Abstract: A method for the automatic detection of colorimetry of CMYK image files includes the calculation of differentiation metrics based on colorant relationships, saturation, and luminance. Summary statistics, such as the means and standard deviations of the differentiation metrics are used to describe a set of known image colorimetry classes. At least one classifying algorithm is used to assign a known colorimetry class to an image of unknown colorimetry. Preferably at least one of the classifying algorithms is a Bayesian Quadratic Classifier algorithm. Mahanalobis distances are used to find the most appropriate colorimetry class to assign to an image. A color image processor operative to automatically detect image colorimetry comprises a training image analyzer, a colorimetry detector and a class associator.

Abstract: A first unit obtains a gradation conversion characteristic for equalizing a histogram of an input image. A second unit obtains an inverse characteristic of a gradation conversion characteristic for equalizing a histogram of an image to which a predetermined gradation conversion is applied. A third unit composites the gradation conversion characteristic obtained by the first unit and the inverse characteristic obtained by the second unit. A fourth unit performs fitting on the composited characteristic obtained by the third unit with a lower degree function. Gradation of the input image is converted based on the composited characteristic after the processing by the fourth unit.

Abstract: To enable a user to rapidly identify one or more sets of values for parameters of an operation, templates are generated dynamically from sets of values already used for these parameters in content available to the system. Each unique set of values may be extracted from the currently available content. Each of these sets of values may be sorted, for example, by recent modification date, for presentation to a user. The user may then select a set of values from among those displayed for use in the operation.

Abstract: In accordance with one embodiment of the invention, a method of compressing a color image includes the following. The wavelet transform of each of the respective color planes of the color image is computed. One of the respective wavelet transformed color plane frames is encoded. For the other two respective wavelet transformed color plane frames, a prediction coefficient from at least one of subbands of each color plane thereof is computed. In accordance with another embodiment of the invention, a method of decompressing a compressed color image includes the following. The compressed color image includes at least an encoded frame for one color plane of the color image and prediction coefficients for the other two color plane frames of the color image. The one color plane frame of the color image is reconstructed from the encoded frame. The other two color plane frames of the color image are at least partially reconstructed from the reconstructed one color plane frame and the prediction coefficients.

Abstract: The invention provides an image processing apparatus capable of continuing the image capture operation without correction error, even in the absence of the correcting condition corresponding to the configuration of a sensor unit connected to a control unit. For this purpose, there are provided memory means for storing the ID information for identifying the selected sensor, memory means for storing the correction table corresponding to the ID information, and search means for searching the correction table corresponding to the ID information, and, in the absence of the correcting condition for the configuration of the connected sensor unit, there is searched substitute correcting information and the image processing is executed with the later determined correcting information.

Abstract: A Simple Inter Color Lossless Image Coder (SICLIC) for the compression of colored images is provided. The color image is treated as several interlaced gray level images that correspond to respective distinct color planes. The compression scenario utilizes three main steps, such as selection of the predictor, context forming with bias cancellation and coding. SICLIC implements predictors, context forming and encoder techniques that exploit the intra- and inter-color plane correlations in an effective and relatively computationally inexpensive manner. The predictor is selected on the basis of the right selection of the contribution of each color plane between the intra- and inter-plane predictors obtained as a weight average of contribution from different color planes. SICLIC processes the image in two modes—regular mode and run mode. A special care is taken to ensure a proper treatment of joint runs, which occur simultaneously in all color planes.

Abstract: In a method and a device for transmission of S+P transform coded digitized images a mask is calculated by means of which a region of interest (ROI) can be transmitted lossless whereby the ROI can be transmitted and received lossless and still maintaining a good compression ratio for the image as a whole. This is possible since no or very few bits can be used for the remaining part of the image. The calculated mask can also be used for transmitting the coefficients needed for a lossless region of interest during any stage of the transmission.

Abstract: A fast and efficient method and system for computation of cubic-spline interpolation for data compression is described. In one aspect, the present invention is a method and system for defining a cubic-spline filter; correlating the filter with the signal to obtain a correlated signal; autocorrelating the filter to obtain autocorrelated filter coefficients; computing a transform of the correlated signal and the autocorrelated filter coefficients; dividing the transform of the correlated signal by the transform of the autocorrelated filter coefficients to obtain a transform of a compressed signal; and computing an inverse transform of the transform of the compressed signal to obtain the compressed signal. The signal, the filter, and the transforms may be one dimensional or two dimensional. Further, the transforms may be a fast Fourier transform (FFT) or a Winograd discrete Fourier transform (WDFT) with an overlap-save scheme.

Abstract: This invention has as its object to provide a viewpoint detection apparatus and method, which can assure high-speed processing, high precision, and high tracking performance with a simple arrangement while suppressing adverse influences on the human body, and a stereoscopic image display apparatus using the same. The viewpoint position detection apparatus of this invention has an image sensing unit (1) and a viewpoint detection unit (2). The image sensing unit has a visible image sensing section (11) and infrared image sensing section (12). A pupil position detection processing section (24) detects the pupil position from an infrared image, and a template generation section (23) generates templates for a visible image using the pupil position obtained from the infrared image. A pattern matching discrimination section (22) executes pattern matching of a visible image.

