Machine Vision-Based Fruit and Vegetable Disease Recognition: A Review

Habib, Md. Tarek; Arif, Md. Ariful Islam; Shorif, Sumaita Binte; Uddin, Mohammad Shorif; Ahmed, Faez

doi:10.1007/978-981-33-6424-0_10

Cited by 5 publications

(1 citation statement)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Bhargava and Bansal (2021) examined techniques in computer vision for grading and classifying fruits and vegetables according to appearance, highlighting the need for improved performance and suggesting exploring color spaces and different image directions. Using computer vision and machine learning, Habib et al (2021) described recent advancements in fruit and vegetable disease detection, compared performance measures to pinpoint cutting-edge methods, and recommended future lines of inquiry. Koç and Vatandaş (2021) developed an image processing algorithm for classifying fruits based on size and color characteristics, with training success rates of 93.6% for KNN, 90.3% for DT, 88.3% for Naive Bayes, 92.6% for MLP, and 94.3% for RF.…”

Section: Introductionmentioning

confidence: 99%

Improving Citrus Fruit Classification Accuracy in Xray Images Using Features Enhanced Vision Transformer Architecture

Raza,

Babeker

et al. 2024

Preprint

View full text Add to dashboard Cite

Quality assessment is a cornerstone of fruit production and distribution, particularly regarding storage conditions and duration. Citrus fruits, a staple in global consumption patterns, serve as aultimate example. This study employs a non-destructive analytical technique, X-ray Computed Tomography (CT) scanning to meticulously analyze a substantial sample of 300 citrus fruits, specifically satsuma, subjected to both ambient (20-22°C, 50-60% humidity) and refrigeration conditions (6-8°C, 65-75% humidity). Through a methodologically rigorous approach, we conduct Stratified Dataset Splitting, allocating 60% of the X-ray datasets for training, with 20% dedicated to validation and testing, respectively. Our research introduces a pioneering methodology termed Feature Enhancement Vision Transformers (FEViT), meticulously designed to augment precision in 1 citrus fruit classification via X-ray image analysis. By leveraging the transforma-tive potential of Vision Transformer architecture, FEViT integrates convolutional layers and expanded input dimensions to enhance classification performance substantially. Our empirical findings unequivocally demonstrate the superior efficacy of FEViT models vis-à-vis conventional ViT counterparts across diverse datasets. Particularly noteworthy are the marked performance gains exhibited by FEViT-Large variants, evidenced by notable increases in precision (5.08%), accuracy (5.47%), recall (4.55%), and F1 scores (5.28%). This underscores the distinguish-able enhanced discriminatory prowess of FEViT models. Extensive validation through rigorous experimentation ratifies FEViT’s supremacy over traditional deep learning architectures, affirming heightened accuracy, precision, recall, and F1 scores. Our study heralds the advent of FEViT architecture as a milepost in citrus fruit image classification, promising augmented accuracy and robustness vis-à-vis extant methodologies. This research holds profound implications for the agricultural sector, especially in domains such as citrus and broader fruit classification , where nuanced image analysis is indispensable for quality assessment and informed decision-making.

show abstract

Section: Introductionmentioning

confidence: 99%