Human Faces Dataset

Dataset comprises 1,200+ high-quality facial images of 400 people, capturing diverse skin tones (lighter to darker), various skin types, and multiple poses (frontal, left/right profiles). Designed for dermatology research, it provides detailed annotations of skin diseases, lesions, acne, rashes, and other dermatological conditions, enabling robust disease detection, classification, and diagnosis. It is ideal for training deep learning models, improving detection… See the full description on the dataset page: https://huggingface.co/datasets/UniDataPro/facial-skin-condition-dataset.

🩺 Dermatology Disease Classification Dataset 📌 Overview This dataset contains 262,874 images of various skin conditions, categorized into 34 different disease classes. It is designed for deep learning-based image classification and can be used to train models for automatic dermatology diagnosis.

🏥 Disease Categories (34 Classes) The dataset includes images of various skin conditions, including but not limited to: ✅ Acne & Rosacea ✅ Actinic Keratosis & Malignant Lesions ✅ Atopic Dermatitis ✅ Eczema ✅ Melanoma & Moles ✅ Psoriasis & Lichen Planus ✅ Fungal Infections (Ringworm, Athlete’s Foot, Nail Fungus) ✅ Herpes, HPV, & STDs ✅ Viral Infections (Chickenpox, Shingles, Warts, Molluscum) ✅ Bacterial Infections (Cellulitis, Impetigo) ✅ Lupus & Connective Tissue Diseases ✅ Pigmentation Disorders ✅ Systemic Diseases with Skin Manifestations

📌 Full category list is available in the dataset.

🛠️ Usage This dataset is ideal for: ✅ Training deep learning models for dermatology image classification ✅ Developing AI-powered medical diagnosis tools ✅ Testing transfer learning models (ResNet, ConvNeXt, EfficientNet, etc.) ✅ Skin disease severity detection & progression tracking

📖 References & Acknowledgments This dataset is a compilation of publicly available dermatology image datasets and medical sources. It is intended for research and educational purposes only.

⚠️ Disclaimer This dataset is not a substitute for professional medical advice. Any models trained on this dataset should be validated by dermatologists before real-world deployment.

Comprehensive Collection: This dataset comprises a diverse collection of images representing various skin diseases.

Categorization: The images are meticulously categorized into 22 distinct classes, each corresponding to a specific skin condition.

Diverse Skin Conditions: These classes include:

• Acne
• Actinic Keratosis
• Benign Tumors
• Bullous
• Candidiasis
• Drug Eruption
• Eczema
• Infestations/Bites
• Lichen
• Lupus
• Moles
• Psoriasis
• Rosacea
• Seborrheic Keratoses
• Skin Cancer
• Sun/Sunlight Damage
• Tinea
• Unknown/Normal
• Vascular Tumors
• Vasculitis
• Vitiligo
• Warts

Intended Use: The dataset is intended for use in image classification tasks, particularly in the fields of dermatology and medical diagnostics.

Research and Development: It provides a valuable resource for researchers, developers, and practitioners aiming to develop and evaluate machine learning algorithms for automated skin disease diagnosis and classification.

Medical Advancements: By leveraging this dataset, advancements in the accurate and efficient identification of skin diseases can be achieved, contributing to improved patient outcomes.

Educational Resource: The dataset can also serve as an educational tool for training healthcare professionals and students in recognizing and diagnosing various skin conditions through image analysis.

The dataset contains rash images of 11 different disease states. Images of normal skin are also included in the dataset.

This dataset can be used to classify the following diseases: 1. Actinic keratosis 2. Atopic Dermatitis 3. Benign keratosis 4. Dermatofibroma 5. Melanocytic nevus 6. Melanoma 7. Squamous cell carcinoma 8. Tinea Ringworm Candidiasis 9. Vascular lesion

Facial Skin Condition Image dataset with photos of various face skin issues for dermatology AI, skin condition classification, facial analysis

📝 Dataset Summary This dataset is a diverse collection of images representing various skin diseases, meticulously categorized into 22 distinct classes. It provides an invaluable resource for image classification tasks, particularly in the fields of dermatology and medical diagnostics.

🌐 Comprehensive Collection The dataset comprises a diverse collection of images representing various skin diseases.

