Introduction
The Hand Palm Recognition Dataset is a large-scale collection of 24,000 high-resolution palm images captured from 2,000 diverse participants using over 200 smartphone models. Unlike traditional palmprint databases that rely on specialized scanners in controlled lab environments, every image in this dataset was taken with a real consumer device making it directly applicable to mobile biometric authentication, contactless identity verification, and palm detection systems deployed in production
Dataset summary
|
Parameter
|
Value
|
|---|---|
|
Total Participants
|
2,000+ unique individuals
|
|
Total Images
|
24,000+ photos
|
|
Images per participant
|
12 images
|
|
Smartphone models
|
200+ (iOS & Android)
|
|
Camera types
|
Front-facing + back-facing
|
|
Ethnic groups
|
Black, South Asian, Caucasian, Arab/Middle Eastern, Hispanic, East Asian
|
|
Age range
|
Under 20 to 50+
|
|
Metadata format
|
JSON & CSV
|
Each participant provides 12 images: left and right hand, front and back camera, across 3 background variations. Metadata includes gender, ethnicity, birth year, profession, device model, OS, camera type, and handedness
Source and collection methodology
All images were collected from consenting participants across multiple countries, following strict ethical guidelines and GDPR-compliant data handling. Participants used their own smartphones, ensuring natural variation in device quality, lighting conditions, and hand positioning. No specialized equipment or controlled environments were used, the dataset reflects real-world capture conditions
Use cases and applications
Palm Recognition & Biometric Authentication. Train and evaluate palm-based identity verification systems for mobile banking, access control, and contactless payment applications. The dataset’s smartphone capture and demographic diversity ensure models generalize to real-world deployment
Hand Detection & Palm Detection. Build detection models that localize palms in unconstrained smartphone images. With 200+ device models and varying backgrounds, the dataset provides robust training data for detection pipelines
Fairness & Bias Auditing. Assess model performance across 6+ ethnic groups, multiple age brackets, and balanced gender representation. Rich demographic metadata enables fine-grained bias analysis, critical for responsible deployment of biometric systems
Why this dataset solves real production challenges
- 2,000 participants – 2-3x more than PolyU, IITD, or Tongji palmprint databases
- 24,000 images – comprehensive coverage with 12 images per subject
- 200+ smartphone models – unmatched cross-device diversity for robustness testing
- 6+ ethnic groups – Black, South Asian, Caucasian, Arab/Middle Eastern, Hispanic, East Asian
- Dual camera – front-facing and back-facing captures per participant
- Rich metadata – demographics, device info, and file mappings in JSON & CSV
Structured Metadata Included
Each participant record comes with detailed JSON and CSV metadata, enabling fine-grained filtering and analysis:
- Demographics – Gender, ethnicity, birth year, profession for fairness-aware model training
- Device Information – Smartphone model, OS (iOS/Android), camera type for cross-device evaluation
- Capture Setup – Camera side (front/back), hand (left/right), background variation for controlled experiments
- Handedness – Left-handed and right-handed participants for comprehensive palm coverage
- File Mappings – Direct links to all 12 images per participant for efficient data loading
Download information
A sample version of this dataset is available on Kaggle. Leave a request for additional samples in the form below
Have a question?
We collect data from consenting participants across multiple countries. All information is verified by our specialists
Once your enquiry has been sent, we will contact you to discuss the details and complete the necessary paperwork. The timing of receiving the dataset depends on the specific request and additional requirements
Our unique selling point is to provide legally clean datasets to our customers. We obtain the consent from all the participants to use their data for AI model development. We are able to provide comprensive reporting on the licensing, data collection and privacy compliance of our datasets. Although there seems to be a diverse response to how to control AI development and deployment, we are able to service global customers seeking to launch global AI products
The price depends on your specific requirements. Please submit a request to receive a free consultation
Most public palmprint databases (PolyU, IITD, Tongji) contain fewer subjects and were captured using specialized scanners. This dataset is 2–3x larger by participant count and was collected entirely on consumer smartphones, making it more representative of real-world deployment conditions
Contact us
Tell us about yourself, and get access to free samples of the dataset
Didn't find what you were looking for?
Our collection includes many datasets for various requests
iBeta Level 1 Dataset
– 35,000+ videos
– 85+ participants
– zoom in and
zoom out
iBeta Level 2 Dataset
– 25 000+ videos
– 3D masks
– iBeta Level 2
iBeta Level 3 Dataset
– 10,000+ videos
– 12 Unique Masks
– iBeta Level 3
Display Replay Dataset for Liveness Detection
– 9,000+ videos
– 6,500+ participants
– Balanced mix of genders and ethnicities
