Annotated Bibliography & References - Plant Disease Detection

Annotated Bibliography

The concepts, methods, and results discussed in this tutorial are based on the following five peer-reviewed papers. Each entry includes the full citation, a brief synopsis, why it is useful for this project, and a direct link to the published paper.

[1] Ding et al. (2024)

W. Ding, M. Abdel-Basset, I. Alrashdi, and H. Hawash, “Next generation of computer vision for plant disease monitoring in precision agriculture: A contemporary survey, taxonomy, experiments, and future direction,” Information Sciences, vol. 665, article 120338, 2024.

Synopsis: This survey gives a broad overview of modern computer vision techniques in precision agriculture, covering CNNs, YOLO object detectors, vision transformers, and lightweight models for edge deployment. It also discusses practical challenges like outdoor lighting, background clutter, and edge computing.

Why this source is useful: Provides the overall computer vision background for the tutorial and explains the transition from basic classification to real-time object detection in agriculture.

View Journal Source (DOI: 10.1016/j.ins.2024.120338) →

[2] Iftikhar et al. (2024)

M. Iftikhar, I. A. Kandhro, N. Kausar, et al., “Plant disease management: a fine-tuned enhanced CNN approach with mobile app integration for early detection and classification,” Artificial Intelligence Review, vol. 57, article 167, 2024.

Synopsis: This study develops a fine-tuned CNN model with transfer learning for crop disease identification and integrates it into a working smartphone app, testing on apple, corn, and potato leaf diseases.

Why this source is useful: Supports the mobile image capture, CNN classification, and on-device deployment sections of this tutorial.

View Journal Source (DOI: 10.1007/s10462-024-10809-z) →

[3] Javidan et al. (2024)

S. M. Javidan, A. Banakar, K. Rahnama, K. Asefpour Vakilian, and Y. Ampatzidis, “Feature engineering to identify plant diseases using image processing and artificial intelligence: A comprehensive review,” Smart Agricultural Technology, vol. 8, article 100480, 2024.

Synopsis: A detailed review of color, texture (GLCM), and shape features used in plant pathology. The paper explains preprocessing steps, color spaces (such as HSV and CIE $L^*a^*b^*$), and disease segmentation methods.

Why this source is useful: Directly supports the preprocessing, color space conversion, and visual feature extraction sections of this tutorial.

View Journal Source (DOI: 10.1016/j.atech.2024.100480) →

[4] Leite et al. (2024)

D. Leite, A. Brito, and G. Faccioli, “Advancements and outlooks in utilizing Convolutional Neural Networks for plant disease severity assessment: A comprehensive review,” Smart Agricultural Technology, vol. 9, article 100573, 2024.

Synopsis: This review explores how deep learning can estimate disease severity rather than just assigning a disease label. It discusses pixel-level segmentation, mathematical severity indices, and automated plant phenotyping.

Why this source is useful: Provides the theoretical backing for Module 4 (Segmentation & Severity Estimation) and the percentage severity formula: $\text{Severity} = (\text{Diseased Pixels} / \text{Total Leaf Pixels}) \times 100$.

View Journal Source (DOI: 10.1016/j.atech.2024.100573) →

[5] Montagut Marques et al. (2025)

M. J. Montagut Marques, L. Mingxin, K. T. Shiojiri, T. Hagiwara, K. Hirose, K. Shiojiri, and S. Umezu, “Plant Doctor: A hybrid machine learning and image segmentation software to quantify plant damage in video footage,” Measurement, vol. 249, article 117094, 2025.

Synopsis: Introduces the Plant Doctor system, combining YOLOv8 for leaf detection, DeepSORT for tracking leaves across video frames, and DeepLabV3+ for damage segmentation. It reports verified results (0.99 mAP@0.5 for YOLO, 0.96 leaf IoU, 0.76 damage IoU) and documents the key finding that processing a 1-minute video required about 50 minutes.

Why this source is useful: Serves as the primary case study (Module 6) and motivation for multi-view video tracking (Module 5), providing concrete real-world numbers and highlighting processing time bottlenecks.

View Journal Source (DOI: 10.1016/j.measurement.2025.117094) →

Audio Guide

Module Narration

A 1–2 minute audio overview of the research papers behind this tutorial.

🎧

Audio Narration (audio/references-audio.mp3) Audio recording scheduled. The media player will activate automatically once the audio file is uploaded to the repository.