---
title: "Male Hair Loss Dataset"
description: "The hair loss dataset contains high-resolution scalp images of people captured from five sides, labeled with seven classes on the Norwood-Hamilton scale and supplemented with…"
url: "https://unidata.pro/datasets/male-hair-loss-dataset/"
date_modified: "2026-03-23T14:09:17+03:00"
language: "en-US"
---
The hair loss dataset contains high-resolution scalp images of people captured from five sides, labeled with seven classes on the Norwood-Hamilton scale and supplemented with hair follicle annotations to help machine learning models analyze hair density, thinning patterns, and diagnose baldness

## Dataset Structure

### The Numbers Section

**Numbered list:**

- **Number:** 2 260 — **Text:** Images
- **Number:** 452 — **Text:** People

### Tooltips Section

**Tooltip items:**

- **Name:** Computer Vision
- **Name:** Medicine
- **Name:** Classification
- **Name:** Machine Learning
- **Name:** Data Labeling

### Dataset Information

**Table with data:**

| Characteristic | Data |
| --- | --- |
| Description | Photos of people with varying degrees of hair loss for alopecia classification |
| Data types | Image |
| Tasks | Classification, Machine Learning |
| Number of images | 2 260 |
| Number of files in a set | 5 images (full-face photo, view from the top, back of the head, left side and right side) |
| Total number of people | 452 |
| Labeling | Metadata (gender, age, ethnicity) |
| Age | Min = 18, max = 80, mean = 45 |

**Media Slider:**

- **Image in the slider:** ![Male Hair Loss Dataset](https://unidata.pro/wp-content/uploads/2025/05/men-hair-loss.webp)
- **Image in the slider:** ![Male Hair Loss Dataset](https://unidata.pro/wp-content/uploads/2025/05/men-hair-loss2.webp)
- **Image in the slider:** ![Male Hair Loss Dataset](https://unidata.pro/wp-content/uploads/2025/05/men-hair-loss3.webp)
- **Image in the slider:** ![Male Hair Loss Dataset](https://unidata.pro/wp-content/uploads/2025/05/men-hair-loss4.webp)
- **Image in the slider:** ![Male Hair Loss Dataset](https://unidata.pro/wp-content/uploads/2025/05/men-hair-loss5.webp)

**Link to the sample:** [Download sample](https://drive.google.com/drive/folders/1-yfMf3hesAdlW82P9Y_UnLMB-jySI5-M?usp=sharing)

### Technical Specifications

**Table with data:**

| Characteristic | Data |
| --- | --- |
| Image Extensions | Png, jpeg |
| Extension of labeling file | txt |

**Source and data collection methodology:** Source and collection methodology: Data was collected via crowdsourcing platforms.

### LLM Languages

**Section Title:** Statistics

**List of Statistics:**

- **Filter by:** Age Distribution — **GIF image:** Age Distribution — **Table with data:**

| Age | Count |
| --- | --- |
| Under 18 | 2 |
| 19-25 | 34 |
| 26-32 | 77 |
| 33-39 | 135 |
| 40-46 | 96 |
| 47-53 | 53 |
| 54-59 | 27 |
| 60-66 | 18 |
| 67+ | 10 |

