Abstract: A method to authenticate a mobile station B in a mobile network, so that the mobile station B is authenticated and an encryption key is agreed between mobile stations A and B using user data exchange during call setup. More specifically the mobile station B is authenticated by the mobile station A constructing and sending to the mobile station B a message M1, the mobile station B receiving the message M1, constructing and sending a message M2 to the mobile station A, the mobile station A receiving the message M2, checking the validity of the information in the message M2, if the information is verified valid the mobile station A accepting to share a shared encryption key K with mobile station B, the mobile station A constructing and sending the message M3 to the mobile station B, the mobile station B receiving the message M3 and verifying the validity of the information, if the information is valid the mobile station B accepting the sharing of the shared encryption key K with the mobile station A.

Abstract: A method and apparatus is disclosed for introducing alterations or distortions in projected images. The distortions on the projected image are imperceptible to a human viewer. The distortions are recorded on recording devices and observable upon viewing the recorded images.

Abstract: Methods and systems are disclosed in which information is securely transmitted in a network comprising untrusted network devices. Setup messages are sent to a networking device, and based on the setup messages, light directing devices are configured to direct light along a path from an origin endpoint to a terminal endpoint, thus providing a path through the network. Through the path, a stream of light information is sent using a plurality of light pulses to carry out quantum-cryptographic key distribution.

Abstract: Rather than downloading each content document on demand from the publisher location to the user site, at the publisher location, each content document is encrypted and then multiple encrypted documents are assembled into a distribution archive that is itself encrypted with a scheduled key. The distribution archive is then downloaded into a content server at the user site. When the content server receives the distribution archive, it decrypts the archive file and unpacks the encrypted documents. The scheduled key used to decrypt an archive file is included with an archive file that was sent previously to the user site in accordance with the subscription service. The scheduled key to decrypt the first archive file sent to the user is sent from the publisher to the user over a communication channel different from the communication channel used to send the archive file from the publisher to the user.

Abstract: The invention relates to a hearing aid with a signal processing unit (14) and at least two microphones (1, 2, 3) which can be coupled together to form directional microphone systems of a different order, where microphone signals (11, 12, 13) emitted by directional microphone systems of a different order can be coupled together in a weighting dependent on the frequency of the microphone signals. The invention further relates to a method for operating a hearing aid of this type.

Abstract: The correct recognition of the auditory situation “television” often poses a problem for hearing aid devices with automatic situation recognition, since a plurality of real situations are simulated by the television audio signal. To correctly recognize the situation “television”, the invention therefore provides to detect a line signal with a particular line signal frequency output by the television device, and given the existence of such a line signal to automatically implement the auditory situation “television”.

Abstract: Acoustical signals impinging on an input converter are converted into a first electric signal by a controllably variable transfer characteristic. The transfer characteristic is dependent on the angle at which the acoustical signals impinge on the input converter. The first electric signal is processed and a resulting signal is applied to an output converter. Feedback to be suppressed is compensated by a feedback compensating signal, which is generated in dependency of the resulting signal and is fed back by a feedback signal path upstream of the processing. The electric feedback compensating signal is fed back to and superimposed upon the first electric signal. An adaptation rate of the converting into a first electric signal by a controllably variable transfer characteristic is controlled in dependency of the loop gain along the feedback signal path.

Abstract: A system includes a number of electronic devices that uses multiple voltage sources and a supply source to provide the different supply voltages without up-converting a voltage level or down-converting a voltage level. In an embodiment, the supply source is realized using a battery having multiple voltage taps, where the battery provides the multiple voltage sources. In an embodiment, the system is a hearing aid. A single battery includes a common substrate on which a number of battery regions is formed, where each battery region provides a supply voltage at a rated voltage level different than the other battery regions. The common substrate may be configured as a rigid platform, a flexible platform in a folded configuration, a flexible platform in a rolled configuration, or other platform configurations that provide for multiple battery regions on a single platform.

Abstract: A suspension tube for a transducer, wherein the suspension tube also functions as a sound-guide for directing sound between the transducer and the external cabinet of an audio processing device, wherein the suspension tube has means for forming a connection with the inlet/outlet of the transducer at a first end and means for forming a connection with the cabinet wall of the audio processing device at a second end in order to guide sound through the tube, and wherein the intermediate part of the tube in the length direction has alternating wide and narrow parts.

