Abstract: In some embodiments, the invention involves utilizing a tree merge sort in a platform to minimize cache reads/writes when sorting large amounts of data. An embodiment uses blocks of pre-sorted data residing in “leaf nodes” residing in memory storage. A pre-sorted block of data from each leaf node is read from memory and stored in faster cache memory. A tree merge sort is performed on the nodes that are cache resident until a block of data migrates to a root node. Sorted blocks reaching the root node are written to memory storage in an output list until all pre-sorted data blocks have been moved to cache and merged upward to the root. The completed output list in memory storage is a list of the fully sorted data. Other embodiments are described and claimed.

Abstract: In some embodiments, the invention involves utilizing a tree merge sort in a platform to minimize cache reads/writes when sorting large amounts of data. An embodiment uses blocks of pre-sorted data residing in “leaf nodes” residing in memory storage. A pre-sorted block of data from each leaf node is read from memory and stored in faster cache memory. A tree merge sort is performed on the nodes that are cache resident until a block of data migrates to a root node. Sorted blocks reaching the root node are written to memory storage in an output list until all pre-sorted data blocks have been moved to cache and merged upward to the root. The completed output list in memory storage is a list of the fully sorted data. Other embodiments are described and claimed.

Abstract: Method, apparatus, and program means for performing bitstream buffer manipulation with a SIMD merge instruction. The method of one embodiment comprises determining whether any unprocessed data bits for a partial variable length symbol exist in a first data block is made. A shift merge operation is performed to merge the unprocessed data bits from the first data block with a second data block. A merged data block is formed. A merged variable length symbol comprised of the unprocessed data bits and a plurality of data bits from the second data block is extracted from the merged data block.

Abstract: A method is disclosed for providing a means for identifying recovered component parts of a destroyed assembly quickly and relatively easily using digital or electronic scanning techniques and comparison to virtual components that are presumed to have constituted the original assembly. The method also provides a means for digitally rigging the component parts in three-dimensional virtual space, thereby minimizing and, in some situations, possibly eliminating any need to physical rig the component parts.

Abstract: A method for reducing row noise from a complementary metal oxide semiconductor (CMOS) image sensor is disclosed. The method includes determining a set of row sums for a set of pixel rows in the image sensor and a set of corresponding contributing pixel counts. Then, determining a set of row offset corrections. Finally, adjusting the set of pixel rows by the set of row offset corrections.

Abstract: A digital image processing method and apparatus corrects geometrical distortions in digital images. The method includes the calibration of the camera by choosing a test pattern and manually adjusting the distortion correction factor of the camera until the image appears to be undistorted. A real image is then captured by the camera grid. The camera grid is then distorted by the same distortion factor such that the image is corrected, but the image contour is deformed. Based on the distortion correction factor, a respective location in the camera grid is determined for each pixel in a display window. An intensity value to each pixel in the display window is assigned based on one or more pixels in the camera grid indicated by the location. The points for mapping camera values to the display window need to be determined only once for a given image size. All subsequent distorted images having the same size are corrected using interpolation and pre-compiled points.

Abstract: Missing color values for pixels in a color filter array created by a digital camera and having a Bayer pattern are generated by determining values for all missing green color values for pixels in the color filter array by interpolation of known green color values adjacent along diagonal lines and determining values for all missing red and blue color values for the pixels from the sum of an interpolation term and a luminance correction term based on differences between green color values of adjacent pixels. The missing green color values are determined by computing temporary values for green which lie at the corners of pixels having known green color values using cubic B-spline filters oriented along diagonally adjacent green color pixels, determining final values for green at the centers of pixels having known red and blue values by using cubic B-spline filters oriented along diagonally adjacent red and blue color pixels, and by sampling the temporary green values.

Abstract: A method and computer system for separating an image into a sequence of wavelet bands, which are equivalent in value to the conventional sequence of wavelet bands, without rearranging the pixel data elements representing the image. The sequence of bands represent different values in reproducing the image. The method of processing the image includes the first step of storing the pixel data elements as first and second packed data sequences in a memory with the pixel data elements stored in an order. A set of intermediate results are generated by performing arithmetic operations between the corresponding pixel data elements of the first and second packed data sequences. The set of intermediate results are then used to generate the sequence of bands by performing arithmetic operations between the intermediate results.