### Statistics - Charts

**Charts with Titles:** - **Shortcode:** [ays_chart id="59"] — **caption above the graph:** Ethnicity Distribution

### Dataset Use Cases - Slider

**Industry Cards:**

- **Industry:** Healthcare & Dermatology — **Title:** Supporting Early Diagnosis of Hair Disorders — **Text:** Male Hair Loss Dataset provides high-quality medical images of different stages of baldness, mapped to the Norwood scale dataset. Dermatologists and researchers can use it to study scalp conditions, hair thinning, and alopecia areata, supporting early detection and improving treatment planning for patients with hair disorders.
- **Industry:** AI & Machine Learning — **Title:** Training Models for Baldness Detection — **Text:** This hair loss dataset is widely used to develop machine learning and deep learning models for bald detection. With labeled bald images datasets, developers can build neural networks that classify hair density, detect hair falling patterns, and provide reliable insights for hair restoration and scalp health research.
- **Industry:** Cosmetic & Hair Care Industry — **Title:** Improving Hair Restoration Solutions — **Text:** The bald men dataset helps cosmetic companies and clinics refine hair transplants and hair care solutions. By analyzing hair textures, skin types, and hair follicles, businesses can design more personalized hair loss treatments that promote thicker hair, better scalp health, and improved outcomes in hair transplantation procedures.
- **Industry:** Research & Development — **Title:** Building Accurate Diagnostic Tools — **Text:** This alopecia dataset serves as reliable training data for researchers exploring new anti-hair loss techniques. By combining dermoscopic images and varied human skin types, it enables the creation of trained models that achieve higher precision in diagnosing hair disorders, supporting advances in artificial intelligence for dermatology and hair growth research.

### Fact

**FAQs Heading:** FAQs

**List of Questions:**

- **Question:** What is Male Hair Loss Dataset used for? — **Answer:** The dataset is used for classification tasks, machine learning, and deep learning models in alopecia research, baldness detection, and scalp health studies. It supports neural networks and learning algorithms for early diagnosis, hair restoration treatments, and accurate detection of hair thinning, hair follicle issues, and scalp conditions.
- **Question:** What types of images are included? — **Answer:** It contains 2 260 images of 452 individuals with different stages of hair thinning and baldness. Each subject has five views (front, top, back, left, right), along with metadata such as gender, age, and ethnicity, making it suitable for hair restoration, scalp condition research, and AI-based alopecia detection.
- **Question:** Can I request a sample of the Male Hair Loss Dataset before I make a purchase? — **Answer:** Yes, Unidata provides samples for evaluation. You can review image quality, annotation formats, and scalp condition diversity to confirm the dataset’s suitability for machine learning, early detection of alopecia areata, hair density analysis, and hair restoration research projects.
- **Question:** What should I consider before buying this dataset? — **Answer:** Before purchasing, consider your training objectives, whether for Norwood scale analysis, scalp condition diagnosis, or alopecia classification. Evaluate the image diversity, labeling quality, and metadata details, since these factors impact the performance of deep learning models, early diagnosis systems, and hair restoration treatment research.
- **Question:** How is the data stored? — **Answer:** Each Unidata dataset is hosted on AWS cloud systems, ensuring high-performance storage and scalability. Security and privacy practices are aligned with ISO 27001 and ISO 27701 frameworks, delivering compliance with recognized international requirements. This provides strong assurance of safe and responsible data management.
- **Question:** Do Unidata datasets follow GDPR or other data privacy regulations? — **Answer:** Yes. Every dataset is GDPR-compliant and adheres to applicable data protection laws. Data is sourced exclusively from permissible and legal channels.
- **Question:** How long does it take to receive the dataset? — **Answer:** Once you submit your request, we will contact you to confirm the details and finalize the required documents. After signing and completing the payment, the dataset will be delivered within 3–10 days.
- **Question:** Is this a real-world dataset or synthetic data? — **Answer:** This is a real-world dataset. The dataset contains photos of people with varying degrees of hair loss for alopecia classification, collected via crowdsourcing platforms. All images are authentic, depicting real individuals across different ages, genders, and ethnicities, suitable for machine learning and classification tasks.
- **Question:** Does the dataset support Norwood-Hamilton hair loss classification? — **Answer:** Yes. The dataset is organized for male hair loss analysis based on the Norwood-Hamilton scale, making it suitable for AI-powered baldness detection, dermatology research, and automated hair loss assessment.
- **Question:** Why are multi-angle scalp images important for AI training? — **Answer:** Hair thinning often appears differently depending on the viewing angle. Multi-view images enable computer vision models to learn complete scalp patterns, improving classification accuracy and hair density analysis.

[Full list of this site's AI-readable pages](https://unidata.pro/llms.txt)