BloomLens: A Curated 30-Class Flower Image Dataset for Computer Vision and Deep Learning

BloomLens is a multi-class flower image dataset developed to support research in computer vision and deep learning, with a focus on robust flower species recognition in real-world conditions. The dataset contains 30 classes of commonly found ornamental and wild flowers, where each class is organized in a separate folder and labeled using both common names and scientific names.

The dataset includes a total of 10,142 images, collected under natural outdoor environments with realistic variations in lighting, viewpoint, distance, background, and occlusion. These real-world variations help improve the robustness of machine learning and deep learning models, making BloomLens suitable for practical classification and benchmarking tasks.

Dataset Composition

Classes (30): Water Lily, Butterfly Pea, Paperflower, American Dwarf Heliconia, Crape Myrtle, Frangipani, Rose, Pink Kopsia, Crown-of-thorns, Singapore Daisy, Marigold, White Jasmine, Shoeblackplant, Thryallis, Dwarf Mexican Petunia, Madagascar Periwinkle, Jungle Geranium, Arrowleaf Sida, Pampas Grass, Bleeding-heart Vine, Sweet Autumn Clematis, Princess Flower, Rose Cactus, Philippine Ground Orchid, Yellow Allamanda, Rangoon Creeper, Crepe Jasmine, Firecracker Flower, White Mussaenda, False Heather

Total Images: 10,142

Label Format: Folder-wise labeling (one folder per class), with serial ID (01–30) + common and scientific name.

Collection and Diversity

BloomLens images were captured in real-world scenarios to ensure diversity and model generalization. The dataset includes natural variations such as:

Different illumination conditions (sunny, cloudy, shadow)

Multiple viewing angles and flower orientations

Varying backgrounds (gardens, roadsides, natural vegetation)

Different flower sizes, growth stages, and partial occlusions

This diversity makes the dataset useful for training and evaluating deep learning models under realistic conditions rather than controlled lab settings.

Repository and Metadata

The dataset is prepared for upload to Zenodo as an open-access dataset. The repository includes:

Class-wise image folders (01–30) Representations in Class_list.csv

Clear documentation of folder structure and labeling conventions for easy use with ML/DL frameworks

Potential Applications

30-class flower image classification

Transfer learning and benchmarking (CNNs and Vision Transformers)

Multi-class classification research in plant and flower recognition

Data augmentation and robustness experiments

Educational use for computer vision dataset practice and model training