Logo Lanfrica

"Curated Dataset of Ethiopian Medicinal Plant Leaf Images for Ethnobotanical Multi-Label Classification"

Domaine:

agriculture

Type de record:

dataset
Créateur:
Yoh
Éditeur:
IEE
Hôte:avatar
"This dataset contains 9,600 high-resolution leaf images from 32 distinct Ethiopian medicinal plant species, supporting the crucial digitization and preservation of indigenous ethnobotanical knowledge. Collected under controlled environmental conditions using a Samsung Galaxy S24 Ultra, domain experts precisely annotated each image with binary indicators across six target anatomical labels: root, bark, leaf, seed, latex, and all_parts. This structures the data for advanced multi-label classification utilizing leaf morphology. Explainable artificial intelligence, specifically Grad-CAM, is integrated to visually map model attention, ensuring deep learning networks predict traditional medicinal-use categories by learning true morphological features\u2014such as lamina contours or venation patterns\u2014rather than mistakenly identifying non-visible plant organs."

Tasks

computer visionimage classification

Languages

Amharic

Licenses

Creative Commons Attribution 4.0 Internationalhttps://creativecommons.org/licenses/by/4.0/legalcode

Similaires

Curated Avocado Leaf Image Dataset for Healthy and Cercospora Leaf Spot Classification

This curated dataset contains labeled images of avocado (Persea americana) leaves collected from avo

Ethiopian Indigenous Medicinal Plant Dataset

This dataset provides a comprehensive overview of Ethiopian Indigenous Medicinal Plant. The dataset

DeepEthnic: Multi-Label Ethnic Classification from Face Images

Ethnic group classification is a well-researched problem, which has been pursued mainly during the p

Hausa Emotion-Tagged Tweets Dataset for Multi-Label Emotion Classification

The dataset comprises 19,757 Hausa tweets, each annotated with 11 distinct emotions: anger, sadness,

Deep learning for Ethiopian indigenous medicinal plant species identification and classification

BD-MediFlora-22: A 22-Species Medicinal Plant Leaf Dataset

In traditional and modern healthcare systems, medical plants can play a vital role due to their bioa