Abdallah A. Mohamed

An improved LBP algorithm for avatar face recognition

This paper presents a novel avatar face recognition algorithm based on Discrete Wavelet Transform and LBP descriptor. The 2-D Discrete Wavelet Transform has been used to process the avatar face dataset by extracting the low frequency components and then forming the low frequency sub-images. Then the LBP operator is used to extract the characterizations of these sub-images. Finally, the Chi-Square distance is used to connect each image to its subject. Experimental results show that the proposed method can be used effectively in avatar face recognition with a single training sample per avatar. The performance of the proposed algorithm on a dataset of 581 avatar face images shows that the proposed algorithm performs better than PCA and Traditional (single scale) LBP method with respect to the recognition rate.

Avatar Face Recognition Using Wavelet Transform and Hierarchical Multi-scale LBP

Recognizing avatars in virtual worlds is a very important issue for law enforcement agencies, terrorism and security experts. In this paper, a novel face recognition technique based on wavelet transform and Hierarchical Multi-scale Local Binary Pattern (HMLBP) is presented and shown to increase the accuracy of recognition of avatar faces. The proposed technique consists of three stages: preprocessing, feature extraction and recognition. In the preprocessing and feature extraction stages, the wavelet decomposition is used to enhance the common features of the same class of images and the HMLBP is used to extract representative features from each avatar face image without a need for any training. In the recognition stage, the Chi-Square distance is used to achieve a robust decision and to indicate the correct class to which the input image belongs. Experiments conducted on two manually cropped avatar image datasets (Second Life and Entropia Universe) show that the proposed technique performs better than traditional (single scale) LBP, Wavelet Local Binary Pattern (WLBP) and HMLBP in terms of accuracy (78.57% and 67.50% recognition rates for Second Life and Entropia Universe datasets respectively).

Artificial Face Recognition Using Wavelet Adaptive LBP with Directional Statistical Features

In this paper, a novel face recognition technique based on discrete wavelet transform and Adaptive Local Binary Pattern (ALBP) with directional statistical features is proposed. The proposed technique consists of three stages: preprocessing, feature extraction and recognition. In preprocessing and feature extraction stages, wavelet decomposition is used to enhance the common features of the same subject of images and the ALBP is used to extract representative features from each facial image. Then, the mean and the standard deviation of the local absolute difference between each pixel and its neighbors are used within ALBP and the nearest neighbor classifier to improve the classification accuracy of the LBP. Experiments conducted on two virtual world avatar face image datasets show that our technique performs better than LBP, PCA, multi-scale Local Binary Pattern, ALBP and ALBP with directional statistical features (ALBPF) in terms of accuracy and the time required to classify each facial image to its subject.

Adaptive Extended Local Ternary Pattern (AELTP) for Recognizing Avatar Faces

Many face recognition techniques have been developed during the past decades but the problem remains challenging, especially recognizing non-biological entities or avatars. Local Binary Pattern (LBP) method is one of these techniques which has shown its superiority in recognizing faces. The original LBP operator mainly thresholds pixels in a specific predetermined window based on the gray value of the central pixel of that window. As a result the LBP operator becomes more sensitive to noise especially in near-uniform or flat area regions of an image. To deal with this problem a generalization of the LBP descriptor, Local Ternary Patterns (LTP), came to the presence. In this paper we introduce a new local adapted texture features for efficient avatar face recognition based on the original LTP operator. The proposed technique, Adaptive Extended Local Ternary Pattern (AELTP), shares with the original LTP descriptor being less sensitive to noise. However AELTP is better as it determines the local pattern threshold automatically based on local statistics. Experiments conducted on two virtual world avatar face image datasets show that our technique performs better than original LBP, original LTP and Extended LTP (ELTP) in terms of accuracy.

