Abstract: A method and apparatus for reducing three-dimensional shape data, includes calculating estimation values for portions to be deformed by converging two or more vertices of a polygon model, and reducing the number of data for the polygon model by converging two or more vertices of the polygon model when the estimation values are equal to or below the predetermined permissible value. Estimation values for surfaces to be deformed by shrinking edges or surfaces are calculated based on distances between the respective surfaces and all the original vertices involved in the surface deformation. Before each data reduction, the portion having been involved in all the previous data reductions is defined as a reduction prohibition area, and a succeeding data reduction is applied to a portion other than the reduction prohibition area.

Abstract: A scanning system and method for locating a point within a region. The method may: 1) determine or locate a region of interest in the region; 2) determine one or more characteristics of the region of interest within the region, wherein the region of interest includes the point of interest; 3) determine a continuous trajectory based on the one or more characteristics of the region of interest; 4) measure the region of interest at a plurality of points along the continuous trajectory to generate a sample data set; 5) perform a surface fit of the sample data set using the approximate model to generate a parameterized surface; and 6) calculate a location of the point of interest based on the parameterized surface. The method may include measuring the region at and/or near the calculated location to confirm the solution, and may also include generating output comprising the results.

Abstract: A method of determining trapping, i.e., spreading or choking, in color boundary areas in a printed image, includes characterizing with respect to register behavior one of a printing machine and a printing machine type, respectively, performing a printing; determining the printing-machine specific register behavior with knowledge of influencing factors relating to the color to be printed and the printing material to be printed on for the job being printed; calculating minimum required spreadings and chokings, respectively, while taking a safety margin into account; and taking into account minimum geometric overlaps in producing an original.

Abstract: A de-convolution process is applied to an MR, CT or other image (25) of a scanned-object (23) to derive the point-spread function (22?) at an object-edge and to pin-point from the mid-point of its full-width-half-maximum FWHM, the location (30) of the true image-edge. With the object-image (25?) overlying the PSF function (22?) in the de-convolution space, sub-pixels which follow location (30) are transferred to before it to re-construct the image-edge (25?) for sharper conformity to the object-edge (23). Sharp definition of image-contour (37) facilitates accurate determination of area and volume of image profiles (35) and their segmentation. The accurate image-edge definition enables viable correction of geometrical distortion in stand-alone MR diagnosis and treatment planning.

Abstract: A system and method for automatically determining a seed vigor index for a lot of seeds by analysis of a scanned image of a plurality of seedlings grown from lot of seeds, including automatically separating and analyzing overlapped seedlings. According to one aspect of the current invention, seedling analysis software is used to analyze an image of seedlings. The seedling analysis software preferably analyzes both hypocotyl and radicle lengths and thus determines the separation point between the two for each seedling. The seedling analysis software also preferably separates overlapped seedlings, preferably using a simulated annealing technique. According to another aspect of the present invention, a low-cost scanner placed in an inverted configuration in a scanner enclosure is used to generate high-quality, reproducible images of seedlings. According to yet another aspect of the present invention, a method of using ordinary germination boxes, i.e.

Abstract: A method of digital imaging includes receiving image data and fitting a curve to boundaries within the image data. The curve is fit to the boundaries within the image data by extracting a region of interest from the image data and computing a signed distance transform in a narrow band within the region of interest. Finite difference equations including various variables are solved to determine a rate at which the distance transform changes. The distance transform is then diffused at that rate. The technique is based on region-based diffusion propagation, pixel classification, and mathematical morphology. The method is implemented to run in the narrow band of the region of interest specified by the user and the computations are implemented using a fast marching method in the narrow band. While idealized for distinguishing segments of white matter, gray matter, and cerebral spinal fluid in the brain, the algorithm can applied to find contours in any digital image.

Abstract: A color image processing provides a thin-line enhancement module for a color image for finding and keeping thin lines in the color image. A boundary enhancement module is provided for finding and keeping the boundary in the color image. A de-background module is provided for removing noise pixels from the white background. The color image is processed to avoid missing and/or twisting the thin lines, boundary, background, and texts in the color image after the scanning procedure.

