In this paper, we present an example-based approach for automatically generating a life-like portrait from a frontal face image. Based on an inhomogeneous Markov Random Field Model, an inhomogeneous non-parametric sampling scheme is used to capture the complex statistical characteristics of face image and corresponding portrait. In our approach, only those pixels corresponding to a portrait poi...

One of the most famous drawings by Leonardo da Vinci is a self-portrait in red chalk, where he looks quite old. In fact, there is a sketch in one of his notebooks, partially covered by written notes, that can be a self-portrait of the artist when he was young. The use of image processing, to remove the handwritten text and improve the image, allows a comparison of the two portraits. A special e...

In one of his paintings, the School of Athens, Raphael is depicting Leonardo da Vinci as the philosopher Plato. Some image processing tools can help us in comparing this portrait with two Leonardo's portraits, considered as self-portraits. The "Scuola di Atene" is one of the most famous paintings by Raphael, the Italian Renaissance artist. Painted between 1510 and 1511, this fresco decorates th...

Wireless networks have been rapidly developing in recent years. GPRS and CDMA 1X for wide areas, and 802.11 and Bluetooth for local areas have already emerged. Broadband wireless networks urgently call for rich contents for consumers. Among various possible applications, video conferencing is one of the most promising for mobile devices on wireless networks. This paper describes the generation,...

In this paper, we present an automatic human portrait system based on the And-Or graph representation. The system can automatically generate a set of life-like portraits in different styles from a frontal face image. The system includes three subsystems, each of which models hair, face and collar respectively. The face subsystem can be further decomposed into face components: eyebrows, eyes, no...

This paper presents a method for learning artistic portrait lighting template from a dataset of artistic and daily portrait photographs. The learned template can be used for (1) classification of artistic and daily portrait photographs, and (2) numerical aesthetic quality assessment of these photographs in lighting usage. For learning the template, we adopt Haar-like local lighting contrast fea...

We investigated the familiar phenomenon of the uncanny feeling that represented people in frontal pose invariably appear to "face you" from wherever you stand. We deploy two different methods. The stimuli include the conventional one-a flat portrait rocking back and forth about a vertical axis-augmented with two novel variations. In one alternative, the portrait frame rotates whereas the actual...

In this paper we propose a sketch-based interface for drawing and generating a realistic 3D human face with texture. The free form sketch-based interface allows a user to intuitively draw a portrait as in traditional pencil sketching way. Then, the user’s drawing is automatically reshaped to an accurate natural human facial shape with the guidance of a statistical description model, and an arti...

We study nonlinear control systems in the plane, affine with respect to control. We introduce two sets of feedback equivariants forming a phase portrait PP and a parameterized phase portrait PPP of the system. The phase portrait PP consists of an equilibrium set E, a critical set C (parameterized, for PPP), an optimality index, a canonical foliation and a drift direction. We show that under wea...