Deep Learning Architectures Extended from Transfer Learning for Classification of Rice Leaf Diseases

Nguyễn, Hải Thanh; Quach, Quyen Thuc; Tran, Chi Le Hoang; Luong, Huong Hoang

doi:10.1007/978-3-031-08530-7_66

Cited by 3 publications

(3 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recall (11) also known as sensitivity or true positive rate, measures the proportion of actual positive cases that are correctly identified by the model. It is calculated as: 𝑅𝑒𝑐𝑎𝑙𝑙 = 𝑇𝑃 𝑇𝑃+𝐹𝑁 (11) On the other hand, precision (12) quantifies the model's ability to correctly identify positive cases among all cases predicted as positive. It is expressed as:…”

Section: A Dataset and Performance Metricsmentioning

confidence: 99%

“…Thus, applying artificial intelligence (I.e., AI) has become popular in recent years in classifying and detecting illnesses [5][6] [7]. www.ijacsa.thesai.org A subset of machine learning in AI is deep learning, it has revolutionized the field of image analysis [8] [9][10] [11] [12]. Deep learning models mimic the ability to process and recognize patterns of the human brain such as CNN.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

EfficientSkinCaSV2B3: An Efficient Framework Towards Improving Skin Classification and Segmentation

Thanh,

Nguyen

2024

ijacsa

View full text Add to dashboard Cite

Ozone layer depletion has gained attention as a serious environmental issue. Because of its effects on human health especially skin cancer. Besides, Ultraviolet (UV) radiation is known to be a major risk factor for skin cancer. For instance, it can damage the DNA in skin cells leading to mutations that may eventually result in cancerous growth. Basal cell carcinoma, squamous cell carcinoma, and melanoma are the three primary forms of skin cancer linked to UV exposure. Additionally, it triggers associated illnesses including nevus, seborrheic keratosis, actinic keratosis, dermatofibroma, and vascular lesions. Many medical and computer studies were published as a result to address these disorders. Especially, using an aspect of deep learning that is transfer learning and fine-tuning for the classification of skin images. In this research, the EffecientSkinCaSV2B3 framework was proposed and applied to classify and segment the skin cancer dataset, which were collected and validated by The International Skin Imaging Collaboration (ISIC). In addition, Gradient-weighted Class Activation Mapping (Grad-CAM) is used in skin cancer classification to visually explain images, aiding in understanding model decisions and highlighting important areas. Based on color and texture, k-means clustering was used for the segmentation between portions that were healthy and those that were unhealthy. The study reached a surprising accuracy of 84.91% in nine classes of classifying skin cancer. In other experiments, the customized EfficientNetV2B3 model achieved 94.00% in classifying malign and benign. Moreover, scenarios pointed out that in classifying six classes (i.e., between benign skin diseases) and three classes (i.e., between malign skin diseases) the model earned a high accuracy of 89.56% and 96.74%, respectively.

show abstract

Section: A Dataset and Performance Metricsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

EfficientSkinCaSV2B3: An Efficient Framework Towards Improving Skin Classification and Segmentation

Thanh,

Nguyen

2024

ijacsa

View full text Add to dashboard Cite

show abstract

“…Deep learning is a subset of artificial intelligence and it has revolutionized various fields, including agriculture and industry. Besides, computer vision appeared as a new way for classification and segmentation of a lot of aspects of images [9] [10] [11] [12] [13], through techniques like transfer learning and fine-tuning. For example, image technologies have come out as invaluable tools in potato farming, offering correct solutions for classification, segmentation, and detection tasks.…”

Section: Introductionmentioning

confidence: 99%

Improving Potato Diseases Classification Based on Custom ConvNeXtSmall and Combine with the Explanation Model

Luong

2024

IJACSA

View full text Add to dashboard Cite

Potatoes are short-term crops grown for harvesting tubers. It is a type of tuber that grows on roots and is the fourth most common crop after rice, wheat, and corn. Fresh potatoes can also be used in an incredible variety of dishes by baking, boiling, or frying them. Moreover, the paper, textile, wood, and pharmaceutical industries also make extensive use of potato starch. However, soil and climate pollution are highly unfavorable for potato growth and lead to a lot of diseases such as common scab, black scurf, blackleg, dry rot, and pink rot. Thus. several types of research in medicine and computers were started for the early detection, classification, and treatment of potato diseases. In this study, transfer learning and finetuning were applied to potato disease classification based on a custom ConvNeXtSmall model. In addition, Gradient-weighted Class Activation Mapping (i.e., Grad-CAM) is provided for visual explanation in the final result after classification. For potato illness segmentation, k-means clustering was used to enable the difference between healthy and diseased sections based on color and texture. The data was collected from numerous websites and validated by the Bangladesh Agricultural Research Institute (i.e., BARI), including six types of potato diseases and healthy images. With a Convolutional Neural Networks (i.e., CNN) model from the Keras library, our study reached the unexpected validation accuracy, test accuracy, and F1 score in seven classifications of 99.49%, 98.97%, and 98.97%, respectively. Concerning four-class classification, high accuracy values were obtained for most of the models (i.e., 100%).

show abstract

Predicting rice diseases using advanced technologies at different scales: present status and future perspectives

Li,

Chen,

Matsumoto

et al. 2023

aBIOTECH

View full text Add to dashboard Cite

The past few years have witnessed significant progress in emerging disease detection techniques for accurately and rapidly tracking rice diseases and predicting potential solutions. In this review we focus on image processing techniques using machine learning (ML) and deep learning (DL) models related to multi-scale rice diseases. Furthermore, we summarize applications of different detection techniques, including genomic, physiological, and biochemical approaches. In addition, we also present the state-of-the-art in contemporary optical sensing applications of pathogen–plant interaction phenotypes. This review serves as a valuable resource for researchers seeking effective solutions to address the challenges of high-throughput data and model recognition for early detection of issues affecting rice crops through ML and DL models.

show abstract

Deep Learning Architectures Extended from Transfer Learning for Classification of Rice Leaf Diseases

Cited by 3 publications

References 18 publications

EfficientSkinCaSV2B3: An Efficient Framework Towards Improving Skin Classification and Segmentation

EfficientSkinCaSV2B3: An Efficient Framework Towards Improving Skin Classification and Segmentation

Improving Potato Diseases Classification Based on Custom ConvNeXtSmall and Combine with the Explanation Model

Predicting rice diseases using advanced technologies at different scales: present status and future perspectives

Contact Info

Product

Resources

About