遺傳算法在人臉識(shí)別特征選擇中的應(yīng)用
達(dá)爾亞 俄澤坎
土耳其畢爾坎特大學(xué)，計(jì)算機(jī)工程部，安卡拉
摘要
人臉識(shí)別對(duì)計(jì)算機(jī)視覺(jué)問(wèn)題一直是個(gè)挑戰(zhàn)。為了解決這個(gè)這個(gè)問(wèn)題，篩選功能[1]已被用于[2] 。不過(guò)，自從篩選特征被定位于物體識(shí)別以來(lái)，我們需要選擇最適合在面部識(shí)別的問(wèn)題。因此，在本文中，我們使用遺傳算法來(lái)選擇最重要的特點(diǎn)來(lái)進(jìn)行人臉識(shí)別。
關(guān)鍵詞：遺傳算法，特征選擇，人臉識(shí)別，篩選功能
1. 引言
本文中，我們的目標(biāo)是選擇最有用的特征，并將它應(yīng)用于人臉識(shí)別中?；谶@樣的目的，我們使用遺傳算法去學(xué)習(xí)篩選功能的某種特征[1]。它能夠應(yīng)用到目標(biāo)識(shí)別，能夠?qū)θ四樀哪硞€(gè)特點(diǎn)進(jìn)行描述。
使用篩選功能進(jìn)行臉部識(shí)別已被提議在[2]中。我們相信找到這些在人臉識(shí)別中十分有用的特征的共同點(diǎn)將對(duì)人臉識(shí)別產(chǎn)生極好的結(jié)果。因?yàn)槲覀儨p少了不必要的特征，所以這將極大的減少計(jì)算機(jī)的識(shí)別時(shí)間。
首先我們?cè)赼部分中給出了篩選功能和人臉識(shí)別問(wèn)題的相關(guān)信息；在b部分中給出了遺傳算法的方法。在第2條中我們介紹了我們?nèi)绾卫眠z傳算法來(lái)選擇最佳的功能進(jìn)行人臉識(shí)別。第3條中則給出了實(shí)驗(yàn)結(jié)果，并在進(jìn)行了簡(jiǎn)要的總結(jié)概括后，對(duì)算法的可擴(kuò)展性做了一些未來(lái)性的工作。
Feature Selection for Face Recognition
Using a Genetic Algorithm
Derya Ozkan
Bilkent University, Department of Computer Engineering
Turkey, Ankara

ABSTRACT
Face recognition has been one of the challenging problems of computer vision.Inresponse to this problem, SIFT features [1] have been used in [2]. However, since SIFT features were addressed to object recognition; we need to select the features that best fits in the face recognition problem. So, in this paper, we are using a genetic algorithm to select the most important features for face recognition.

Keywords: Genetic Algorithm, Feature Selection, Face Recognition, SIFT Features
1. INTRODUCTION
In this paper, we aim to select the most useful features for face recognition. For this purpose, we use a genetic algorithm to learn which features of SIFT features [1], used in object recognition, can describe an interest point of the face.
A face recognition approach using the SIFT features has been proposed in [2]. We believe that finding the subset of those features, which are more useful for face recognition,will lead to better results for the face recognition problem. It will reduce the computation time since we remove the unnecessary features.
We first give information about SIFT features and the problem of face recognition in part a; and the genetic algorithm approach in part b. In section 2, we show how we can use genetic algorithm to select the best features for face recognition. Section 3 gives the experimental results; and in conclusion after a summary, we give future works that can be done to extend the algorithm.