Efficient Leaf Disease Classification and Segmentation using Midpoint Normalization Technique and Attention Mechanism

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Taufik, Enam Ahmed, Parsa, Antara Firoz, Mostafa, Seraj Al Mahmud
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910970733920256
author Taufik, Enam Ahmed
Parsa, Antara Firoz
Mostafa, Seraj Al Mahmud
author_facet Taufik, Enam Ahmed
Parsa, Antara Firoz
Mostafa, Seraj Al Mahmud
contents Enhancing plant disease detection from leaf imagery remains a persistent challenge due to scarce labeled data and complex contextual factors. We introduce a transformative two-stage methodology, Mid Point Normalization (MPN) for intelligent image preprocessing, coupled with sophisticated attention mechanisms that dynamically recalibrate feature representations. Our classification pipeline, merging MPN with Squeeze-and-Excitation (SE) blocks, achieves remarkable 93% accuracy while maintaining exceptional class-wise balance. The perfect F1 score attained for our target class exemplifies attention's power in adaptive feature refinement. For segmentation tasks, we seamlessly integrate identical attention blocks within U-Net architecture using MPN-enhanced inputs, delivering compelling performance gains with 72.44% Dice score and 58.54% IoU, substantially outperforming baseline implementations. Beyond superior accuracy metrics, our approach yields computationally efficient, lightweight architectures perfectly suited for real-world computer vision applications.
format Preprint
id arxiv_https___arxiv_org_abs_2505_21316
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Efficient Leaf Disease Classification and Segmentation using Midpoint Normalization Technique and Attention Mechanism
Taufik, Enam Ahmed
Parsa, Antara Firoz
Mostafa, Seraj Al Mahmud
Computer Vision and Pattern Recognition
Image and Video Processing
Enhancing plant disease detection from leaf imagery remains a persistent challenge due to scarce labeled data and complex contextual factors. We introduce a transformative two-stage methodology, Mid Point Normalization (MPN) for intelligent image preprocessing, coupled with sophisticated attention mechanisms that dynamically recalibrate feature representations. Our classification pipeline, merging MPN with Squeeze-and-Excitation (SE) blocks, achieves remarkable 93% accuracy while maintaining exceptional class-wise balance. The perfect F1 score attained for our target class exemplifies attention's power in adaptive feature refinement. For segmentation tasks, we seamlessly integrate identical attention blocks within U-Net architecture using MPN-enhanced inputs, delivering compelling performance gains with 72.44% Dice score and 58.54% IoU, substantially outperforming baseline implementations. Beyond superior accuracy metrics, our approach yields computationally efficient, lightweight architectures perfectly suited for real-world computer vision applications.
title Efficient Leaf Disease Classification and Segmentation using Midpoint Normalization Technique and Attention Mechanism
topic Computer Vision and Pattern Recognition
Image and Video Processing
url https://arxiv.org/abs/2505.21316