Abstract: A system is disclosed for changing a coverage angle of sound produced from a loudspeaker system. The loudspeaker system includes an enclosure that projects sound at a predetermined angle. A sound integrator includes an inner surface positioned adjacent to a mid-range frequency sound source. An outer surface of the sound integrator includes a planar and a curved surface. The surfaces control the angle which sound radiates from the loudspeaker.

Abstract: A small earphone or headphone which can produce a wide band acoustic output from a low-pitched tone to a high-pitched tone and can generate a body-sensitive vibration independent output or a body-sensitive vibration output synchronized with a music. The earphone or headphone is mounting a vibration actuator which is provided with a magnetic circuit including a permanent magnet, a yoke, and a plate for concentrating the flux of the permanent magnet, with a coil disposed in an air gap of the magnetic circuit, with a diaphragm fixed with the coil and being imparted with a driving force therefrom, and with a vibration transmitting section for supporting the magnetic circuit flexibly through a suspension comprising a flexible spring.

Abstract: A wide dispersion speaker system 1 comprises a cone type speaker unit 2, and a restricting element 10A. The restricting element 10A is provided with a center hole 11 at a center section thereof, and a peripheral hole 12 located outward relative to the center hole 11. The restricting element 10A has an annular sound travel inhibiting portion 19 positioned radially outward relative to the center hole 11 and radially inward relative to the peripheral hole 12. An outer end in a radial direction of the sound travel inhibiting portion 19 is positioned at a substantially middle point between an outer end in the radial direction of the center hole 11 and an outer end in the radial direction of the peripheral hole 12 or positioned radially outward relative to the substantially middle point.

Abstract: A voice coil and a magnetic driving circuit oscillate a diaphragm and a center cap. A magnetic lighting circuit for providing a magnetic field to an induction coil is mounted separately from a magnetic driving circuit. The induction coil generates an electromotive force for lighting light-emitting devices. Further, the light-emitting devices, the induction coil, and the magnetic lighting circuit are mounted integrally on the center cap.

Abstract: A speaker includes a diaphragm having a central aperture at which a bobbin with a voice coil wound therearound is mounted, and mounted at the outer periphery thereof on a frame with an edge therebetween, and a magnetic circuit section that has a magnetic gap in which the bobbin is placed, and that drives the diaphragm to vibrate in the frontward and rearward direction. The speaker can use a larger diaphragm by providing the frame with an edge-mounting portion on which the edge is mounted, and a portion formed in front of the edge-mounting portion.

Abstract: A frame is provided with an opening allowing insertion of a jig for setting an inner rim of a suspension holder to a proper position. The jig ensures positive alignment of the suspension holder when making connection to the frame. The jig also ensures reliable bonding of a diaphragm to the suspension holder with a bonding agent, since it steadily supports the suspension holder in position during the bonding process. The positioning of the bobbin and a voice coil is thus reliable when being assembled, thereby improving acoustic performance of a speaker.

Abstract: An image position matching apparatus and an image processing apparatus capable of accurately matching the positions of a three-dimensional past image and a two-dimensional present image, even for cases in which fluctuation in the position of the subject has occurred when the respective images were obtained. An image reducing means reduces to 1/10 size a three-dimensional past image data and a two-dimensional current image data that have been inputted thereto. The reduced three-dimensional past image data and the reduced two-dimensional current image data are inputted to a position matching image obtaining means from the reducing means. After the reduced three-dimensional image data has been subjected to a three-dimensional affine transform by the position matching image obtaining means, a two-dimensional past image data having a high correlation with the reduced two-dimensional present image is obtained utilizing a projection transform by perspective projection.

Abstract: A computer-implemented system and method of intra-oral analysis for measuring plaque removal is disclosed. The system includes hardware for real-time image acquisition and software to store the acquired images on a patient-by-patient basis. The system implements algorithms to segment teeth of interest from surrounding gum, and uses a real-time image-based morphing procedure to automatically overlay a grid onto each segmented tooth. Pattern recognition methods are used to classify plaque from surrounding gum and enamel, while ignoring glare effects due to the reflection of camera light and ambient light from enamel regions. The system integrates these components into a single software suite with an easy-to-use graphical user interface (GUI) that allows users to do an end-to-end run of a patient record, including tooth segmentation of all teeth, grid morphing of each segmented tooth, and plaque classification of each tooth image.

Abstract: A method of embedding watermark data into a two-colour (binary) image includes dividing the image into blocks and assessing the suitability of each block to embed a bit of watermark data by assessing whether or not the flipping of a defined pixel in each block affects the visual attributes of said block in manner to be perceptible by the human eye. Data is only embedded in those blocks determined to be suitable for data embedding, by flipping the defined pixel, as required. A recipient of the document may similarly assess which blocks contain watermark data, by assessing the suitability of each block in the document to embed such data. Conveniently, watermark data may be extracted without further information about the data's location within a document.

