Feature Mapping for Rice Leaf Defect Detection Based on a Custom Convolutional Architecture

Muhammad Hussain; Hussain Al-Aqrabi; Muhammad Munawar; Richard Hill

doi:10.3390/foods11233914

Feature Mapping for Rice Leaf Defect Detection Based on a Custom Convolutional Architecture

Muhammad Hussain, Hussain Al-Aqrabi, Muhammad Munawar, Richard Hill

COMSATS University Islamabad

Research output: Contribution to journal › Article › peer-review

17 Citations (Scopus)

Abstract

Rice is a widely consumed food across the world. Whilst the world recovers from COVID-19, food manufacturers are looking to enhance their quality inspection processes for satisfying exportation requirements and providing safety assurance to their clients. Rice cultivation is a significant process, the yield of which can be significantly impacted in an adverse manner due to plant disease. Yet, a large portion of rice cultivation takes place in developing countries with less stringent quality inspection protocols due to various reasons including cost of labor. To address this, we propose the development of lightweight convolutional neural network architecture for the automated detection of rice leaf smut and rice leaf blight. In doing so, this research addresses the issue of data scarcity via a practical variance modeling mechanism (Domain Feature Mapping) and a custom filter development mechanism assisted through a reference protocol for filter suppression.

Original language	English
Article number	3914
Number of pages	18
Journal	Foods
Volume	11
Issue number	23
DOIs	https://doi.org/10.3390/foods11233914
Publication status	Published - 4 Dec 2022

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 2 Zero Hunger
SDG 3 Good Health and Well-being
SDG 9 Industry, Innovation, and Infrastructure
SDG 11 Sustainable Cities and Communities

Access to Document

10.3390/foods11233914Licence: CC BY

Cite this

@article{d60739a8f50144d08d109a7283da2ebe,

title = "Feature Mapping for Rice Leaf Defect Detection Based on a Custom Convolutional Architecture",

abstract = "Rice is a widely consumed food across the world. Whilst the world recovers from COVID-19, food manufacturers are looking to enhance their quality inspection processes for satisfying exportation requirements and providing safety assurance to their clients. Rice cultivation is a significant process, the yield of which can be significantly impacted in an adverse manner due to plant disease. Yet, a large portion of rice cultivation takes place in developing countries with less stringent quality inspection protocols due to various reasons including cost of labor. To address this, we propose the development of lightweight convolutional neural network architecture for the automated detection of rice leaf smut and rice leaf blight. In doing so, this research addresses the issue of data scarcity via a practical variance modeling mechanism (Domain Feature Mapping) and a custom filter development mechanism assisted through a reference protocol for filter suppression.",

keywords = "Leaf smut, Bacterial blight, Quality inspection, Lightweight, Deep learning",

author = "Muhammad Hussain and Hussain Al-Aqrabi and Muhammad Munawar and Richard Hill",

note = "Funding Information: This research has received no external funding. Publisher Copyright: {\textcopyright} 2022 by the authors.",

year = "2022",

month = dec,

day = "4",

doi = "10.3390/foods11233914",

language = "English",

volume = "11",

journal = "Foods",

issn = "2304-8158",

publisher = "Multidisciplinary Digital Publishing Institute (MDPI)",

number = "23",

}

TY - JOUR

T1 - Feature Mapping for Rice Leaf Defect Detection Based on a Custom Convolutional Architecture

AU - Hussain, Muhammad

AU - Al-Aqrabi, Hussain

AU - Munawar, Muhammad

AU - Hill, Richard

PY - 2022/12/4

Y1 - 2022/12/4

N2 - Rice is a widely consumed food across the world. Whilst the world recovers from COVID-19, food manufacturers are looking to enhance their quality inspection processes for satisfying exportation requirements and providing safety assurance to their clients. Rice cultivation is a significant process, the yield of which can be significantly impacted in an adverse manner due to plant disease. Yet, a large portion of rice cultivation takes place in developing countries with less stringent quality inspection protocols due to various reasons including cost of labor. To address this, we propose the development of lightweight convolutional neural network architecture for the automated detection of rice leaf smut and rice leaf blight. In doing so, this research addresses the issue of data scarcity via a practical variance modeling mechanism (Domain Feature Mapping) and a custom filter development mechanism assisted through a reference protocol for filter suppression.

AB - Rice is a widely consumed food across the world. Whilst the world recovers from COVID-19, food manufacturers are looking to enhance their quality inspection processes for satisfying exportation requirements and providing safety assurance to their clients. Rice cultivation is a significant process, the yield of which can be significantly impacted in an adverse manner due to plant disease. Yet, a large portion of rice cultivation takes place in developing countries with less stringent quality inspection protocols due to various reasons including cost of labor. To address this, we propose the development of lightweight convolutional neural network architecture for the automated detection of rice leaf smut and rice leaf blight. In doing so, this research addresses the issue of data scarcity via a practical variance modeling mechanism (Domain Feature Mapping) and a custom filter development mechanism assisted through a reference protocol for filter suppression.

KW - Leaf smut

KW - Bacterial blight

KW - Quality inspection

KW - Lightweight

KW - Deep learning

UR - https://www.scopus.com/pages/publications/85143593948

U2 - 10.3390/foods11233914

DO - 10.3390/foods11233914

M3 - Article

C2 - 36496723

SN - 2304-8158

VL - 11

JO - Foods

JF - Foods

IS - 23

M1 - 3914

ER -

Feature Mapping for Rice Leaf Defect Detection Based on a Custom Convolutional Architecture

Abstract

UN SDGs

Access to Document

Other files and links

Fingerprint

Custom Lightweight Convolutional Neural Network Architecture For Automated Detection of Damaged Pallet Racking In Warehousing & Distribution Centers

Domain Feature Mapping with YOLOv7 for Automated Edge-Based Pallet Racking Inspections

Exudate Regeneration for Automated Exudate Detection in Retinal Fundus Images

PV-CrackNet Architecture for Filter Induced Augmentation and Micro-Cracks Detection within a Photovoltaic Manufacturing Facility

Cite this