Face Detection

Resources for Face Detection


This web page contains information of face detection works. As a first step to encourage researchers to embark on this topic, we also provide some sample code, scripts, and plots to develop face detection systems. Consequently, this page does not contain all the detailed information that you may need. Nevertheless, we think it contains "substantial" information that you will find useful in developing face detection methods (01/21/2001).


Recent methods (after March, 2001) that are not included in the survey paper due to publication deadline

In this page, you will find the following information:

Please send comments or suggestions to: mhyang@vision.ai.uiuc.edu , or visit my web page

Face Database

Data Set



MIT Media Labs Database


Faces of 16 people, 27 of each person under various illumination conditions, scale and head orientation.

MIT CBCL Face Data Set


A training set consists of 6,977 cropped images (2,429 faces and 4,548 nonfaces), and the test set consists of 24,045 images (472 faces and 23,573 nonfaces).

FERET Database


A large collection of male and female faces. Each image contains a single person with certain expression.




564 images of 20 subjects. Each subject covers a range of poses from profile to frontal views.

University of Bern


300 frontal view face images of 30 people (10 images per person) and 150 profile face images (5 images per person).

Yale Database


Face images with expressions, glasses under different illumination conditions.

AT&T (Olivettti) Database


40 subjects, 10 images per subject. (10 images per person) and 150 profile face images (5 images per person)

Harvard Database


Cropped, masked frontal face  images under a wide range of  illumination conditions.

M2VTS Database


A multimodal database containing various image sequences.

Purdue Database


3,276 face images with  different facial expressions and occlusions under different illuminations.

Benchmark Database

Data Set



MIT Test Set


Two sets of high and low resolution gray scale images with multiple faces in complex background. Subsumed by CMU frontal face test set.

CMU Frontal Face Test Set


130 gray scale images with a total of 507 frontal 507 frontal faces.

CMU Profile Face Test Set


208 gray scale images with faces in profile views. 

Kodak Data Set


Faces of multiple size, pose and under varying illumination in color images. Designed for face detection and recognition.

Sample Face Detection Code and Evaluation Tools

Note: The section provides a sample code for face detection in gray-scale images. It is not an full-fledged system that you can retrieve detected faces in an image. Our intention is to provide a first step for researchers to get some exposure to this subject. The code is provided as is since we may not have time to update/modify the code. We hope and encourage researchers to develop better evaluation protocol for face detection.

Sample Codes