Abstract: A portable flight parameter measurement system is a standalone smart camera which tracks the surface of an object in motion, e.g., a ball, and determines speed, trajectory, a spin axis, and a spin rate around that axis. The measurement system is particularly suited for analyzing the path of a ball in flight which is determined, in great part, by the amount of spin and the direction of spin imparted to the ball upon impact. The measurement system provides a user, such as a golfer, with important feedback for modifying his or her swing to obtain desired results. The measurement system utilizes non-precision marks, surface blemishes such as cuts made by a club, dimples, or a combination of all three as the only features necessary to determine ball flight characteristics.

Abstract: A method of and system for determining the angular orientation of an object, such as a person's head. In one aspect, a plurality of images of the object is obtained. Values are assigned to a plurality of positions in a polar plot using data from the images. A centroid is computed based on the assigned values. An angle of the centroid with respect to an origin of the polar plot indicates the angular orientation of the object.

Abstract: A method of multi-resolution adaptive correlation processing of images, such as seeded fluid flow images, to efficiently increase the spatial resolution and dynamic range of detecting particle image displacements in the images. The technique takes full advantage of the multi-resolution characteristic of the discrete correlation function by starting the processing at the smallest scale and if necessary gradually building correlation planes into larger interrogation areas based on the result of inter-level correlation correction and validation. It is shown that the method can be implemented in both direct and FFT based correlation algorithms with greatly reduced computational complexity. Processing the images at the lowest scale (e.g. pixel or particle image size) allows the combination of correlation planes of various shapes both in space and in time for maximizing the correlation plane signal-to-noise ratio or for estimating statistical flow parameters.

Abstract: A method for assigning of geocodes to addresses identifying entities on a street includes ordering a set of entity geocodes associated with a street segment based on ordering criteria such as the linear distance of the geocodes along the length of the street segment. Assignable addresses are matched with the ordered geocodes creating a correspondence between a numerical order of the assignable addresses and a linear order of the ordered set of geocodes, consistent with address range direction data and street segment side data. The geocodes may be implicit or explicit, locally unique or globally unique. The set of entity geocodes may be obtained by identifying image features in aerial imagery corresponding to streets and buildings and correlating this information with data from a street map database.

Abstract: A data converter is provided, which data converter includes a data conversion unit, a timer unit which counts time, and a lock system which locks a data conversion function of the data conversion unit in a disabled state based on the time counted by the timer unit.

Abstract: A method of performing a beauty analysis is disclosed. The method comprises receiving information of at least one portion of a subject's external body condition, identifying in the information at least one condition, extracting from the information at least one feature of the at least one condition, and storing extracted information reflective of the at least one feature.

Abstract: Disclosed is an image processing apparatus in which the cheek of a person captured in an image of a photo may be corrected to a finish with the cheek looking slimmer than in a two-dimensional photo. A face correction unit (400) calculates, in a calculation unit (411), a face length L1 and a cheek width L2 of a face of a person as an object and L3 corrected from the face length L1. A face classifying unit (412) compares L2 and L3 to each other to classify the face shape into a ‘round shape’, ‘a long shape’ and a ‘square shape’. Depending on the results of classification, the image trimming is carried out by a first contour correction unit (413), a second contour correction unit (414), and a third contour correction unit (415) so that the cheek will look slim.

Abstract: A face image processing apparatus, includes: a face region detecting unit configured to detect a face feature point of a person from a plurality of images picked up by a plurality of imaging units respectively, to detect a face region; a face feature extracting unit configured to extract a face feature from an image of the face region detected by the face region detecting unit; a person recognizing unit configured to calculate a similarity measure based on a face feature of a specific person being previously registered and the face feature extracted by the face feature extracting unit to recognize the person; and an output apparatus which outputs a recognition result in the person recognizing unit.

Abstract: A system and method for real-time multi-view (i.e. not just frontal view) face detection. The system and method uses a sequence of detectors of increasing complexity and face/non-face discriminating thresholds to quickly discard non-faces at the earliest stage possible, thus saving much computation compared to prior art systems. The detector-pyramid architecture for multi-view face detection uses a coarse-to-fine and simple-to-complex scheme. This architecture solves the problem of lengthy processing that precludes real-time face detection effectively and efficiently by discarding most of non-face sub-windows using the simplest possible features at the earliest possible stage. This leads to the first real-time multi-view face detection system which has the accuracy almost as good as the state-of-the-art system yet 270 times faster, allowing real-time performance.

