Unique identifiers for 13,617 subjects, allowing for longitudinal tracking across 55,134 total images. 2. Pre-computed & Engineered Features
: Longitudinal gaps ranging from several months up to five years per individual. morph ii dataset
Unlike many datasets that lack diversity, MORPH II is well-regarded for its extensive coverage of ethnic groups, including: African American Other groups. 3. Image Quality and Consistency Unlike many datasets that lack diversity, MORPH II
As of 2023-2025, the original hosting at UNCW has become less active, and the dataset is most reliably accessed via the National Institute of Standards and Technology (NIST) and face recognition research communities. MORPH II Dataset Composition: ├── Total Images: 55,134
MORPH II Dataset Composition: ├── Total Images: 55,134 ├── Total Identities: 13,000 ├── Time Horizon: 2003 – 2007 (4-Year Window) └── Primary Demographics: Black/White, Male/Female
The MORPH II dataset is a large-scale dataset of face images, consisting of over 55,000 images of 1,376 subjects. The dataset was collected from various sources, including mugshots, driver's licenses, and passport photographs. The images are diverse in terms of age, ethnicity, and image quality, making it a challenging benchmark for face recognition systems.
The (also known as MORPH Album 2) stands as one of the most influential and widely cited longitudinal face databases in the history of computer vision and biometrics. Released as a non-commercial research corpus, it contains 55,134 high-quality facial images across 13,617 unique individuals . Collected from real-world booking and mugshot records over a five-year span (2003 to late 2007), the dataset captured subjects arrested multiple times, providing a sequential, real-time look at how individual human faces change over months and years.