Abstract: A method and system for segmenting textures in an image includes computing multiresolution simultaneous autoregressive (MSAR) features in the image, preparing an uncertainty map of the MSAR features (the uncertainty map including high confidence pixels and low confidence pixels), computing wavelet features in the image, preparing a classifier based on the high confidence pixels and the wavelet features, and reclassifying the low confidence pixels based on the classifier to obtain the final segmentation.

Abstract: The system of the present invention increases the resolution of an image that may be formed from an image sensor without increasing the resolution of the sensor. An image beam is directed along a path through a color filter wheel and a single non-rotating transparent plate and impinges on a CCD (Charge Coupled Device). The transparent plate is positioned in a frame by flexures. A lever, controlled by a cam, exert a force on the transparent plate causing the transparent plate to tilt about the optical axis. The cam surface directs the lever to tilt the transparent plate in a plurality of discrete sampling positions. At each sampling position, the tilted transparent plate displaces the image beam in a different direction which allows each pixel of the CCD to sample a plurality of areas of the image. The color wheel is rotated to sequentially place each filter into the path of the image beam.