Abstract: An input device which generates control information by moving an object to be detected, having an image capture section which captures an image of the object to be detected, a feature point extraction section which extracts a feature point of the image captured by the image capture section, a difference calculation section which calculates a difference between a reference position and a position of the feature point, and a control information output section which outputs the control information corresponding to the calculated difference.

Abstract: There is disclosed an image processing apparatus for performing an image processing on a medical image represented by digital data in a medical field, and the appropriate image processing is performed with respect to various medical images. An image processing condition suitable for a photography condition is stored beforehand in an image processing condition storing section 218, and an image processing section 212 subjects the medical image to an image processing based on the image processing condition suitable for the photography condition when the medical image is obtained.

Abstract: An image processing device having a very straightforward construction, for obtaining an image in which normal tissue and diseased tissue are easy to identify, comprises: an image synthesizing section that generates a synthesized image by synthesizing an image signal of reflected light image produced by illumination light obtained by illuminating body tissue with illumination light and an image signal of a fluorescent image obtained by illuminating the body tissue with excitation light; and a gain adjustment section that adjusts the gain of the image signal of the reflected light image and/or the image signal of the fluorescent image such that the boundary of the hues of the normal tissue and diseased tissue found from the optical characteristics of the respective tissues is contained in a predetermined range with respect to a prescribed standard chromaticity diagram, depending on whether the body tissue that is displayed on the synthesized image generated by the image synthesizing section is normal tissue or

Abstract: A method to quantify the radial endoluminal irregularity of aortoiliac arteries is provided. Radial endoluminal outlines of a vessel of interest are determined. The cross sectional area is determined for the area outlined by each endoluminal outline. Using this cross sectional area a shape is selected that has substantially the same area as the endoluminal outline. Subsequently, the shape is fitted to the endoluminal outline. In one aspect, the irregularity index is calculated as the ratio of the endoluminal outline and the outline of the fitted shape. In another aspect, the irregularity index is calculated as the ratio of at least a part of the endoluminal outline and the outline of the fitted shape that corresponds to the same part of the endoluminal outline. The irregularity index is visualized using a color scheme, a range of numbers, or a set of labels.

Abstract: Primary prospective abnormal shadow regions in images of objects are detected by different kinds of detecting processes. Whether or not the respective primary prospective abnormal shadow regions are of a desired abnormal shadow is determined by methods different from each other according to the kinds of processes by which the respective primary prospective abnormal shadow regions are detected. Only primary prospective abnormal shadow regions which are determined to be of a desired abnormal shadow are output as final prospective abnormal shadow regions.

Abstract: Methods, systems and recordable media for accurately reading and identifying high quality signals from a microarray feature. Signals may be identified and used regardless of their geographic/geometric locations and patterns within the feature zone. High quality signals may be read, identified and outputted from a microarray feature in a geometrically independent manner, such that the best quality signals are identified and useable, regardless of the locations or patterns in the region from which the best quality signals are outputted.

Abstract: In order to model a fluoroscopic noise present in a radiography operation, two successive images of a same zone are used so that it is possible to pair the dots of the two images as a function of the zone of the space that they represent. The pairs of dots are grouped in sub-groups according to their gray level. For each sub-group, the mean standard deviation ? of the Pi(x, y)?Pi?1(x, y) values is computed. A sub-group is discriminated by eliminating the dots for which Pi(x, y)?Pi?1(x, y) is greater than the mean of the values Pi(x, y)?Pi?1(x, y) plus k times the mean standard deviation. These computations are repeated a certain number of times. Once the sub-group is discriminated, its centering is assessed. A sub-group is non-centered if its mean is greater than 1.5 times its mean standard deviation. Pairs of dots (v, ?) are then obtained. From these dots, an iterative regression is performed to obtain a model of noise according to ?(v)=?.?v+?.

Abstract: A medical image radiographing system has a medical image reading apparatus to read out identification information of a cassette and a medical image from the cassette recording the medical image radiographed according to radiographing order information, a portable radiographing information apparatus having a correspondence setting section to set correspondence of the identification information of the cassette to the radiographing order information for radiographing using the cassette, and a judging section to judge whether or not the cassette is usable for next radiographing. The correspondence setting section prohibits the setting of the correspondence of the identification information of the cassette, which is judged by the judging section to be nonusable for the next radiographing, to the radiographing order information.

