Abstract: A method of improving images is provided. A body of image data is collected and signal to noise (SNR) values thereof are determined. The collected data is converted into an electronic image representation X. Image X comprises a first array of pixel intensity values. Further, a low pass filtered image representation F comprising a second array of pixel intensity values is obtained. An improved electronic image representation P comprising a third array of pixel intensity values is generated by replacing each pixel intensity value of electronic image representation X by a linear combination of the replaced pixel intensity value from image X and the corresponding pixel intensity value from image F. An array of linear combination coefficients &agr;, (1−&agr;) determine the relative contributions of the replaced X pixel intensity value and the value of the corresponding pixel intensity from image F, respectively.

Abstract: An image compression method for video decoding based on a motion compensation such as MPEG-2 by using an image compression algorithm in which an image characteristic is differentiated on the basis of a difference between adjacent pels and finally classified by image types by using image characteristic information, and a suitable code word is assigned to each image type, thereby executing an image compression. There is also provided a CDC (classified differential coding) algorithm that defines a bundle by setting up a size of a pel block and searches the values between the adjacent and neighboring pels and its variation pattern, by which the computational complexity is reduced for the image compression coding, while satisfying the random accessibility of the memory.

Abstract: A real-time imaging and visualization method and system that allows multiple field-of-view imaging on multiple receiver channels is disclosed. The method and system implement a semi-bit reversed modified phase-encoding scheme to acquire identical data over all receiver channels, and to reconstruct independently on each channel an image thereby providing multiple FOV images. The method and system provide for real-time catheter tracking where separate receiver channels collect anatomical roadmap data, guidewire data, and catheter data. The present invention uses a loopless antenna to acquire projection images thereby allowing the entire antenna and structures within its diameter of sensitivity to appear as a bright signal and a long narrow connected region. The present invention allows for very narrow FOV imaging for guidewire and catheter channels as well as full FOV imaging for roadmap image reconstruction.

Abstract: A color image processing method for retrieving a color feature descriptor for describing color features of an image is provided. The color image processing method includes the steps of (a) obtaining color vectors of an input image, (b) classifying the color vectors to obtain dominant colors of the input image and the ratios thereof, and (c) representing the dominant colors and the ratios thereof as a color feature descriptor of the input image. The color image processing method is applied to an object-based image processing method, thereby allowing fast search and retrieval of multi-media contents.

Abstract: The invention relates to an associated information adding apparatus and method for adding information associated with image data as an electronic watermark to the image data, and an associated information detecting apparatus and method for detecting the associated information. Particularly, the apparatus includes a memory for storing a unit watermark, a unit watermark repeating section for repeatedly reading the unit watermark from the memory by using a surplus obtained by dividing a pixel position coordinate value of a pixel in a vertical direction and a horizontal direction of an image by a size of a vertical and horizontal repetitive unit of the unit watermark, and an adding section for adding the unit watermark read out from the unit watermark repeating section to information of the image so that the unit watermark is repeated vertically and horizontally on the image. By this, since it is sufficient if the memory stores only the unit watermark, there is an effect that the memory to be used may be small.

Abstract: An object recognition system having at least two image sensors and a controller that is adapted for measuring the distance from the system to a physical object with respect to respective windows of a n image captured by the sensors. The controller is further programmed to form clusters by uniting adjacent windows that have similar measure distances. The controller is programmed to judge whether each of the clusters is valid or invalid based on the attributes of the cluster and to recognize an object based on the clusters judged to be valid.

Abstract: In a 3-D shape data processing device for producing 3-D shape data from color image data and range image data, a virtual plane is defined at the rear of a range image, and a color image is projected onto the virtual plane. A human figure region rectangle is defined as a rectangle which surrounds a human figure region on the virtual plane, and the range image and the virtual plane are sliced along cutting planes. A line connects an outermost point of measurement and a point at the end of the human figure region rectangle which lie on each of the cutting planes, and a point at the end of the human figure region on the line is defined as a reference point. A region lying between the reference point and the outermost point of measurement is defined as a no-data region, and an additional point is produced in the no-data region. Thus, the device can easily complement the range image data, thereby to easily produce the 3-D shape data based on the range image data.

Abstract: An improved ROI segmentation image processing system substantially masks non-ROI image data from a digital image to produce a ROI segmented image for subsequent digital processing. The ROI segmentation image processing system is a computer-based system having a collimation subsystem configured to detect and mask out collimated regions within the image. Furthermore, a direct exposure (DE) subsystem is configured to detect and remove DE regions from the image. Holes generated in the image are filled-in to provide a resulting image with only ROI.

Abstract: In predictive encoders that support both intra-frame and inter-frame coding, the coding of intermediate dissolve frames (i.e., those falling between the first and last dissolve frames) is restricted, such that either (1) no intermediate dissolve frame is coded as an anchor frame (e.g., MPEG I or P frame) or (2) only a specific number of frames at specific locations within the dissolve are encoded as anchor frames. In certain MPEG implementations, all intermediate dissolve frames are coded as B frames, while the first and last frames are coded as anchor frames (e.g., I or P frames). In other implementations, particular intermediate dissolve frames may be coded as anchor frames with the other intermediate frames coded as B frames. The present invention can provide improved coding results in terms of both bit rate and video quality by avoiding the accumulation of predication errors that can otherwise occur when fixed GOP patterns are applied during dissolves.

Abstract: A method and apparatus is provided for producing a smooth closed curve from a binary mask such as the type produced when segmenting various parts of a human body. Points defining the segmentation boundary are transformed into a set of polar coordinates. The set of coordinates is thresholded and averaged, and then smoothed using a window smoothing technique. The resulting boundary points are curve fit to produce the smooth closed curve.