Abstract: Assuming that there are three continuous frames, i.e, cross sectional images of an organism, a dummy region of interest (ROI) is specified manually in the first frame, a temporary ROI is set in the second frame at the same position as that of the dummy ROI in the first frame. Whether a specific region in the second frame is inside or outside of a true ROI is judged based on the initial judgment criterion and, values of pixels in the specific region. Whether a specific region in the third frame is inside or outside of the true ROI is judged based on values of pixels of regions that have been judged to be inside the region of interest in the second frame.

Abstract: A method and apparatus for locating the boundary of an object. An electronic image of the object is formed, having a plurality of image pixels. Groups of the image pixels are identified that represent edge segments of the object. Patches are formed around the image pixel groups, where each patch is dimensioned and positioned to entirely contain one of the image pixel groups. A patch merge process is preformed that merges any two of the patches together that overlap each other by a predetermined amount, to form a merged patch that is dimensioned and positioned to entirely contain the two merged patches. The merge process continues for any overlapping patches and merged patches until none of the patches and the merged patches overlap each other by the predetermined amount. All the edge segments contained within one of the merged patches are associated as representing the boundary of the object.

Abstract: In a display device, three light-emitting elements, which respectively emit light of the three primary colors of R, G, and B, are aligned in a fixed order in a first direction to form one pixel. A plurality of such pixels are aligned in a the direction to form one line. A plurality of such lines are aligned in a second direction, which is orthogonal to the first direction, to form a display screen. With this display device, a three-times magnified pattern, with which a target pixel in a raster image to be displayed currently is magnified by three in the first direction, is determined dynamically in accordance with a rectangular reference pattern of 3×3 pixels consisting of the target pixel and pixels surrounding the target pixel. Display is performed upon allocating this three-times magnified pattern to the three light-emitting elements that comprise one pixel. Character interval adjustment and color display of sub-pixel precision precision are enabled.

Abstract: A foreground erosion method is used to meet thin (but unbroken) text requirements using linear YCC segmentation. The method uses a fixed value subtracted from a gray selector signal, thereby thinning/eroding the foreground. In cases where the pixel would be converted from foreground to background, this is only done if a neighborhood test verifies that the thinning won't result in broken lines. The foreground erosion method attempts to match a couple of templates wherein if a match is found, then the adjustment is performed.

Abstract: A system according to the invention identifies image data points defining a curve. The method comprises the steps of determining a start point and an end point for the curve, establishing a search space that includes at least the start point, the end point, and other image data elements comprising the curve, and searching the search space using a dynamic programming algorithm to locate image data elements corresponding to the curve. Another embodiment consistent with the present invention identifies image data points defining a curve. The method comprises the steps of determining a start point and an end point for the curve, generating a model of the curve, establishing a search space that includes at least the start point, the end point, and other image data elements comprising the curve, and searching the search space using a dynamic programming algorithm and the model for the curve to locate image data elements corresponding to the curve.

Abstract: A method of and system for compensating artwork for coverage gain that occurs during reproducing of the artwork on a reproduction system. The artwork includes one or more graphic elements. The method includes characterizing the reproduction system, selecting one or more graphic elements of the artwork, and automatically modifying the artwork by causing a spread or choke to the selected graphic elements of the artwork by an amount determined according to the results of the characterization step. Reproducing the modified artwork on the reproduction system reduces the coverage gain effects.

Abstract: This at least comprises: a first step of capturing an image of a fine pattern; a second step of extracting a contour of the fine pattern from the image; a third step of capturing a standard figure of the fine pattern; a fourth step of superimposing the standard figure on the contour by enlarging or reducing the standard figure while maintaining an aspect ratio thereof; a fifth step of extracting an intersection of the contour and the standard figure; a sixth step of extracting a differential region surrounded with the contour, the standard figure and the intersection; a seventh step of extracting a correction pattern region from the differential region; and an eighth step of measuring the correction pattern region.

Abstract: A method for mapping a boundary for a multi-pel thickness line into a bitmap image which describes the pel boundary with respect to an orthogonal pel array. The line has thickness T centered around a spine between a start and stop point. The boundaries for the rounded ends of the line are determined by centering a pre-stored T-diameter pel dot boundary with respect to the start and stop points. The rounded end boundaries are tangentially connected by a first pair of sides of a rectangular perimeter whose remaining two sides diametrically intersect the dot boundaries. The start point, the thickness, and line slope are utilized for estimating and mapping four corner points of the rectangular perimeter with respect to the orthogonal pel array. The vertical orientation of the mapped corner points designate up to five sections of the line boundary including two end sections, one of which lies above an uppermost corner point, and the other below a lowermost corner point.