Face Recognition Based on Wavelet Transform and Adaptive Local Binary Pattern

Local Binary Pattern (LBP) is a very efficient local descriptor for describing image texture. In this paper, we propose a novel face recognition technique based on wavelet transform and the least square estimator to enhance the classical LBP. First, Wavelet transform is used to decompose a given image into four kinds of frequency images from which the features of that image can be extracted. Then, the least square estimation of local difference between each image pixel and its neighborhoods is used to build the adaptive LBP. Finally, the classification accuracy is computed using a nearest neighbor classifier with Chi-square as a dissimilarity measure. Experiments conducted on three face image datasets (ORL dataset and two avatar face image datasets); show that the proposed technique performs better than traditional methods (single scale) LBP and PCA, Wavelet Local Binary Pattern (WLBP) and Adaptive Local Binary Pattern (ALBP) in terms of accuracy.

Artificial human face recognition via Daubechies wavelet transform and SVM

This work presents an approach for applying face recognition to non-biological entities (avatars) in virtual worlds to achieve authentication. Massively multiplayer online games involve virtual worlds which require avatar identification to avoid fraud. First, virtual worlds and avatars are briefly discussed. Next, the concepts of facial biometrics and the face recognition systems are presented. Later, support vector machines and wavelet transforms are introduced as classification tools. Finally, the dataset and the designed biometric system are described with the obtained results.

Learning Visual Features for the Avatar Captcha Recognition Challenge

Captchas are frequently used on the modern world wide web to differentiate human users from automated bots by giving tests that are easy for humans to answer but difficult or impossible for algorithms. As artificial intelligence algorithms have improved, new types of Captchas have had to be developed. Recent work has proposed a new system called Avatar Captcha, in which a user is asked to distinguish between facial images of real humans and those of avatars generated by computer graphics. This novel system has been proposed on the assumption that this Captcha is very difficult for computers to break. In this paper we test a variety of modern visual features and learning algorithms on this avatar recognition task. We find that relatively simple techniques can perform very well on this task, and in some cases can even surpass human performance.

Solving Avatar Captchas Automatically

Captchas are challenge-response tests used in many online systems to prevent attacks by automated bots. Avatar Captchas are a recently-proposed variant in which users are asked to classify between human faces and computer-generated avatar faces, and have been shown to be secure if bots employ random guessing. We test a variety of modern object recognition and machine learning approaches on the problem of avatar versus human face classification. Our results show that using these techniques, a bot can successfully solve Avatar Captchas as often as humans can. These experiments suggest that this high performance is caused more by biases in the facial datasets used by Avatar Captchas and not by a fundamental flaw in the concept itself, but nevertheless our results highlight the difficulty in creating Captcha tasks that are immune to automatic solution.

Behavioral Biometrics: Categorization and Review

This work categorizes and reviews behavioral biometrics with the inclusion of future-oriented techniques. A general introduction to this field is given alongside the benefits of this non-intrusive approach. It presents the examination and analysis of the current research in the field and the different types of behavior-centric features. Accuracy rates for verifying users with different behavioral biometric approaches are compared. Privacy issues that will or may arise in the future with behavioral biometrics are also addressed. Finally, the general properties of behavior, the influence of environmental factors on observed behavior and the potential directions for future research in the field of behavioral biometrics are discussed.

Recognizing Avatar Faces Using Wavelet-Based Adaptive Local Binary Patterns with Directional Statistical Features

In this paper, a novel face recognition technique based on discrete wavelet transform and Adaptive Local Binary Pattern (ALBP) with directional statistical features is proposed. The proposed technique consists of three stages: preprocessing, feature extraction and recognition. In preprocessing and feature extraction stages, wavelet decomposition is used to enhance the common features of the same subject of images and the ALBP is used to extract representative features from each facial image. Then, the mean and the standard deviation of the local absolute difference between each pixel and its neighbors are used within ALBP and the nearest neighbor classifier to improve the classification accuracy of the LBP. Experiments conducted on two virtual world avatar face image datasets show that our technique performs better than LBP, PCA, multi-scale Local Binary Pattern, ALBP and ALBP with directional statistical features (ALBPF) in terms of accuracy and the time required to classify each facial image to its subject.