Cyberware

Abstract: A method of manifold representation for human faces with pose variations is proposed. Our model consists of mappings between 3D head angles and facial images separately represented in shape and texture, via sub-space models spanned by principal components (PC). Explicit mappings to and from 3D head angles are used as processes of pose estimation and transformation, respectively. Generalization capability to unknown head poses enables our model to continuously cover pose parameter space, providing high approximation accuracy. The feasibility of this model is evaluated in a number of experiments. We also propose a novel pose-invariant face recognition system using our model as the entry format for a gallery of known persons. Experimental results with 3D facial models recorded by a Cyberware scanner show that our model provides a superior recognition performance against pose variations, and that the texture synthesis process is carried out correctly.

Abstract: Describes a system for automatically digitizing the surfaces of a completely unknown object to a prescribed sampling density. Unlike many available commercial systems (e.g. Cyberware), our system analyzes actively the data and computes sensor trajectories to achieve complete surface coverage taking into account the limitations of the sensor/manipulator. This represents in fact an active approach to the problem of complete object digitization, working directly at the measurement level, as opposed to existing off-line methods that perform post-processing on a fixed data set. We propose a theoretical framework to achieve this goal and we present preliminary results of a laboratory implementation.

Abstract: Quantification of facial mimic ability represents a need for comparative investigation in facial medicine and surgery. The aim of the current study was to develop a simple, noninvasive, re- peatable three-dimensional method for measuring facial mobility in clinical and research setup. The faces of 20 healthy adult subjects (10 men and 10 women) and 12 primary school children (6 boys and 6 girls), without cra- niofacial pathologic injuries or previous treatments, were captured by a Cyberware 3030RGB laser scanner (Cyberware, Inc, Monterey, CA) in rest position and during voluntary movements. Data were processed by Cyberware Echo (Cyberware, Inc) and Inus Rapidform 2004 software (INUS Technologies Inc, Seoul, South Korea). Each movement was assigned a main landmark. The facial move- ments were described for surface displacement using clearance vec- tor mapping and three-dimensional tracing of the skin landmarks. The mean landmark displacement vector was also calculated for every movement. The study showed that movements were characterized by similar displacement in the same facial areas in all subjects. Minor differ- ences were recorded between adult subjects and children. Descrip- tive statistics concerning the amount and direction of movements were provided. A case of unilateral postsurgical nerve palsy was prospectively analyzed to test applicability of the method in clinical investigation. A numerical scale based on the mean movements was constructed and used to monitor recovery of function. The method developed seems easy, noncontact, and effective to quantify facial movements in normal and pathologic conditions. It may be usefully applied to the investigation and the clinical moni- toring of different medical and surgical pathologic conditions.

Abstract: The Cyberware WB4 whole body scanner is one of the first scanning systems in the world that generates a high resolution data set of the outer surface of the human body. The Computerized Anthropometric Research and Design (CARD) Laboratory of Wright-Patterson AFB intends to use the scanner to enable quick and reliable acquisition of anthropometric data. For this purpose, a validation study was initiated to check the accuracy, reliability and errors of the system. A calibration object, consisting of two boxes and a cylinder, was scanned in several locations in the scanning space. The object dimensions in the resulting scans compared favorably to the actual dimensions of the calibration object.