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: In a system for segmenting a pixel based image, pixels containing image boundaries are identified. The image boundaries are then fattened by repeatedly adding fattening rows of pixels to the pixels containing boundaries to separate the remaining pixels into separate segments. The separate segments are then grown back to their original size before the boundaries were fattened. This operation has the effect of linking the boundaries together to separate the image into segments and to extend incomplete boundaries into complete boundaries around segments in the image.

Abstract: A method for locating symbols arranged in one or more rows in an image includes smearing the image, and fitting line segments through edge points of features in the smeared image. A group is found of the line segments that are in mutual proximity and are mutually substantially parallel. A region of the image that contains the group of the line segments is identified as a possible location of the symbols.

Abstract: A sizing processing system according to the present invention generates an offset figure based on an offset point set obtained by offsetting the respective sides of a source figure by a distance equal to a prescribed sizing amount. When an inside-out side is detected on the offset figure, two sides of the source figure that intersect at a vertex thereof associated with the detected inside-out side are translated by a distance equal to the prescribed sizing amount, and the respective end points of the thus translated sides corresponding to that vertex are taken as offset points. Then, the offset points are added to the offset point set to generate an offset figure that does not entail the generation of an inside-out side. This can also address the problem of an inside-out side that occurs when an edge cut is inserted in the offset figure.

Abstract: Disclosed is an image processing apparatus 10D for processing image data that composes a dynamic image, wherein pixels are thinned for each frame with respect to the pixels of the respective frames that compose a dynamic image, in such a manner that they become the chessboard-like lattice format in both directions of the spatial direction and the temporal direction, so that the quantity of information can be reduced, maintaining the resolutions of horizontal, vertical and oblique directions of the dynamic image.

Abstract: A method is disclosed for reducing halo print defects occurring in printed/copied color images. The method includes detecting a boundary between a first image object and a second image object within a color separation of the color document, and modifying the video values of a plurality of pixels within the color separation so that the video values slope toward the boundary, the plurality of pixels being located within a transition zone adjacent the boundary. In the case where toner black is used, the video values of a plurality of pixels within a transition zone of a toner black color separation are modified so that the video values ramp or slope down toward the boundary, and the video values of a plurality of pixels within transition zones of a cyan color separation, a magenta color separation, and a yellow color separation are modified so that the video values ramp or slope up toward the boundary. In effect, the process increasingly replaces toner black with process black (i.e.

Abstract: Regular-size white cells are expanded in advance to adjust a boundary between black cells and the white cells before a printing operation is performed. Shrinkage of black cells occurs in the region where the expanded white cells overhang over the neighboring black cells. No shrinkage of the black cells occurs in the boundary between two black cells which are located next to each other. A region where one white cell overhangs over another white cell remains white. This is simply realized by outputting 0 for the region where the white dot (0) and the black dot (1) are overlapped and by outputting 0 for the region where two white dots (0) are overlapped. By shrinking the black cells beforehand in this manner, the overhang of the black cells over the while cells is reduced or completely eliminated when they grow fat through the data reading performed by facsimile or copying machines.

Abstract: A system is provided for repairing a binary image image containing discontinuous segments of a character. The binary image comprises a two-dimensional array of pixels, and the system comprises a device for storing the binary image, and a processor for performing various steps, including (1) creating a morphological filter, (2) mapping the morphological filter onto a selected region of the binary image, wherein each element of the morphological filter corresponds to a pixel of the binary image, (3) for each of the elements of the morphological filter of the first filter type, determining whether the corresponding pixel of the binary image is set and any of the pixels of the binary image corresponding to the elements of the morphological filter of the second filter type are set, and (4) setting the pixel of the binary image corresponding to the center element of the morphological filter, responsive to the previous step.

Abstract: A method determines a surface of an object in a sequence of images. The method begins by estimating a boundary of the object in each image of the sequence using motion information of adjacent images of the sequence. Then, portions of each image of the sequence are ordered to produce an ordered sequence of images. The ordered portions are exterior to the estimated object boundary. Edges in each ordered image are filtered using the motion information, and each ordered image of the sequence is searched to locate the filtered edges to form a new boundary outside the estimated boundary. The filtering and searching are repeated, while projecting the new object boundaries over the sequence of images, until the new object boundaries converges to a surface of the object.

