Face Recognition System

On-Line Face Verification Module. Just select two facial images.

Images must have the same size, they can be RGB or gray scale, with N by M by 3 pixels, where N is image height in pixels, M is image width in pixels and 3 is the number of color components (Red, Green and Blue components). For gray scale images these components are equal. You can use CMU AMP Face EXpression Database. There are 13 subjects in this database, each with 75 images. Each file is named as: "*##.bmp", where * is the index of subject (a letter between A and M), and ## is the index of face image for this subject (a number between 00 and 74). Some URL examples: facedb/A00.bmp facedb/D32.bmp facedb/M74.bmp

URL of first image:

URL of second image:

In order to obtain the source code please email us luigi.rosa@tiscali.it.


October 30th, 2013


Text-independent speaker recognition based on Wavelet Transform. Click here to try this advanced script.


Face verification based on Advanced Correlation Filters. Click here to try this script developed entirely in PHP language.


PhiImage Image Processing Library. Click here for an on-line demo version.