📂 Categorization The images are meticulously categorized into 22 distinct classes, each corresponding to a specific skin condition:

Acne Actinic Keratosis Benign Tumors Bullous Candidiasis Drug Eruption Eczema Infestations/Bites Lichen Lupus Moles Psoriasis Rosacea Seborrheic Keratoses Skin Cancer Sun/Sunlight Damage Tinea Unknown/Normal Vascular Tumors Vasculitis Vitiligo Warts 🎯 Intended Use This dataset is designed for the following purposes:

Research and Development: Supports researchers and practitioners in developing and evaluating machine learning algorithms for skin disease diagnosis and classification. Medical Advancements: Enables advancements in the accurate and efficient identification of skin diseases, contributing to improved patient outcomes. Educational Resource: Serves as a training tool for healthcare professionals and students in recognizing and diagnosing skin conditions through image analysis. 📁 Directory Structure The dataset is organized into the following directory structure:

SkinDisease/ │ ├── Train/ │ ├── Acne/ │ ├── Actinic_Keratosis/ │ ├── ... │ └── Warts/ │ └── Test/ ├── Acne/ ├── Actinic_Keratosis/ ├── ... └── Warts/

This dataset combines images from the open-source Skin Diseases Dataset (Hossain, 2022), Dermnet Skin Diseases Database (DermNet, 2022), and Dermatology Atlas (2022) databases. It contains 38,760 images of 6 different skin diseases: infectious skin diseases, eczema, acne, pigment diseases, benign and malignant tumors.

The data set is randomly divided 0.80:0.10:0.10 train, test and validation.

Purpose : Classification and identification of six different skin disease categories for automatic diagnosis. Type of data: Image files (512 x 512 pixels) Data format: Joint Photographic Expert Group (JPG) and Comma Separated Values (CSV) file formats Number of classes: Six (Atopic Dermatitis, Contact Dermatitis, Eczema, Scabies, Seborrheic Dermatitis, and Tinea Corporis) Number of images: Preprocessed Folder: 1710 images Augmented Folder: 11970 images Metadata: The metadata associated with each skin lesion is composed of 7 attributes. All attributes are available in a CSV document. In total, there are 416 patients and 1,710 skin disease images present in the dataset. Each image/sample has a reference to the patient and the skin disease in the metadata.

Data Acquisition: Images were captured using smartphone cameras during the patients’ consultations with dermatologists. Data source: Clinical sources: 1. Institution: Rangpur Medical College, City: Rangpur, Country: Bangladesh 2. Institution: Shahid Syed Nazrul Islam Medical College, City: Kishoreganj, Country: Bangladesh

Applications: Skin disease detection and classification, diagnosis systems, medical image analysis, computer vision and more.

Dataset Title: Skin Disease Image Classification (Over 8000 Images)

Description:
This dataset contains over 8,000 high-quality images of skin conditions, categorized into five distinct disease classes. It is designed for the development and evaluation of machine learning models aimed at skin disease classification and recognition. Each image is labeled according to one of the following skin conditions:

1. Atopic Dermatitis: A chronic skin condition that causes itchy, inflamed skin, often appearing in patches, most commonly on the face, hands, feet, or behind the knees.
2. Eczema: A group of medical conditions that result in inflammation, redness, and itching of the skin, with various forms including atopic eczema and contact dermatitis.
3. Seborrheic Keratoses and other Benign Tumors: Non-cancerous, often raised growths on the skin, typically appearing in middle-aged or elderly individuals. They are typically tan, brown, or black in color.
4. Tinea Ringworm, Candidiasis, and other Fungal Infections: A collection of skin conditions caused by fungal infections, such as ringworm, athlete's foot, and candidiasis, presenting as red, itchy, scaly patches on the skin.
5. Psoriasis, Lichen Planus, and Related Diseases: A group of chronic skin diseases that cause the rapid growth of skin cells, leading to scaly, itchy patches. Lichen planus is an inflammatory condition that causes flat-topped, purplish lesions on the skin.

This dataset provides a wide variety of images, each representing different severities and variations of these conditions, making it ideal for training deep learning models to identify and differentiate between common skin diseases.

Features:
- Images: High-resolution skin images from various sources - Classes: 5 disease categories - Size: More than 8,000 labeled images, suitable for model training, validation, and testing.

Usage:
This dataset is perfect for: - Building models for automatic skin disease detection. - Assisting in the diagnosis and classification of common skin conditions. - Educational and research purposes in dermatology and medical image processing.