Abstract: Pattern inspection equipment has at least a measured data generation unit for generating measured data from patterns that have been delineated on a sample according to design data, a reference data generation unit for generating reference data used to inspect the patterns from gradational data expressed in multiple gradation levels, and a fault decision circuit for comparing the measured data with the reference data. The reference data generation unit has a multi-valued pattern development circuit for developing the design data into the gradational data and a fine adjustment circuit for finely shifting the positions or adjusting the curvatures of pattern edges in the pattern constructed with the gradational data. The fine adjustment of the pattern edges is necessary to cope with slightly displaced edges and rounded corners of the actual patterns on the sample.

Abstract: An image defect detection apparatus comprises a means to prepare two replicates of inspection image from a single inspection image, the first image processing means to process an image applying the expansion filter and the contraction filter in such order for the one of replicated inspection images, the second processing means to process an image using the contraction filter and the expansion filter in such order for the other of replicated digital image information, and an image information outputting means to output image information composed of the differential value respectively outputted from the first image processing means and the second image processing means.

Abstract: A region-based binarization system applies adaptive thresholding and image rendering to a gray scale image to generate first and second binary images. The gray scale image can also be subsampled to acquire a low resolution image and locations of photographic images are detected in the low resolution image. Further, photographic images of the detected photographic images which have a rectangular shape are identified and a classification map which distinguishes pixels in the rectangular shaped photographic images from remaining pixels is generated. A final binary image can then be formed from the first and second binary images based on the classification map. The binarization system of the present invention is effective when the gray scale image is captured from a document which contains at least both photographic and text portions.

Abstract: An adaptive multiscale method approximates shapes with continuous or uniformly and densely sampled contours, with the purpose of sparsely and nonuniformly discretizing the boundaries of shapes at any prescribed resolution, while at the same time retaining the salient shape features at that resolution. In another aspect, a fundamental geometric filtering scheme using the Constrained Delaunay Triangulation (CDT) of polygonized shapes creates an efficient parsing of shapes into components that have semantic significance dependent only on the shapes' structure and not on their representations per se. A shape skeletonization process generalizes to sparsely discretized shapes, with the additional benefit of prunability to filter out irrelevant and morphologically insignificant features.

Abstract: A method and apparatus is provided for intuitively, graphically parameterizing a region of an input image to be processed by a machine-vision vision system, the region being defined by a deformable window, where the window is deformed by a user using a pointing device. The window pictorially indicates the defined region to the user. The region identified and parameterized is transformed into a destination region. A preferred embodiment is a parameterization of a polar region and the subsequent transformation of the polar region into an OCR rectangular window that is then available for further processing, such as by an OCR software application.

Abstract: Noise-corrupted boundary information in tomographic images is restored using a data structure, called a “boundary envelope”. Both the restored boundary information and a measure of the precision of the restoration are described by the process. This data structure is used to describe the restored information in both qualitative and quantitative terms. The results of the boundary restoration process are described qualitatively by graphically displaying the boundary envelope together with the noisy CT image in such a way that allows a human observer to (a) see more details of the boundary than are visible in the CT image alone, and (b) to visually apprehend the precision with which the boundary has been restored. A boundary envelope describes a region in the image within which the boundary of a given noisy object is guaranteed to lie. The boundary envelope describes a set of limits on the object boundary, and limits on those properties of a noisy object that can be computed from boundary information.

Abstract: The widths of characters, that have had (or that are having) resolution enhancement processing applied, are adjusted so that the widths of the characters are maintained. In this way, formatting of any file including such characters is maintained. Specifically, the advance width of each character may be adjusted. A non-uniformity of gaps between characters may be minimized by adjusting the left and/or right side bearing of each character. Finally, a non-uniformity in the weight of character lines may be minimized by adjusting the black body width of each character.

Abstract: There are provided a print image-forming method and device. Print image data of a dot matrix is formed in which print portions are represented by positive dots and blank portions are represented by negative dots. Basic image data formed in a manner such that when the basic image data is developed into a dot matrix, a group of image pixels formed by one of a set of positive dots and a set of negative dots is capable of representing a basic image, is read from a memory device. Developed image data item representative of the basic image is formed by developing the basic image data read from the memory device into a dot matrix which is smaller in size than the dot matrix of the print image data in at least one predetermined direction of a vertical direction and a horizontal direction.

