[其它] Face Recognition and Clustering for Home Photos

[复制链接]

彬彬

797 主题	1 听众	1万积分

资深设计师

Rank: 7 Rank: 7 Rank: 7

纳金币: 5568
精华: 0

电梯直达

楼主

发表于 2012-1-5 08:55:57 |只看该作者 |倒序浏览

Abstract

In this work, we focus on clustering faces in home photos by face

recognition technologies. We propose two methods to improve the

approach based on a well-known algorithm, local binary patterns.

The adoption of the partial matching metric improves the recognition

accuracy under face pose variations, while the adoption of the

Gabor filter improves the accuracy under noises and various illuminations.

We evaluate our methods on two home photo sets. In both

evaluations, the results show that our methods improve the performance

in accuracy. Compared to baseline LBP methods, in both

evaluations, the results show that our methods improve the performance

in accuracy from 90.4% to 99.5% and from 94.7% to 99.6%

in two home-photo data sets respectively. Even compared to Google

Picasa, the number of clusters where there is only one photo (thus

can not be merged with other clusters, also means not good), our

methods show that the number of “single” clusters reduced by half

can be achieved. Our experience also shows that GPU speedup for

Gabor filter can reach 140 times, and the overall system plus clustering

can thus have 10 times speedup for face recognition.

1 Introduction

As the popularity of digital camera increases over time, when people

go on vacation, they always take many pictures. Sometimes

people may need to find out the pictures of some people, and it takes

long time to check out all the pictures. We want to design a system

so that we can use it to find out who are in the pictures, or who

are always in the same photos. In this case, we are dealing with

photos taken by everyday people, called “Home Photos”. These

home photos perhaps contain a lot of noise or occlusion, varies luminance,

and non-frontal faces, which increase the difficulty of face

recognition.

In this work, we improve a well known face recognition algorithm

based on local binary patterns to be more reliable on recognizing

home photos. Local binary patterns-based (LBP-based) face recognition

has been proven successful and becomes popular since proposed

by T. Ahonen et al. because of its high accuracy and efficiency.

Like other existed works, LBP-based algorithm is originally

designed for recognition under restricted environments. We propose

two methods for LBP-based algorithm to overcome the weakness

in home photos