallow classifiers are used. These depend mainly on several phases that help in feature extraction and include Support Vector Machine (SVM) classifiers [ 54 , 55 ], random forest [ 56 ] and K-nearest neighbours [ 57 , 58 ].…”

Section: Feature Representation In Shallow Classifiersmentioning

confidence: 99%

Review of the State of the Art of Deep Learning for Plant Diseases: A Broad Analysis and Discussion

Hasan

Yusuf

Alzubaidi

2020

Plants

151

View full text Add to dashboard Cite

Deep learning (DL) represents the golden era in the machine learning (ML) domain, and it has gradually become the leading approach in many fields. It is currently playing a vital role in the early detection and classification of plant diseases. The use of ML techniques in this field is viewed as having brought considerable improvement in cultivation productivity sectors, particularly with the recent emergence of DL, which seems to have increased accuracy levels. Recently, many DL architectures have been implemented accompanying visualisation techniques that are essential for determining symptoms and classifying plant diseases. This review investigates and analyses the most recent methods, developed over three years leading up to 2020, for training, augmentation, feature fusion and extraction, recognising and counting crops, and detecting plant diseases, including how these methods can be harnessed to feed deep classifiers and their effects on classifier accuracy.

show abstract

Section: Feature Representation In Shallow Classifiersmentioning

confidence: 99%

Review of the State of the Art of Deep Learning for Plant Diseases: A Broad Analysis and Discussion

Hasan

Yusuf

Alzubaidi

2020

Plants

151

View full text Add to dashboard Cite

show abstract

“…It is used in classification and regression. Its application is in leaf disease classification like grapes [38]. Likewise, we have used this classifier for our database also.…”

Section: Related Workmentioning

confidence: 99%

A Perspective View of Cotton Leaf Image Classification Using Machine Learning Algorithms Using WEKA

Patil¹,

Burkpalli²

2021

Advances in Human-Computer Interaction

View full text Add to dashboard Cite

Cotton is one of the major crops in India, where 23% of cotton gets exported to other countries. The cotton yield depends on crop growth, and it gets affected by diseases. In this paper, cotton disease classification is performed using different machine learning algorithms. For this research, the cotton leaf image database was used to segment the images from the natural background using modified factorization-based active contour method. First, the color and texture features are extracted from segmented images. Later, it has to be fed to the machine learning algorithms such as multilayer perceptron, support vector machine, Naïve Bayes, Random Forest, AdaBoost, and K-nearest neighbor. Four color features and eight texture features were extracted, and experimentation was done using three cases: (1) only color features, (2) only texture features, and (3) both color and texture features. The performance of classifiers was better when color features are extracted compared to texture feature extraction. The color features are enough to classify the healthy and unhealthy cotton leaf images. The performance of the classifiers was evaluated using performance parameters such as precision, recall, F-measure, and Matthews correlation coefficient. The accuracies of classifiers such as support vector machine, Naïve Bayes, Random Forest, AdaBoost, and K-nearest neighbor are 93.38%, 90.91%, 95.86%, 92.56%, and 94.21%, respectively, whereas that of the multilayer perceptron classifier is 96.69%.

show abstract

“…The system can classify apples in real time, according to physical parameters such as size, color and external defects. Sandika et al (2016) [19] mainly work with grape anthrax image preprocessing, feature extraction, powdery mildew and downy mildew, and then by using and through, abstract, SVM (support vector machine) and comparing four random forest algorithms, this model combine with the application of gray symbiosis matrix to establish the random forest and obtain the function, and the accuracy is up to 86%. Moallem et al (2017) [20] firstly segment apple images, combine morphological methods and Markov distance classifier to monitor the quality of apple stem end and calyx region, respectively, then realize defect segmentation through an MLP neural network, and finally use an SVM classifier to classify golden apples.…”

Section: B Recognition and Classification Of Imagesmentioning

confidence: 99%

An Improved CNN-Based Apple Appearance Quality Classification Method With Small Samples

et al. 2021

View full text Add to dashboard Cite

Apple quality classification is an important means to refine apple sales market and promote apple sales. At present, most of classification methods based on a convolutional neural network (CNN) depend on the quantity of training samples to get good performance. But due to the lack of large-scale public apple appearance dataset, it is a big challenge to obtain high accuracy of apple appearance quality classification with small samples. Therefore, we propose an improved method based on CNN for apple appearance, quality classification with small samples. Firstly, support vector machine (SVM) is used for image segmentation to avoid the decrease of recognition accuracy caused by environmental noise. Secondly, the segmented image data are input into deep convolutional generative adversarial networks (DCGAN) model, which is used for data expansion. Thirdly, the improved ResNet50 (Imp-ResNet50) is proposed as follows: Replace the fully-connected layer with global average pooling layer; Add the dropout algorithm and batch normalization algorithm at the fully-connected layer; Replace the activation function ReLU with Swish. Through comparative experiments with 360 apple images, we verify the performance of the proposed method including the training image quality, the running time, and classification accuracy. The result shows that the proposed method can obtain high quality training samples and reduce the running time of the method effectively. At the same time, it can realize higher classification accuracy that is up to 96.5%, which is higher than the previous classification method.INDEX TERMS Apple quality classification, SVM, DCGAN, ResNet50.

show abstract

Random forest based classification of diseases in grapes from images captured in uncontrolled environments

Cited by 46 publications

References 21 publications

Review of the State of the Art of Deep Learning for Plant Diseases: A Broad Analysis and Discussion

Review of the State of the Art of Deep Learning for Plant Diseases: A Broad Analysis and Discussion

A Perspective View of Cotton Leaf Image Classification Using Machine Learning Algorithms Using WEKA

An Improved CNN-Based Apple Appearance Quality Classification Method With Small Samples

Contact Info

Product

Resources

About