Abstract: A method of determining peaks in a discrete function. The method comprising the steps of: applying a closing function to the discrete function to generate a closed discrete function; defining peaks within the closed discrete function; sorting the defined peaks according to function value; and applying a threshold value to each sorted defined peak in individual succession, wherein sorted defined peaks having a peak height value above the threshold value are retained within the closed discrete function.

Abstract: A method and device for generating, displaying and manipulating three-dimensional images for medical applications is provided. The method creates a three-dimensional images from MRI or other similar medical imaging equipment. The medical imaging system allows a user to view the three-dimensional model at arbitrary angles, vary the light or color of different elements, and to remove confusing elements or to select particular organs for close viewing. Selection or removal of organs is accomplished using fuzzy connectivity methods to select the organ based on morphological parameters.

Abstract: A method and system for detecting and displaying clustered microcalcifications in a digital mammogram, wherein a single digital mammogram is first automatically cropped to a breast area sub-image which is then processed by means of an optimized Difference of Gaussians filter to enhance the appearance of potential microcalcifications in the sub-image. The potential microcalcifications are thresholded, clusters are detected, features are computed for the detected clusters, and the clusters are classified as either suspicious or not suspicious by means of a neural network. Thresholding is preferably by sloping local thresholding, but may also be performed by global and dual-local thresholding. The locations in the original digital mammogram of the suspicious detected clustered microcalcifications are indicated. Parameters for use in the detection and thresholding portions of the system are computer-optimized by means of a genetic algorithm.

Abstract: Dilation and erosion operations are performed on imaged objects that are represented using a number of object pixels; the object pixels are a subset of a larger number of image pixels. A ring-shaped structuring element is specified by a radius and an origin. In the ring dilation operation, the boundary of the structuring element includes two concentric circles, one having a radius that is one pixel greater than the other so that the boundary is two-pixels wide. The origin of a copy of the structuring element is then overlaid onto each object pixel such that the boundaries of the copies intersect to form a dilated image feature. The image feature includes a feature boundary defined by the outermost portions of the boundaries of the overlapping copies of the structuring element. This feature boundary is identified and described using conventional chain-coding techniques. The dilation is then completed by filling an area defined within the feature boundary.

Abstract: A method and apparatus for processing an image by adding a border to the image, where said border has a width that is proportional to the extent of a filter used during image processing. Specifically, the processing reduces an image to produce an image pyramid and expands an image pyramid to produce an image. At each pass through the reduction or expansion process, the border is added to the image being processed, where the border has a width that is at least as large as an extent of a filter used in the reduction or expansion process.

Abstract: An operation of an iris filter is carried out on an original image signal representing an image, and the degree of centralization of gradients of the original image signal with respect to a picture element is thereby calculated, each of picture elements constituting the image being taken as the picture element. An image portion, which is associated with a high degree of centralization, in the image is detected in accordance with the calculated degree of centralization. Image emphasis processing is then selectively carried out on the detected image portion. Alternatively, a morphology operation is carried out on an original image signal Dorg by using a multiply structure element Bi and a scale factor .lambda., and a morphology signal Dmor is thereby obtained.

Abstract: Analog image data a SEM are converted into digital data, and are processed by a spatial filtering processing, histogram processing, threshold value setting, three-valued image data processing, noise reduction and the like. Area of a pattern in the three-valued image data is calculated by a labelling and calculation processing, and a pattern is sequentially detected by comparing the area of the pattern with a reference area value. The comparison and detection of the same or similar patterns repeated in the SEM image are performed by using the area of the pattern, and are not performed by a shape of the pattern, thereby resulting a precise detection at high speed by using a microprocessor. Since it is possible to perform a pattern recognition from the area value even though the pattern does not have a characteristic, it is possible to precisely detect and recognize a pattern image in high speed.