Abstract: A color correction apparatus and method in which a mask is derived from image data in a first pixel representation and is used to convert the image data into a perceptual color space representation which is a function of a background luminance parameter. The mask corresponds to a blurred monochrome version of the original image and includes a set of averaged greyscale values having a pixel-by-pixel correspondence with the original image. The values within the mask vary dependent on the location of the corresponding pixel within the image data. When converting the image data pixel-by-pixel into the perceptual color space representation, localized color correction is obtained by using varying mask values as the background luminance parameter for each pixel conversion.

Abstract: A method of registering images is provided which includes capturing a first original image of a scene under surveillance, capturing a second original image of the scene under surveillance, coarsely matching the first original image to the second original image to give approximate angle and offset parameters of the first original image to the second original image, and finely matching the first original image to the second original image based on the approximate angle and offset parameters of the coarsely matching step. The coarsely matching step involves applying a plurality of rotations to a reduced version of the first original image to form a rotated and reduced first original image and performing a correlation match between the rotated and reduced first original image and a reduced version of the second original image.

Abstract: This invention relates to a method and apparatus for implementing a trapping operation on a digital image during image processing. More specifically, the invention is directed to implementation of a trapping technique to prevent visual gaps or overlaps between colors on a poorly registered image that is produced by an imaging device, e.g. a color printer. The invention is most advantageously used in an imaging device that incorporates therein a split-level buffer.

Abstract: A decoder includes an indexing and thresholding stage that receives a compressed image matrix and produces therefrom a signal that is based on a comparison of at least one element in the compressed image matrix with a predetermined threshold value. A transform stage is coupled to receive the signal from an output of the indexing and thresholding stage, wherein the transform stage selectively decodes the compressed image matrix based on the signal. A row column index for each coefficient in a DCT matrix is used, together with a threshold value, to access each coefficient, and decide if the entry is greater than the threshold value. This information is used by an IDCT decoder to avoid unnecessary MAC operations for those entries with values below the threshold value. By not performing the IDCT on the DCT matrix values below the threshold value, the computational requirement of the decoder is significantly reduced, thereby reducing the computational speed requirement for the decoder.

Abstract: A position detection tool in a machine vision system finds the position of target objects in a digital image using the length and width of the target object as parameters. The input length and width dimensions are measured by the developer as the length and width of a simple hypothetical rectangle that surrounds the object. For most shapes, the developer can easily obtain these two measurements. The position detection tool can easily be adapted to discern particular image patterns from multiple component images.

Abstract: A multivalue image of the face input by a CCD camera 2 is stored in a multivalue-image memory 3. A multivalue-image characteristic extracting means 23 extracts a pixel of interest from the stored multivalue face image in accordance with distribution of relative brightness of the brightness of the pixel of interest and those of pixels adjacent to the pixel of interest. The extracted pixel of interest is stored in a binarized-image memory 5. The stored pixel of interest is used to extract an eye region. In accordance with the extracted eye region, an opening/closing determining means 7 determines opening/closing of the eyes.

Abstract: A method and apparatus is described that smoothes images within regions but not across boundaries. In one embodiment, a segmentation map is smoothed. Based on the color difference between pixels in an input frame and corresponding pixels in a background image, this segmentation map indicates the likelihood that each pixel in the input frame belongs to the foreground. The smoothed segmentation map may be processed further to reduce misclassification errors. Based on the segmentation map, the foreground portion of the image is superimposed over a new background image.

Abstract: An image processing apparatus for calculating a new luminance value of a central pixel to adjust the spatial frequency characteristics of an input image includes a plurality of subfilters, totalizer, and adder. The subfilters are arranged in parallel with each other for a plurality of pixel groups each made up of one or more pixels in a submatrix. The subfilters multiply the sums of the luminance values of pixels included in corresponding pixel groups by predetermined coefficients corresponding to desired spatial frequency adjustment filter characteristics, and output the products for each submatrix made up of M×M (M is an odd number of 3 or more) pixels centered on pixels constituting an input image for a two-dimensional input image made up of many pixels that are arrayed in a matrix and represent luminance values at positions. The totalizer totals outputs from the subfilters, and outputs the sum as the adjustment amount of the spatial frequency characteristics.

Abstract: Color image quantization using a hierarchical perceptual color model is disclosed. In one embodiment, a method constructs a clustering space of an image having a number of pixels, based on a color perception model. The clustering space includes a number of significant pixels, where each of the significant pixels does not have a parent pixel within the clustering space. The colors of the image are quantized based on these significant pixels. The remaining pixels have their colors mapped to one of the quantized colors.

Abstract: Automated layer extraction from 2D images making up a 3D scene, and automated image pixel assignment to layers, to provide for scene modeling, is disclosed. In one embodiment, a computer-implemented method determines a number of planes, or layers, and assigns pixels to the planes. The method can determine the number of planes by first determining the high-entropy pixels of the images, and then determining a 1-plane through a predetermined n-plane estimation, such as via a robust estimation, and a most likely x-plane estimation, where x is between 1 and n, such as via a Bayesian approach. Furthermore, the method can assign pixels via an iterative EM approach based on classifying criteria.

Abstract: A first points range of high brightness and a second points range of high brightness in a photographed image are selected. It is checked if an identical end point is shared by the three and four points range selected. A first straight line, connecting a center of gravity corresponding to the identical end point and a center of gravity corresponding to another end point of the first points range opposite to the identical end point, is calculated. A second straight line, connecting the center of gravity corresponding to the identical end point and a center of gravity corresponding to another end point of the second points range opposite to the identical end point, is calculated. It is checked if an angle, defined by the first and second straight lines, is within a predetermined limit.