Face Detection on the iPhone

Download the talk as a PDF (4.4MB), or view it on iWork.com. The associated visualization by Adam Harvey and sample code (20.8MB) built during the talk are also available.
Download Chapter 7 (2.7MB) for free.

Visualising Haar Classifiers

OpenCV Face Detection by Adam Harv.

This video by Adam Harvey visualizes the detection process of OpenCV library's face detector.

This visualization was created as part of the CV Dazzle project by Adam Harvey during his work on the Interactive Telecommunications Program at NYU.


The OpenCV library is a collection of routines intended for real-time computer vision, released under the BSD License, free for both private and commercial use. The library has a number of different possible applications including object recognition and tracking.

Given during OSCON 2010 in Portland, OR. This talk walks through the cross-compiling and building a static distribution of the library which you can link to your application and make use of from both the iPhone Simulator and the iPhone (and iPod touch) device itself.

It discusses how to build a simple application to perform face recognition on images taken directly using the iPhone's own camera. It assumes some experience with programming the iPhone and with Objective-C, and experience with the command line build tools.


"Programming iPhone Sensors" is published by O'Reilly Media.