Abstract: A method and device for identifying objects, especially teeth, on a digitized X-ray picture, by using image processing algorithms to localize areas containing the object by segmenting and/or edge detection, these areas being computationally linked with parameters of the X-ray unit and, optionally, with patient-heightened specific parameters. Another method and device for assigning information to objects, especially teeth, determined in a digitized X-ray picture or in a schematic representation, includes a first step detecting the digitized X-ray image for the schematic representation, a second step in which a determination of objects manually or automatically ensues in the event these objects have not yet been determined, a third step selecting the object for which additional information should be stored, retrieved or deleted, and a fourth step in which a reference tht is stored is followed for a query operation to determine the information displayed by using such reference.

Abstract: The present invention is directed to solving the problems associated with the detection of surface defects on metal bars as well as the problems associated with applying metal flat inspection systems to metal bars for non-destructive surface defects detection. A specially designed imaging system, which is comprised of a computing unit, line lights and high data rate line scan cameras, is developed for the aforementioned purpose. The target application is the metal bars (1) that have a circumference/cross-section-area ratio equal to or smaller than 4.25 when the cross section area is unity for the given shape, (2) whose cross-sections are round, oval, or in the shape of a polygon, and (3) are manufactured by mechanically cross-section reduction processes. The said metal can be steel, stainless steel, aluminum, copper, bronze, titanium, nickel, and so forth, and/or their alloys. The said metal bars can be at the temperature when they are being manufactured.

Abstract: Systems and methods are provided for excluding extraneous image features from inspection operations in a machine vision inspection system. The method identifies extraneous features that are close to image features to be inspected. No image modifications are performed on the “non-excluded” image features to be inspected. A video tool region of interest provided by a user interface of the vision system can encompass both the feature to be inspected and the extraneous features, making the video tool easy to use. The extraneous feature excluding operations are concentrated in the region of interest. The user interface for the video tool may operate similarly whether there are extraneous features in the region of interest, or not. The invention is of particular use when inspecting flat panel display screen masks having occluded features that are to be inspected.

Abstract: Determination of inclination of positioning patterns used in bonding being made by: imaging a positioning pattern of reference chip and taking such image as reference-image; specifying a polar coordinate conversion origin for the reference-image; imaging an object (chip) of bonding to use it as an object-image, thus obtaining a relative positional-relationship with the reference-image; specifying the polar coordinate conversion origin of the object-image, so that the object-image is subjected to a polar coordinate conversion; and calculating inclination-angle from both images that have been subjected to a polar coordinate conversion; thus using a point, in which an error in position of the object of comparison detected by pattern matching between an image, which is the object of comparison obtained by imaging the object of comparison disposed in an attitude that includes positional deviation, and the reference-image, shows a minimal value, as an origin of the polar coordinate conversion.

Abstract: With an assumption that the three data of the position (X1, Y1) of the first positioning pattern 202 and position (X2, Y2) of the second positioning pattern 212 of the reference chip 200, and the position (X3, Y3) of the first positioning pattern 232 of the bonding object chip 230, as well as the length L of a line segment connecting (X1, Y1) and (X2, Y2), and the angle ?2 of this line segment with respect to the X axis, are known, the coordinates (X4, Y4) of the center position of the imaging range 250 that is to be imaged next is determined by detecting the inclination-angle ?? of the first positioning pattern 232 of the bonding object chip 230. Furthermore, the imaging range can be narrowed and the second positioning pattern 252 can be captured by increasing the precision of ??.

Abstract: In one embodiment, a system comprises logic configured to identify a tip of a pin that has been press fit into a circuit board, logic configured to measure characteristics that pertain to a flat end surface and a chamfered surface of the identified pin tip, logic configured to compare the measured characteristics with at least one of stored reference values and each other, and logic configured to make a final decision as to whether the pin is properly installed based upon results of the comparing performed by the logic configured to compare.

Abstract: The technology described relates to reconstruction of 3-dimensional scenes from uncalibrated images, and provides a robust and systematic strategy for using cheirality in scene reconstruction and camera calibration. A general projective reconstruction is upgraded to a quasi-affine reconstruction. Cheirality constraints are deduced with regard to the cameras by statistical use of scene points in a voting procedure. The deduced cheirality constraints constrain the position of the plane at infinity. Linear programming is used to determine a tentative plane at infinity. Based on this tentative plane at infinity, the initial projective reconstruction can be transformed into a reconstruction that is quasi-affine with respect to the cameras.