Abstract: A method and system for detecting and displaying clustered microcalcifications in a digital mammogram, wherein a single digital mammogram is first automatically cropped to a breast area sub-image which is then processed by means of an optimized Difference of Gaussians filter to enhance the appearance of potential microcalcifications in the sub-image. The potential microcalcifications are thresholded, clusters are detected, features are computed for the detected clusters, and the clusters are classified as either suspicious or not suspicious by means of a neural network. Thresholding is preferably by sloping local thresholding, but may also be performed by global and dual-local thresholding. The locations in the original digital mammogram of the suspicious detected clustered microcalcifications are indicated. Parameters for use in the detection and thresholding portions of the system are computer-optimized by means of a genetic algorithm.

Abstract: Methods and apparatus for determining the allocation of a trap width to the spread of a pair of inks in printing. Allocation of the spread is based on both a solidity value that may be between zero and one and a lightness value. The technique may be applied to an arbitrary number of inks by considering each pair of inks separately.

Abstract: In a method for modifying the resolution of an image obtained by digitising a real image, the digitised image includes a plurality of pixels of a particular intensity. The outlines in the digitised image are studied and isolated and additional pixels are created by interpolation of the intensities of original pixels located on one side of an outline to form an image with a modified resolution. The studying of outlines is achieved by locating, for close pixels, the intensity transitions representative of a gradient exceeding a particular threshold. The method is utilized for modifying the image resolution of facsimile machines.

Abstract: A fingerprint image is divided into blocks of pixels. The blocks are determined to be within the foreground or background of the image. Each of the foreground blocks are assigned a block direction. If an image consists of the complete impression of the fingerprint, there should exist at least one path (ridge), composes of foreground blocks, which lies on both half planes of a coordinate system with an origin at the centroid of the foreground and that comes sufficiently close to the x axis once the path crosses to the second half plane of the coordinate system.

Abstract: An image processing system for effecting a predetermined transformation to data representing a multiplicity of pixels which together form an initial image so as to create data representing a multiplicity of pixels which together form a transformed image in which each pixel is formed as a weighted combination of pixels in a respective block of data in the initial image. The system includes a controller operable for each pixel in the transformed image to identify the block of data containing all pixels in the initial image that contribute to the transformed image pixel, to divide the block into a plurality of sub-blocks comprising a plurality of rows of pixel data and plurality of columns of pixel data, and to calculate for each sub-block a set of transformation coefficients depending on the predetermined transformation.

Abstract: An image processing apparatus which eliminates a deformation depending on the position of expansion which is produced when parallel contours within contour information are drawn on a bit plane.

Abstract: A method of printing an image with an electronically sharpened edge. The method uses an image writing medium to form an image on a substrate. The image is printed using a range of writing medium exposures greater than a standard range. The standard range is the range required to insure that macroscopic areas of the substrate exhibit the full density range of the substrate between Dmin and Dmax. Such printing provides that sharpened edges of the image will be printed with reduced clipping of sharpened edge density. An apparatus for executing the method is also provided.

Abstract: A decaying, propagating reference signal allows for the efficient implementation of various image morphological operations, including grayscale dilations and erosions, with only two passes through the image. Pyramid and other morphological shape operators can be duplicated by varying the decay rate(s) of the reference signal, the offset directions and magnitudes of the comparison vector(s), and the paths and number of passes through the image. The methods may also be performed in parallel on the same input image to generate an adaptive threshold image defined as the biased average of an image separately transformed by a dilation and by an erosion. Applications of the technique in one and two dimensions are disclosed.

Abstract: A tracking method including receiving a representation of an event including at least one dynamic object having a border and having at least one edge portion which is absent during at least a portion of the event and providing an ongoing indication of the location of the border of the object during the event. Apparatus for carrying out the method is also disclosed.

Abstract: A multiple spatial channel technique is described that can produce near continuous-tone output quality from an output device having a large, dilute dot channel, referred to as the L (lowpass) channel, and a small, concentrated dot channel, referred to as the N (noisy) channel. The new process described here overcomes contouring artifacts and produces vastly improved images over techniques that use only a single dot type. Given a matrix of image luminance values (raster), two images are computed for printing with the two channels of the printer. The two images are computed simultaneously with a two-pass algorithm, one pass horizontally and one pass vertically. Initially, the L channel image is set to be equal to the input image. Each adjacent pair of pixels in the original image is compared by calculating an edge contrast strength.

Abstract: A method and system for processing a digital image of an object comprises forming a single pixel image outline of the object in a digital image and producing a measure of the outline shape as a single number. In this way risk of spina bifida can be determined from an ultrasonic image of a fetal skull.