• Skin diseases encompass a broad spectrum of conditions affecting the largest organ of the human body, ranging from common dermatological issues to more severe and potentially life-threatening disorders. Skin cancers, a subset of skin diseases, specifically involve the abnormal and uncontrolled growth of skin cells, often triggered by exposure to ultraviolet (UV) radiation, genetic factors, or environmental influences. Skin cancers, including melanoma, basal cell carcinoma, and squamous cell carcinoma, pose a significant health concern globally due to their prevalence and potential for metastasis. On the other hand, non-cancerous skin diseases, such as eczema, psoriasis, and acne, impact millions, affecting quality of life and sometimes leading to complications if left untreated. Research in this field is vital for understanding the complexities of skin diseases and cancers, developing effective detection methods, advancing treatment options, and ultimately improving outcomes for individuals affected by these conditions.

• Early detection, accurate diagnosis, and targeted interventions are key elements in the ongoing efforts to mitigate the impact of skin diseases and cancers on public health.

• In recent times, computer vision has shown great promise in conducting the classification and identification tasks of this kind.

• Fifty seven distinct kinds of skin diseases and skin cancer are shown in this large dataset, which can be used to develop machine vision-based techniques.

• In this dataset, there are 978 (primary source 90, secondary source 888) original images of skin diseases and skin cancer. Then, in order to increase the number of data points, shifting, flipping, zooming, shearing, brightness enhancement, and rotation techniques are used to create a total of 630 augmented images from these original images (primary source).

Overview The Facial Skin Condition Dataset is a curated collection of 639 high-quality facial images representing 213 unique individuals, designed to support dermatological research, AI-powered diagnostics, and computer vision applications in medical imaging. The dataset covers a wide spectrum of skin conditions — from acne and redness to under-eye bags — enabling robust model training for skin disease detection, classification, and diagnosis.

Each image is accompanied by structured metadata, including subject ID, gender, age, and type condition, making it suitable for demographic-aware research and cross-group analysis.

Skin Conditions Covered The dataset includes 4 annotated condition categories across all 213 subjects: 1. Acne — 54 subjects 2. Acne black — 43 subjects 3. Bags — 58 subjects 4. Redness — 58 subjects

Subject Demographics The dataset represents 213 people across a balanced mix of genders, skin tones, and age groups: 1. Gender distribution: 102 female subjects and 111 male subjects 2. Age groups represented: 10, 15, 18, 20, 25, 30, 35, 50, and 55 years — with the largest cohorts at ages 20 (94 subjects) and 30 (96 subjects)

Image Specifications 1. Total images: 639 2. Subjects: 213 unique individuals (~3 images per subject on average) 3. Image quality: high-resolution facial photographs 4. Capture poses: frontal, left profile, and right profile views Multiple poses per subject allow models to learn condition appearance from different angles, improving robustness and generalization.

Annotations Every image in the dataset includes structured annotation metadata: 1. Subject ID 2. Gender 3. Age 4. Skin condition label(s) The labeling structure is consistent across all 639 images, ensuring clean data pipelines with minimal preprocessing overhead.

Use Cases - Dermatology AI & Clinical Decision Support. Train and validate diagnostic models that assist dermatologists in detecting and classifying skin conditions from facial images — reducing time-to-diagnosis and supporting remote consultations. - Skin Disease Detection & Classification. Build multi-class classifiers distinguishing between acne, blackheads, under-eye bags, redness, and healthy skin, benchmarked against real annotated medical imagery. - Medical Imaging & Computer Vision. Develop and benchmark detection algorithms, segmentation models, and disease localization methods on real-world facial dermatological data. - Deep Learning Model Training. Use the dataset as a domain-specific training set or fine-tuning resource for CNN-based architectures, transformer models, or hybrid pipelines targeting skin condition recognition.

Compliance & Data Responsibility All images were collected with proper consent from subjects. The dataset is structured to comply with data protection standards applicable to biometric and medical imagery. Storage and distribution follow established data security protocols to ensure responsible use in research and commercial healthcare applications.

Summary The Facial Skin Condition Dataset is a focused, high-quality resource of 639 annotated facial images from 213 individuals — 102 female and 111 male — spanning age groups from 10 to 55 years. It covers four dermatological condition categories: acne (54 subjects), acne black / blackheads (43), under-eye bags (58), and redness (58). Combined with multi-pose captures, structured demographic annotations, and diverse skin tone representation, the dataset provides a reliable and practical foundation for training and benchmarking AI models in skin disease detection, classification, and medical imaging research.

