Showing papers by "Hazim Kemal Ekenel published in 2015"

Accio: A Data Set for Face Track Retrieval in Movies Across Age

Abstract: Video face recognition is a very popular task and has come a long way. The primary challenges such as illumination, resolution and pose are well studied through multiple data sets. However there are no video-based data sets dedicated to study the effects of aging on facial appearance. We present a challenging face track data set, Harry Potter Movies Aging Data set (Accio1), to study and develop age invariant face recognition methods for videos. Our data set not only has strong challenges of pose, illumination and distractors, but also spans a period of ten years providing substantial variation in facial appearance. We propose two primary tasks: within and across movie face track retrieval; and two protocols which differ in their freedom to use external data. We present baseline results for the retrieval performance using a state-of-the-art face track descriptor. Our experiments show clear trends of reduction in performance as the age gap between the query and database increases. We will make the data set publicly available for further exploration in age-invariant video face recognition.

Action unit intensity estimation using hierarchical partial least squares

Abstract: Estimation of action unit (AU) intensities is considered a challenging problem. AUs exhibit high variations among the subjects due to the differences in facial plasticity and morphology. In this paper, we propose a novel framework to model the individual AUs using a hierarchical regression model. Our approach can be seen as a combination of locally linear Partial Least Squares (PLS) models where each one of them learns the relation between visual features and the AU intensity labels at different levels of details. It automatically adapts to the non-linearity in the source domain by adjusting the learned hierarchical structure. We evaluate our approach on the benchmark of the Bosphorus dataset and show that the proposed approach outperforms both the 2D state-of-the-art and the plain PLS baseline models. The generalization to other datasets is evaluated on the extended Cohn-Kanade dataset (CK+), where our hierarchical model outperforms linear and Gaussian kernel PLS.

Game design for physical therapy and rehabilitation using Kinect

Abstract: In this paper, we present a game, which is designed according to gamification concept for rehabilitation patients. This game can also be used for physical exercising. Main motivation for designing this game is making rehabilitation gestures, which might be boring and difficult, more enjoyable for patients and common users. The game is designed by using Unity game engine and Kinect hardware. Kinect is used for taking joint coordinates from user. Using the extracted features, we calculated if user makes the correct gesture. Main theme of designed game is maze. User can control the character in the game with body motions in order to find the exit of the maze. Also there are different games in the maze and the user have to play different levels of these games to proceed in the maze.

Combining view-based pose normalization and feature transform for cross-pose face recognition

Abstract: Automatic face recognition across large pose changes is still a challenging problem. Previous solutions apply a transform in image space or feature space for normalizing the pose mismatch. For feature transform, the feature vector extracted on a probe facial image is transferred to match the gallery condition with regression models. Usually, the regression models are learned from paired gallery-probe conditions, in which pose angles are known or accurately estimated. The solution based on image transform is able to handle continuous pose changes, yet the approach suffers from warping artifacts due to misalignment and self-occlusion. In this work, we propose a novel approach, which combines the advantage of both methods. The algorithm is able to handle continuous pose mismatch in gallery and probe set, mitigating the impact of inaccurate pose estimation in feature-transform-based method. We evaluate the proposed algorithm on the FERET face database, where the pose angles are roughly annotated. Experimental results show that our proposed method is superior to solely image/feature transform methods, especially when the pose angle difference is large.

Analyzing effects of face modalities

Abstract: In this paper, we investigate the effect of face modalities on each other. Analysing the effect of face modalities is a difficult research problem, because of the lack of publicly available annotated databases, in which each sample has labels for each face mode. We selected gender and age face modes to analyse their effect between them. The database is divided into groups uniformly and there is no overlap between training and testing sets. Same amount of training samples is used to train each model to avoid the effect of having different amount of training samples to the results. According to obtained results, utilising the correlation between the face modes provided better results than using the face modes alone.

Eye blink based warning system for eye health while using computers

Abstract: In this paper, we present a computer vision based real-time warning system to prevent the formation of eye diseases of people working continuously in front of computers. This system takes an image of user sitting in front of the computer by web camera then processes it to determine how often user blinks. The system warns user, if there is not sufficient number of eye blinks for a long time. The general flow of the eye blink based warning system consists of three main steps: face and eye detection, feature extraction of preprocessed eye images, and open-close classification of eye images. The system has attained high performance in the experiments. Moreover, the developed system has been turned into a computer plug-in that can work real-time and is available for practical use.

Rotation update on manifold in probabilistic NRSFM for robust 3D face modeling

Abstract: This paper focuses on recovering the 3D structure and motion of human faces from a sequence of 2D images. Based on a probabilistic model, we extensively studied the rotation constraints of the problem. Instead of imposing numerical optimizations, the inherent geometric properties of the rotation matrices are taken into account. The conventional Newton’s method for optimization problems was generalized on the rotation manifold, which ultimately resolves the constraints into unconstrained optimization on the manifold. Furthermore, we also extended the algorithm to model within-individual and between-individual shape variances separately. Evaluation results give evidence to the improvement over the state-of-the-art algorithms on the Mocap-Face dataset with additive noise, as well as on the Binghamton University A 3D Facial Expression (BU-3DFE) dataset. Robustness in handling noisy data and modeling multiple subjects shows the capability of our system to deal with real-world image tracks.