Akinobu Maejima

Facial aging simulator considering geometry and patch-tiled texture

People can estimate an approximate age of others by looking at their faces. This is because faces have certain elements by which people can judge a persons age. If computers can extract and manipulate such information, wide variety of applications for entertainment and security purpose would be expected.

Future Cast System

Most likely, everyone has gone through dreaming of acting a hero in the movie. The system called “Future Case System”(FCS) is a new entertainment system that is easily able to accomplish that dream. FCS has been implemented in MITSUI TOSHIBA pavilion at Expo 2005 Aichi Japan first in the world. This attraction is to allow 240 theater attendances to have a role of the movie they are watching. Comparing FCS with Previous Attraction Systems (PASs), PASs provide the visual information to visitors one-sidedly. On the other hand, since attendances’ faces come out on the screen, they can feel as if they are acting in the movie. This is the main idea of FCS and makes attendances’ feeling of immersion increase.

Photorealistic aged face image synthesis by wrinkles manipulation

Many studies on an aged face image synthesis have been reported with the purpose of security application such as investigation for criminal or kidnapped child and entertainment applications such as movie or video game.

Detection of Driver's Drowsy Facial Expression

We propose a method for the estimation of the degree of a drivers drowsiness on basis of changes in facial expressions captured by an IR camera. Typically, drowsiness is accompanied by falling of eyelids. Therefore, most of the related studies have focused on tracking eyelid movement by monitoring facial feature points. However, textural changes that arise from frowning are also very important and sensitive features in the initial stage of drowsiness, and it is difficult to detect such changes solely using facial feature points. In this paper, we propose a more precise drowsiness-degree estimation method considering wrinkles change by calculating local edge intensity on faces that expresses drowsiness more directly in the initial stage.

Development of an integrated multi-modal communication robotic face

This paper presents an overview of the new version of our multi-model communication face “Mask-Bot”, a rear-projected animated robotic head, including our display system, face animation, speech communication and sound localization.

Facial Aging Simulation by Patch-Based Texture Synthesis with Statistical Wrinkle Aging Pattern Model

We propose a method for synthesizing a photorealistic human aged-face image based on the patch-based texture synthesis using a set of human face images of a target age. The advantage of our method is that it synthesizes an aged-face image with fine skin texture such as spots and pigments of facial skin, as well as age-related facial wrinkles without blurs (such as those resulting from lack of accurate pixel-wise alignments as in the linear combination model) while maintaining the quality of the original image.

Driver drowsiness estimation using facial wrinkle feature

In recent years, the rate of fatal motor vehicle accidents caused by distracted driving resulting from factors such as sleeping at the wheel has been increasing. Therefore, an alert system that detects driver drowsiness and prevents accidents as a result by warning drivers before they fall asleep is urgently required. Non-contact measuring systems using computer vision techniques have been studied, and in vision approach, it is important to decide what kind of feature we should use for estimating drowsiness.

An Empirical Study of Bringing Audience into the Movie

In this paper we first present an audience-participating movie experience DIM, in which the photo-realistic 3D virtual actor of audience is constructed by computer graphic technologies, and then evaluate the effects of DIMon audience experience using physiological and subjective methods. The empirical results suggest that the participation of virtual actors causes increased subjective sense of presence and engagement, and more intensive emotional responses as compared to traditional movie form; interestingly, there also significantly different physiological responses caused by the participation of virtual actors, objectively indicating the improvement of interaction between audience and movie.

Interactive shade control for cartoon animation

Shade in traditional cel animation is an essential element and plays a symbolic role in the artistic portrayal of character and scene. The shade on a characters face can be used to show emotion such as anger, sadness and hatred. Despite its usability, shade is relatively quickly or roughly drawn in animation for the following reasons. Firstly, cel animators require a large amount of time to draw shade. Secondly, because of the time requirements, producing complicated shade is expensive. On the other hand, 3D models enable users to more easily render or recreate shade than cel animation techniques. Consequently, 3D models are being gradually introduced into cartoon animation. Using Phongs 3D shading model, however, shade is rendered too realistically for cartoon animation, and is therefore not appropriate for traditional-style cel animation. To solve similar problems with highlighting, Anjyo and Hiramatsu proposed a procedural method for designing stylized highlights [Anjyo and Hiramatsu 2003]. This concept has been applied to shade in our system.

Facial Aging Simulator by Data-Driven Component-Based Texture Cloning

Facial aging and rejuvenation simulation is a challenging topic because keeping personal characteristics in every age is difficult problem. In this demonstration, we simulate a facial aging/rejuvenating only from a single photo. Our system alters an input face image to aged face by reconstructing every facial component with face database for target age. An appropriate facial components image are selected by a special similarity measurement between current age and target age to keep personal characteristics as much as possible. Our system successfully generated aged/ rejuvenated faces with age-related features such as spots, wrinkles, and sagging while keeping personal characteristics throughout all ages.