Browsing by Subject "Face"

Now showing 1 - 3 of 3

Open Access
FAME: Face association through model evolution
(IEEE, 2015-06) Gölge, Eren; Duygulu, Pınar
We attack the problem of building classifiers for public faces from web images collected through querying a name. The search results are very noisy even after face detection, with several irrelevant faces corresponding to other people. Moreover, the photographs are taken in the wild with large variety in poses and expressions. We propose a novel method, Face Association through Model Evolution (FAME), that is able to prune the data in an iterative way, for the models associated to a name to evolve. The idea is based on capturing discriminative and representative properties of each instance and eliminating the outliers. The final models are used to classify faces on novel datasets with different characteristics. On benchmark datasets, our results are comparable to or better than the state-of-the-art studies for the task of face identification. © 2015 IEEE.
Open Access
Looking through the printmaking : site specific screenprint
(2006) Özmenoğlu, Ardan
The aim of this study is to explore the possibilities of how the surface of the background affects the foreground, which is the image of my face. When viewing an image produced by the printmaking process it can be seen that while surface is a part of the image, reciprocally, the image becomes a part of the surface. The projects I have conceived and implemented were based on exploring this phenomenon of the reciprocal interaction of image and canvas. The invisible support of the surface becomes visible. The reading of the art works is as background to the study, such as concepts of face, as in the face does not belong to the body, and surface as in the oscillation between beneath and above. Finally, I will discuss my screen prints in terms of techniques and especially, of the aforementioned concepts of Face and Surface.
Open Access
Recognizing faces in news photographs on the web
(IEEE, 2009-09) Zitouni, Hilal; Bulut, Muhammed Fatih; Duygulu, Pınar
We propose a graph based method in order to recognize the faces that appear on the web using a small training set. First, relevant pictures of the desired people are collected by querying the name in a text based search engine in order to construct the data set. Then, detected faces in these photographs are represented using SIFT features extracted from facial features. The similarities of faces are represented in a graph which is then used in random walk with restart algorithm to provide links between faces. Those links are used for recognition by using two different methods. © 2009 IEEE.