Novel approach for region merging and image segmentation for human-computer interaction

For the purpose of human-computer interaction (HCI), a vision-based gesture segmentation approach is proposed. The technique essentially includes skin color detection and gesture segmentation. The skin color detection employs a skin-color artificial neural network (ANN). To merge and segment the region of interest, we propose a novel mountain algorithm. The details of the approach and experiment results are provided. The experimental segmentation accuracy is 96.25%. (C) 2003 Society of Photo-Optical Instrumentation Engineers.

Characters of Surface Deformation and Surface Wave in Thermal Capillary Convection

In the field of fluid mechanics, free surface phenomena is one of the most important physical processes. In the present research work, the surface deformation and surface wave caused by temperature difference of sidewalls in a rectangular cavity have been investigated. The horizontal cross-section of the container is 52 mmx42 mm, and there is a silicon oil layer of height 3.5 mm in the experimental cavity. Temperature difference between the two side walls of the cavity is increased gradually, and the flow on the liquid layer will develop from stable convection to un-stable convection. An optical diagnostic system consisting of a modified Michelson interferometer and image processor has been developed for study of the surface deformation and surface wave of thermal capillary convection. The Fourier transformation method is used to interferometer fringe analysis. The quantitative results of surface deformation and surface wave have been calculated from a serial of the interference fringe patterns.The characters of surface deformation and surface wave have been obtained. They are related with temperature gradient and surface tension. Surface deformation is fluctuant with time, which shows the character of surface wave. The cycle period of the wave is 4.8 s, and the amplitudes are from 0 to 0.55 mu m. The phase of the wave near the cool side of the cavity is opposite and correlative to that near the hot side. The present experiment proves that the surface wave of thermal capillary convection exists on liquid free surface, and it is wrapped in surface deformation.

Growth Mechanism And Joint Structure Of Zno Tetrapods

Regular zinc oxide (ZnO) tetrapods with a flat plane have been obtained on Si(1 0 0) substrate via the chemical vapour deposition approach. The x-ray diffraction result suggests that these tetrapods are all single crystals with a wurtzite structure that grow along the (0 0 0 1) direction and corresponding electron backscatter diffraction analysis reveals the crystal orientation of growth and exposed surface. Furthermore, we find some ZnO tetrapods with some legs off and the angles between every two legs are measured with the aid of scanning electron microscopy and image analysis, which benefit to reveal the structure of ZnO tetrapods joint. The structure model and growth mechanism of ZnO tetrapods are proposed. Besides, the stable model of the interface was obtained through the density-functional theory calculation and the energy needed to break the twin plane junction was calculated as 5.651 J m(-2).

Optical image processing using the photoinduced anisotropy of pyrrylfulgide

A synthesized photochromic compound-pyrrylfulgide-is prepared as a thin film doped in a polymethylmethacrylate (PMMA) matrix. Under irradiation by UV light, the film converts from the bleached state into a colored state that has a maximum absorption at 635 nm and is thermally stable at room temperature. When the colored state is irradiated by a linearly polarized 650 nm laser, the film returns to the bleached state; photoinduced anisotropy is produced during this process. Application of optical image processing methods using the photoinduced anisotropy of the pyrrylfulgide/PMMA film is described. Examples in non-Fourier optical image processing, such as contrast reversal and image subtraction and summation, as well as in Fourier optical image processing, such as low-pass filtering and edge enhancement, are presented. (c) 2006 Optical Society of America.

Fast Haar Transform Based Feature Extraction for Face Representation and Recognition

Subspace learning is the process of finding a proper feature subspace and then projecting high-dimensional data onto the learned low-dimensional subspace. The projection operation requires many floating-point multiplications and additions, which makes the projection process computationally expensive. To tackle this problem, this paper proposes two simple-but-effective fast subspace learning and image projection methods, fast Haar transform (FHT) based principal component analysis and FHT based spectral regression discriminant analysis. The advantages of these two methods result from employing both the FHT for subspace learning and the integral vector for feature extraction. Experimental results on three face databases demonstrated their effectiveness and efficiency.