The rise in the prevalence of skin diseases increases the demand for accurate and efficient diagnostic tools. Various traditional diagnostic tools face a few major struggles such as time-consuming and prone to error. Therefore, this paper proposes a novel and reliable skin disease classification framework by integrating advanced preprocessing, feature extraction, and ensemble learning approaches to enhance diagnostic accuracy. The proposed method involves extensive data collection from the Skin disease image dataset, Skin Disease Dataset, and 33k skin disease dataset. Then the collected data are preprocessed by applying key approaches such as normalization, resizing, noise reduction, and grayscale conversion to improve the image quality. The Crayfish Optimization Algorithm with a Reverse Wheel Strategy is applied for an effective feature segmentation, where the most relevant features are segmented. Then the feature extraction is performed using the Gray Level Co-occurrence Matrix. For classification, the Meta Ensemble-based Random Cat Gradient Boost model is introduced by combining the merits of multiple classifiers to enhance prediction performance. The experimental findings demonstrate that the proposed model achieves excellent accuracy and precision of 99.78% and 98.51%, respectively, on the Skin Disease Image Dataset.

Dogs Skin Disease

## Overview

Dogs Skin Disease is a dataset for classification tasks - it contains Dogs annotations for 2,953 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [CC BY 4.0 license](https://creativecommons.org/licenses/CC BY 4.0).

Skin Disease

## Overview

Skin Disease is a dataset for object detection tasks - it contains Disease annotations for 1,042 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [MIT license](https://creativecommons.org/licenses/MIT).

Review 1 Skin Condition

## Overview

Review 1 Skin Condition is a dataset for object detection tasks - it contains Skin Conditions annotations for 401 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [CC BY 4.0 license](https://creativecommons.org/licenses/CC BY 4.0).

This dataset is a curated collection of high-quality images depicting various common skin conditions and rashes. It was developed by combining resources from reputable dermatological image libraries such as DermNet NZ, Kaggle's DermNet collection, and the IEEE DataPort. The dataset is structured to facilitate easy access to images categorized by skin color (Black, Brown, Fair) and condition type (Dermatitis, Eczema, Ringworm), making it an ideal resource for training and testing machine learning models in medical imaging.

Key Features:

• Diverse Conditions: Includes multiple types of skin conditions like dermatitis, eczema, and ringworm.
• Skin Tone Variation: Categorized images based on different skin tones to promote inclusivity and accuracy in diagnosis algorithms.
• Ready for ML: Organized in a machine-learning-friendly format to streamline the development of diagnostic models.
• Educational Value: A valuable resource for educational purposes in dermatology and machine learning fields.

Potential Uses:

• Medical Image Recognition: Train deep learning models to recognize and diagnose various skin conditions.
• Algorithm Testing: Test the efficacy of image processing algorithms in differentiating and categorizing skin conditions.
• Educational Tool: Serve as a visual aid for educational institutions teaching dermatology or machine learning applications in medicine.

Clinical trials database for Skin Disease

Skin Disease Single Balanced

## Overview

Skin Disease Single Balanced is a dataset for classification tasks - it contains Skin Disease Single Balanced annotations for 572 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [CC BY 4.0 license](https://creativecommons.org/licenses/CC BY 4.0).

This dataset is a cleaned and preprocessed combination of the HAM10000 and ISIC Archive dermoscopic image datasets, intended for training and evaluating deep learning models for skin lesion classification.

It is structured to support multi-class image classification, and has been carefully processed to maintain high quality, class balance.

Classes Included :

"melanocytic nevi": "Melanocytic Nevus", "nv": "Melanocytic Nevus", "melanoma": "Melanoma", "mel": "Melanoma", "benign keratosis": "Benign Keratosis", "bkl": "Benign Keratosis", "basal cell carcinoma": "Basal Cell Carcinoma", "bcc": "Basal Cell Carcinoma", "actinic keratosis": "Actinic Keratosis", "akiec": "Actinic Keratosis", "dermatofibroma": "Dermatofibroma", "df": "Dermatofibroma", "vascular lesions": "Vascular Lesion", "vasc": "Vascular Lesion", "warts/molluscum": "Warts/Molluscum"

Preprocessing Notes

• All images resized to 224x224 for CNN compatibility
• Labels unified and cleaned across both datasets
• Invalid or corrupted entries removed