Scribd
Upload
60 views3 pages

Face Detection Documentation

This document describes a face detection project that uses a rejection-based classification approach. The detector consists of several steps: 1) Skin color segmentation is used to reject non-skin color regions by defining thresholds in HSV color space based on histograms of training face images. 2) Morphological operations filter remaining regions. 3) Connected regions are classified based on geometry and number of holes. 4) Template matching detects faces in each region. The goal is to detect faces in images similar to training images provided for the project.

Uploaded by

Ajith Kumar M
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
60 views3 pages

Face Detection Documentation

This document describes a face detection project that uses a rejection-based classification approach. The detector consists of several steps: 1) Skin color segmentation is used to reject non-skin color regions by defining thresholds in HSV color space based on histograms of training face images. 2) Morphological operations filter remaining regions. 3) Connected regions are classified based on geometry and number of holes. 4) Template matching detects faces in each region. The goal is to detect faces in images similar to training images provided for the project.

Uploaded by

Ajith Kumar M
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 3

Face Detection Project

Waqar Mohsin wmohsin@stanford.edu


Noman Ahmed khattak@stanford.edu
Chung-Tse Mar ctmar@stanford.edu

May 26, 2003

EE368 Digital Image Processing


Spring 2002-2003
Department of Electrical Engineering
Stanford University
EE368 Digital Image Processing

1 Introduction
The goal of this project is to detect and locate human faces in a color image. A set of seven
training images were provided for this purpose. The objective was to design and implement a face
detector in MATLAB that will detect human faces in an image similar to the training images.

The problem of face detection has been studied extensively. A wide spectrum of techniques have
been used including color analysis, template matching, neural networks, support vector machines
(SVM), maximal rejection classification and model based detection. However, it is difficult to
design algorithms that work for all illuminations, face colors, sizes and geometries, and image
backgrounds. As a result, face detection remains as much an art as science.

Our method uses rejection based classification. The face detector consists of a set of weak
classifiers that sequentially reject non-face regions. First, the non-skin color regions are rejected
using color segmentation. A set of morphological operations are then applied to filter the clutter
resulting from the previous step. The remaining connected regions are then classified based on
their geometry and the number of holes. Finally, template matching is used to detect zero or more
faces in each connected region. A block diagram of the detector is shown in Figure 1.

Figure 1. Block diagram of face detector

2 Skin Color Segmentation


The goal of skin color segmentation is to reject non-skin color regions from the input image. It is
based on the fact that the color of the human face across all races agrees closely in its
chrominance value and varies mainly in its luminance value.

We chose the HSV (Hue, Saturation, Value) color space for segmentation since it decouples the
chrominance information from the luminance information. Thus we can only focus on the hue
and the saturation component. The faces in each training image were extracted using the ground
truth data and a histogram was plotted for their H and S color component (Figure 2). The
histograms reveal that the H and S color components for faces are nicely clustered. This
information was used to define appropriate thresholds for H and S space that correspond to faces.
The threshold values were embedded into the color segmentation routine.

During the execution of the detector, segmentation is performed as follows:


1. The input image is subsampled at 2:1 to improve computational efficiency
2. The resulting image is converted to HSV color space
3. All pixels that fall outside the H and S thresholds are rejected (marked black).

The result is shown in Figure 3.

1
EE368 Digital Image Processing

Figure 2. Histograms for the H and S components of all faces in training image1

Figure 3. Image after histogram thresholding (training image 1)

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy