Canon Kabushiki Kaisha

Canon Information Systems Research Australia Pty. Ltd.

Michael John Webb

Kia Silverbrook

Simon Robert Walmsley

Timothy Merrick Long

Christopher Amies

Yu-Ling Chen

Ian Richard Gibson

Alexander Will

David William Funk

Alexander Vincent Danilo

Kai Huang

Michael Anthony Martin

Matthew William Gallagher

Peter Leslie Bell

Yoong-Chert Foo

A method is disclosed for activating the filling of a graphical object. The method generates, for a current scanline, a plurality of edge records associated with an edge of the object from a previously generated edge record for a previous scanline. One of these edge records comprises fractional data which defines a minimum position of the edge within the current scanline or on a border thereto with respect to a direction along said current scanline. Another of these edge records comprises fractional data which defines a maximum position of the edge within the current scanline or on a border thereto with respect to a direction along the current scanline. One of these edge records comprises fractional data which defines an exit position of the edge from the current scanline. The previously generated edge record comprises fractional data defining an exit point of the edge from the previous scanline. After the edge record generation step, the method then activates, for the current scanline, the filling of the graphical object over a run of pixels or pixel from a minimum pixel position to a maximum pixel position. The minimum pixel position is derived from rounding down a value equal to the fractional data of the edge record defining the minimum position, and the maximum pixel position is derived from rounding up a value equal to the fractional data of the edge record defining the maximum position.

Activating a filling of a graphical object

Disclosed is method of detecting a predetermined mark ( ) forming part of an image. A digitized form ( ) of the image ( ) comprising a plurality of picture elements is provided and within a current region of the image a set of features is determined. The features typically comprise a dominant color feature ( ) within the current region; and at least one moment feature ( ) based on picture elements pertaining to the predetermined mark within the current region. Each determined feature is compared ( ) with a corresponding predetermined feature ( ) of the predetermined mark. Using the comparison, a confidence level for a detection of said predetermined mark within the current region calculated. Based on the confidence level, whether or not said predetermined mark is detected in the current region can then be determined. Adjunct to the above method, also disclosed are methods for providing multiple encoded representations ( ) of the image, detecting a center location ( ) of a predetermined pattern in the image, and determining ( ) a moment feature of a portion of the image.

Image pattern detection method and apparatus

The present invention relates to a method, apparatus and system for managing virtual memory, in which a co-processor ( ) is adapted to use virtual memory with a host processor ( ). A host memory ( ) is coupled to the host processor ( ) to implement the virtual memory. The co-processor ( ) includes a virtual-physical memory mapping device ( ) for interrogating a virtual memory table and for mapping one or more virtual memory addresses ( ) requested by the co-processor ( ) into corresponding physical addresses ( ) in the host memory ( ). The virtual memory table is stored in two or more non-contiguously addressable regions of the host memory ( ), and is preferably a page table. The memory mapping device ( ) further includes a multiple-entry translation lookaside buffer ( ) for caching virtual-to-physical address mappings ( ), where entries in the buffer ( ) are replaced on a least recently used replacement basis. The memory mapping device ( ) also includes devices ( ) for comparing, replacing, singly invalidating and multiply invalidating one or more entries of the translation lookaside buffer ( ). It also includes a hashing device ( ) for, upon an occurrence of a miss in the translation lookaside buffer ( ), hashing a virtual memory address ( ) using a hash function to produce an index into the virtual memory table.

Method apparatus and system for managing virtual memory with virtual-physical mapping

Method, apparatus and system for managing virtual memory with virtual-physical mapping

An apparatus for data normalization includes a FIFO buffer for receiving input data words, an input register for receiving a first data word from the FIFO buffer, and a combinatorial circuit for transforming the first data word in the input register and a subsequent data word from the FIFO buffer into a normalized output data word. The apparatus utilizes two or more independent instruction streams to increase the processing speed of the apparatus.

Transformation of a first dataword received from a FIFO into an input

A method and apparatus is disclosed for preprocessing fragments of two-dimensional graphic objects prior to display in a real-time rasterized format. The apparatus is formed as a pipeline having a translation and scaling section, a filter section, a pre-calculation section, and an interlace correction section. The preferred embodiment is specifically configured to process quadratic polynomial fragments (QPFs) of objects, and to calculate QPFs at high speed thereby permitting real-time rendering on a display. The preferred embodiment also forms part of a real-time object based graphics system.

Preprocessing pipeline for real-time object based graphics systems

An object based graphics processor includes an input device for receiving object outlines of an image intended for rasterized display, each of the outline comprising at least one object fragment, a sorter for sorting the object fragments into a rasterization sequence corresponding to a scan line in a raster format for rasterized display, and a storage having a first storage area and a second storage area connected to the sorter for storing the rasterization sequence in one of the storage areas. A reading device connected to the storage reads a previously stored rasterization sequence in real-time and calculates object edges in a respective scan line, and prioritizing device assigns pixel data values within each of the scan lines based upon priority levels assigned to the object edges. The pixel data values are output from the processor for rasterized display.

Object based graphics system for rasterizing images in real-time

Growing community of inventors

West Denistone, Australia

Michael John Webb