Abstract: A method for detecting a skew of a document image corrects the skew of a document image input from an image scanner, and achieves increased accuracy compared with prior art document image skew detection methods. After segmenting the input document image into regions each having a predetermined width, lines containing black pixels are detected from each of these regions. Then, from a region where the detected lines containing black pixels follow one another in a consecutive manner, a partial image is extracted, the skew angle of the partial image is detected, and the skew angle of the document image is determined based on the thus detected skew angle of the partial image.

Abstract: A method is disclosed for decoding multiple-coded symbols from a coded input symbol stream in a single clock cycle. The method constructs an original Huffman look-up table by extending the associated Huffman tree to decode multiple symbols in one clock cycle in a first embodiment and decodes multiple DCT coefficient symbols in an alternate embodiment. An advantage of the method is that the depth of the new Huffman tree is adjustable thereby making the method easily adaptable to various hardware architectures. A further advantage of the present invention is that the decoding process speed is significantly increased while the size of the look-up table is nominally increased.

Abstract: An image processing apparatus and method perform an efficient wavelet transform to provide sub-bands having a unit size for being encoded in an encoding device in a post-stage. In accordance with one embodiment of the present invention, the image processing apparatus includes a transform unit for performing a two-dimensional discrete wavelet transform on an input image to generate a plurality of frequency components, and an entropy encoding unit for performing entropy encoding on each of the frequency components in M×N-sized units. In a first encoding mode, the transform unit performs the two-dimensional discrete wavelet transform on the image either a predetermined number of times or for a number of times which allows a lowest frequency component (LL) to have a size of M×N, and in a second encoding mode, the transform unit performs the two-dimensional discrete wavelet transform on the image the predetermined number of times.

Abstract: A sensing device for sensing region identity data and generating movement data when the sensing device is moved relative to a region of a surface, the region identity data being indicative of an identity of the region, the movement data being indicative of the movement of the sensing device relative to the region, the surface having disposed upon it coded data indicative of at least one region associated with the surface, the sensing device including: region identity sensing means configured to sense the region identity data using at least some of the coded data; motion sensing means configured to generate the movement data; and communications means configured to communicate the region identity data and the movement data to a computer system.

Abstract: A color sensor for generating color information defining colors of an image includes an input section, a color processing section, a color comparison section, a color boundary processing section and a memory processing section. The input section includes an array of transducer pairs, each pair defining one of a plurality of pixels. Each transducer pair generates two peak outputs, one for the selected color of each transducer of the pair. A plurality of pixel processors in the color processing section each receives the outputs from one of the transducer pairs. The color processing section generates a color feature vector representative of the brightness of the light incident on the pixels and a color value corresponding to the ratio of outputs from the transducers comprising the transducer pair associated with the pixels. The color boundary processing section generates a plurality of color boundary feature vectors, each representing the difference between the color value for a pixel and its neighboring pixels.

Abstract: Methods and apparatus are disclosed for tracking an object of interest in a video processing system, using clustering techniques. An area is partitioned into approximate regions, referred to as clusters, each associated with an object of interest. Each cluster has associated average pan, tilt and zoom values. Audio or video information, or both, are used to identify the cluster associated with a speaker (or another object of interest). Once the cluster of interest is identified, the camera is focused on the cluster, using the recorded pan, tilt and zoom values, if available. An event accumulator initially accumulates audio (and optionally video) events for a specified time, to allow several speakers to speak. The accumulated audio events are then used by a cluster generator to generate clusters associated with the various objects of interest. After initialization of the clusters, the illustrative event accumulator gathers events at periodic intervals.

Abstract: A user authorization system including printing a human cognizable digital image of a user onto an article. The article being a bracelet, a pass key, a placard, a legal citation, a vehicle rental agreement and a tag. The human cognizable image optionally being stored in a computer memory in combination with personal user information, the memory to be accessed to verify user authorization.

Abstract: This invention relates to an image processing method for precisely and automatically recognizing a specific image extraction region to be divided from an input image, and extracting the specific image extraction region. Thresholding is done for intensity differences of edge data obtained from the input data to extract difference edge data. A main extraction region is estimated from the outermost contour line extracted based on the extraction result of the difference edge data. Thresholding or the like is done in units of pixels of the input image to extract an initial region. Extraction region determination processing is done for extracting an accurate target region by combining the main extraction region and initial region.

Abstract: A method and apparatus are provided for performing a contrast-based dynamic range management (C-DRM) algorithm. The apparatus comprises an C-DRM processor that performs the C-DRM algorithm of the invention in order to compress an image input to the C-DRM processor down to a desired gray scale range for observation on a display. The C-DRM processor decouples adjustment of image mean values (low frequency) and image contrast values (high frequency), and manages mean and contrast separately. The use of separate mean and contrast modification functions improve on other known compression techniques by providing a more deterministic behavior and reduced complexity, allowing, for example, independent management of negative and positive contrasts. The C-DRM processor can also automatically adapt to the dynamic range of an input image so that the input image thereby applying the minimal compression needed to display the image.

Abstract: Disclosed herein are new forms of computer inputs particularly using TV Cameras, and providing affordable methods and apparatus for data communication with respect to people and computers using optically inputted information from specialized datum's on objects and/or natural features of objects. Particular embodiments capable of fast and reliable acquisition of features and tracking of motion are disclosed, together with numerous applications in various fields of endeavor.