Figure 3 - uploaded by Roman Yampolskiy
Content may be subject to copyright.
Examples of different face images of the same subject from the Second Life avatar dataset with a complex background. Each image corresponds to the different head rotations while facing the camera. The frontal image is (a). (b) to ( e) represent the same
Source publication
It is desirable to address accessibility issues within virtual worlds. Moreover, curbing criminal activities within virtual worlds is a major concern to the law enforcement agencies. Forensic investigators and accessibility researchers are gaining considerable interests in detecting and tracking avatars as well as describing their appearance within...
Citations
... Before the emergence of deep learning technology, traditional object detection methods are mainly based on handdesigned features, such as scale-invariant feature transform (SIFT) [12], Haar-like feature (HAAR) [13], histograms of oriented gradient (HOG) [14], and so on. Due to the factors of the object itself and the imaging environment, the methods of manual design features have problems of poor robustness, poor generalization, and low detection accuracy [15]. ...
The indoor scene object detection technology is of important research significance, which is one of the popular research topics in the field of scene understanding for indoor robots. In recent years, the solutions based on deep learning have achieved good results in object detection. However, there are still some problems to be further studied in indoor object detection methods, such as lighting problem and occlusion problem caused by the complexity of the indoor environment. Aiming at these problems, an improved object detection method based on deep neural networks is proposed in this paper, which uses a framework similar to the Single Shot MultiBox Detector (SSD). In the proposed method, an improved ResNet50 network is used to enhance the transmission of information, and the feature expression capability of the feature extraction network is improved. At the same time, a multi-scale contextual information extraction (MCIE) module is used to extract the contextual information of the indoor scene, so as to improve the indoor object detection effect. In addition, an improved dual-threshold non-maximum suppression (DT-NMS) algorithm is used to alleviate the occlusion problem in indoor scenes. Finally, the public dataset SUN2012 is further screened for the special application of indoor scene object detection, and the proposed method is tested on this dataset. The experimental results show that the mean average precision (
mAP
) of the proposed method can reach 54.10%, which is higher than those of the state-of-the-art methods.
... Notable work has been carried out in applying biometric principles on avatar faces. Artimetrics: a field of study that identifies, classifies and authenticates avatars, virtual robots and virtual reality agents [9], verification and recognition of avatar faces [10], a personalized avatar creation system [21], Avatar DNA that aims to link the biometrics of the user to his/her avatar profile [22], detecting avatar faces [23], recognizing avatar faces [24] and examining the personality of an avatar's character based on its facial appearance [25]. Besides avatars, face recognition has also been applied on viewed sketches [26] and forensic sketches [27], [28] mapping them to their corresponding digital pictures. ...
Face classification is a technique used in Biometrics to help distinguish between facial images. However, this technique has been applicable on human face images only. Online virtual worlds such as Second Life, Sims Online, etc. are gaining popularity over the Internet. They require human users to create a digital persona of oneself, known as an 'avatar'. Several avatars are designed to resemble human users. With crime being reported in virtual worlds, computer-generated avatar faces being created from human faces and human-resembling humanoids being designed, there is a need to distinguish between natural and artificial faces. Our work applies two new face classification techniques on grayscale, facial images of humans and avatars to tell them apart. (1) Uniform Local Directional Pattern (ULDP) utilizes the uniform patterns from Local Directional Pattern (LDP) (2) Wavelet Uniform Local Directional Pattern (WULDP) applies the ULDP technique on the wavelet transform of an image. Extensive experiments conducted on five different face image datasets (Caltech, FERET for human faces and Entropia, Second Life, Evolver for avatar faces) achieve baseline average classification accuracies of 98.55% using ULDP and 89.55% using WULDP respectively.
... Due to the growing number of virtual crimes, avatar tracking and recognition is becoming an important problem which security professionals and forensic investigators face every day. To address that problem authors have proposed a new field of research: Artimetrics -a field of study that identifies, classifies and authenticates virtual reality avatars, robots and intelligent software agents [45,49,48,16,22,46,50,2,7,17,47,12,3,26]. ...
The Artimetrics, a field of study that identifies, classifies and authenticates virtual reality avatars and intelligent software agents, has been proposed as a tool for fighting crimes taking place in virtual reality communities and in multiplayer game worlds. Forensic investigators are interested in developing tools for accurate and automated tracking and recognition of avatar faces. In this paper, we evaluate state of the art academic and commercial algorithms developed for human face recognition in the new domain of avatar recognition. While the obtained results are encouraging, ranging from 53.57% to 79.9% on different systems, the paper clearly demonstrated that there is room for improvement and presents avatar face recognition as an open problem to the pattern recognition and biometric communities.
Use of protective gear helmet head is often considered unimportant and trivial by workers. Whereas the use of protective headgear helmet is very important and affect the safety and health of workers. Kedisiplina workers to use protective gear head is still low so that the risk of accidents that could endanger workers large enough. In this research aims to detect protective equipment head helmet on video. In this study, the method used is the Haar Cascade Classifier. The system consists of two main processes, namely the process of training data and the detection process. This method of training process has four main processes, haar-like feature, integral image, no-boost and cascade classifier. Haar-like feature is a collection of special features presented the head, face and helmet. Citra is how to quickly calculate integrals haar feature. While no-boost are statistically weighted feature values are obtained and filtered using a cascade classifier. The detection process in this study there are two processes, the first detection process whether human or not, if the result of human detected will continue the process of detection of whether to use a helmet or not. Detection system testing is done individually using helmet colors red, blue and yellow. It obtained accuracy rate of 92%, while the testing group obtained the degree of accuracy of 71%.
This chapter presents an overview and classification of security approaches based on computer analysis of human behavior. Overview of different methodologies is followed by an analysis of achieved accuracy rates, required equipment and prospects for future improvements. In particular the following broad categories of behavior-based authentication mechanisms are examined: Behavioral Biometrics (Authorship based, Human–Computer Interaction based, Motor Skill, and Purely Behavioral), Behavioral Passwords (syntactic, semantic, one-time methods and visual memory based), Biosignals (cognitive and semi-controllable biometrics) and Virtual Biometrics (representations of users in virtual worlds).
