CVGResearch

Home
3D Reconstruction
Texture Analysis
Shape Analysis
Segmentation
Recognition
Fractal Graphics
Members

Computer Vision and Graphics   中文

3D Reconstruction We live in a three-dimensional world (evolving with the elapsing time) and possess stereo vision thanks to the pair of our eyes (and our brain). Inspired by this natural endowment, a central problem of computer vision is to obtain 3D geometric shape information of the objects from planar images. This process is traditionally termed 3D reconstruction. 3D reconstruction of the objects and environments is useful in itself as it amounts to obtaining their 3D geometric measurements (termed 3D models in the graphics community), and is also a helpful means for object recognition since it eliminates the headache-causing variances produced by perspective projection in the imaging process and variable illumination.
Texture Analysis The unevenness patterns of the pixel attributes in a region give rise to the visual perception of image texture. Texture reflects the variations of the optical properties of object surfaces and illumination. Different materials usually produce distinctive surface texture. This makes image texture an important source of discriminant information. Texture plays an important role in various recognition applications such as product surface inspection, identification of objects in images, image based medical screening and diagnosis.
Shape Analysis Different objects typically posses distinctive shapes, which makes shape an important discriminant feature for object description and recognition. Some shapes are inherently planar such as the alphabets and words while many others are 3D in nature. Shape analysis is key to many applications such as character recognition, symbol classification and retrieval, object recognition and retrieval.
Segmentation Scenes, natural and man-made, are often made up of constituent parts, and some parts can further be divided into smaller components, and so on. This hierarchical organization provides a natural motivation for the study of segmentation, that is, an image of scenes and objects (as well as their 3D reconstructed models) can be beneficially segmented into meaningful parts. Automatic segmentation using the computer is useful in itself, and is also (debatably) widely considered as an important intermediate step for scene analysis and recognition.
Recognition Objects tend to fall into categories. Those of the same class usually share common features while those of different classes possess distinctive features, which makes recognition possible. A key (futuristic) goal of computer vision is to empower the machine with the superb recognition ability of the human vision system. Object recognition has found many successful applications such as character, fingerprint, face recognition, and also plays a key role in many fields such as video surveillance and remote sensing, product inspection, biological research and medical diagnosis.
Fractal Graphics Fractal geometry is a mathematical system characterized by features recurring at all levels of detail. While such properties are widely observable in nature (coastal lines and fern leaves for example), it is somehow surprising and yet completely pleasing that fractals are a good source for visual arts.
More...

Updated. July 2008