Abstract: A system and process for computing a 3D reconstruction of a scene from multiple images thereof, which is based on a color segmentation-based approach, is presented. First, each image is independently segmented. Second, an initial disparity space distribution (DSD) is computed for each segment, using the assumption that all pixels within a segment have the same disparity. Next, each segment's DSD is refined using neighboring segments and its projection into other images. The assumption that each segment has a single disparity is then relaxed during a disparity smoothing stage. The result is a disparity map for each image, which in turn can be used to compute a per pixel depth map if the reconstruction application calls for it.

Abstract: A method determines a direction of a principal light source in an image. An input image I is acquired of an object illuminated by a principal light source from an unknown direction. The input image includes an array of pixels, and each pixel has an intensity I(x, y). An intensity vector {right arrow over (I)} is constructed from the intensities of the input image. An albedo map ? is defined for the object. An albedo vector {right arrow over (?)} is constructed from the albedo map. A shape matrix N is generated for the object. The albedo vector {right arrow over (?)} is multiplied by the shape matrix N to obtain a shape-albedo matrix A. Then, a direction s* to the principal light source is estimated from the intensity vector {right arrow over (I)}, the albedo vector {right arrow over (?)} and the shape-albedo matrix A according to an optimization s * = arg ? ? min s ? ? I ? - ? ? - As ? .

Abstract: A method of performing red eye correction in an image including storing a high resolution image on a server computer, transmitting a low resolution image derived from the high resolution image, from the server computer to a client computer, displaying the low resolution image on a display device connected to the client computer, receiving from a user an indication of a selected location within the displayed low resolution image, partially automatically defining an outline of an area in the low resolution image within which area red eye correction is to be carried out, by the client computer, based on the user's selected location, carrying out red eye correction on the low resolution image only within the area, by the client computer, and transmitting parameters of the area from the client computer to the server computer. A system is also described and claimed.

Abstract: An apparatus and method for controlling gain characteristics in a CMOS imager and for calibrating light intensity and analog to digital conversion in a pixel array. A mask with varying sized apertures is provided over pixels of an array outside the active area for use in intensity adjustments and calibration.

Abstract: A system and method for shape recognition of hand-drawn objects is provided. A shape recognizer may recognize a drawing such as a diagram or chart from ink input by recognizing closed containers and/or unclosed connectors in the drawing. The closed containers may represent any number of shapes that may be recognized including circles, ellipses, triangles, quadrilaterals, pentagons, hexagons, and so forth. The unclosed connectors may be any type of connector including lines, curves, arrows, and so forth. Polylines may be used to approximate a skeleton of a connector for handling continuation strokes, overlapping strokes and over-tracing strokes of the skeleton. By using the present invention, a user may draw diagrams and flow charts freely and without restrictions on the hand-drawn input.

Abstract: The present invention is a character recognition apparatus, which comprises a background discriminating section, a non-character line discriminating section, a first non-character line removed image creating section that creates a first non-character line removed image, which is an original image from which the non-character line is removed, a first character area discriminating section, an enlarged image creating section, a second non-character line removed image creating section, an interference judgment section that judges whether or not the character and the non-character line interfere with each other in the original image, a character image restoring section that restores the character image, a second character area discriminating section, and a character recognizing section that digitizes the character area recognized by the second character area discriminating section and recognizes the character, thereby characters written on a color form are recognized at a high accuracy.

Abstract: A digital image processing method for automatically outlining a contour of a figure in a digital image, including: testing parameters of a region within the digital image according to a plurality of cascaded tests; determining whether the region contains characteristic features of the figure within the digital image; computing location parameters of the characteristic features in the region for the figure within the digital image; determining boundary parameters for the figure corresponding to the location parameters of the characteristic features in the region; computing an information map of the digital image; computing a set of indicative pixels for the contour of the figure; and automatically outlining the contour of the figure using the set of indicative pixels, the information map, and a contour outlining tool.

Abstract: Most automatic particle classification methods produce errors. The invention provides a method for improving the accuracy of particle classification while shortening the amount of manual review time required from the operator. The method uses class weights, which are statistically-derived correction factors that accounts for frequency of classification errors. A first class weight and a second class weight are assigned to the first class and the second class, respectively. The number of particles in each of the first and the second classes is multiplied by the first class weight and the second class weight, respectively, to generate a corrected number of particles in each of the classes. If particles are reclassified, the class weights are recalculated in response to the reclassification. The method is usable with a complete classification where all the particles in a sample are classified, or a selective classification of a subset of the particles in the sample.