Abstract: A fast loss less image compression system based on neighborhood comparisons compares pixel value differences with neighboring pixels and replaces such pixel values with the minimum of the differences. A marker is attached to a block of pixels, such that all the pixels in that block are compared with neighbors of one direction. The marker indicates how all of the pixels in that block are compared. Intermittent Huffman-tree construction is used such that one tree is used for several frames. Huffman coding is used to compress the resulting frame. A single Huffman-tree is constructed once every predetermined number of frames. The frequency of Huffman-tree construction can be performed according to the instantaneous availability of processor time to perform the construction. When more processing time is available, the Huffman-trees are computed more frequently. Such frequency variation can be implemented by using an input video frame buffer.

Abstract: A method of representing an object appearing in a still or video image, by processing signals corresponding to the image, comprises deriving a plurality of numerical values associated with features appearing on the outline of an object starting from an arbitrary point on the outline and applying a predetermined ordering to said values to arrive at a representation of the outline.

Abstract: The present invention relates to a method for reduction of noise in an image including a plurality of pixels, comprising averaging pixel values over a region (R), comprising the steps of: adding a selected pixel to the region (R); grouping pixels adjacent the region (R) in pairs, wherein the pixels of each pair being oppositely located with respect to said selected pixel; adding said pairs, pair by pair, to the region (R) in dependence on the squared difference of the selected pixel value from the pairs half sums does not exceed the dispersion (D) of the noise of said difference multiplied by a tolerance level (L); repeating said step of grouping and said step of adding said pairs until that, in said step of adding said pairs, the condition for adding said pairs is not fulfilled for any pair; averaging the pixel values of said region (R); and using the thus averaged pixel value for the selected pixel of said region (R) in reconstruction of said image.

Abstract: The present invention provides extended depth of field or focus to conventional Amplitude Contrast imaging systems. This is accomplished by including a Wavefront Coding mask in the system to apply phase variations to the wavefront transmitted by the Phase Object being imaged. The phase variations induced by the Wavefront Coding mask code the wavefront and cause the optical transfer function to remain essentially constant within some range away from the in-focus position. This provides a coded image at the detector. Post processing decodes this coded image, resulting in an in-focus image over an increased depth of field.

Abstract: A system identifies an abrupt transition in content between two frames, and determines whether the abrupt transition was caused by a shot boundary between the two frames or by a flashlight event. Identification of the abrupt transition in content includes calculating a difference in light intensity histograms between the current frame and a preceding frame, and comparing the histogram difference to a dynamically determined threshold. Further, an average light intensity based method is used to determine whether the abrupt transition was caused by a shot boundary or by a flashlight event.

Abstract: A system, method, and computer-readable medium for detecting and eliminating correspondence errors associated with image occlusions. In a first embodiment of the invention, the method applies traditional correspondence methods for matching points in two images, a left image (FIG. 1A) and a right image (FIG. 1B), taken of the same scene. The method applies the correspondence method to locate a matching a point (310) in the right image (FIG. 1B) with a “best match” point (320) in the left image (FIG. 1A). A set of matching points (310, 320) is generated. A second search is then performed by using the best match point (320) in the right image (FIG. 1B) as the basis for an additional correspondence search in the left image (FIG. 1A). The range of match candidates in the second search is such that points to the left of the starting point (310) are not tested as match candidates.

Abstract: In a computer system, methods and computer-readable medium are disclosed for tracking motion of a subject in an activity captured by camera. The camera supplies pluralities of discrete images of the subject to a computing system environment. An event window, displayed on a monitor, has at least two cells for receiving a user input pertaining to an action of the subject in the activity. In a first of the two cells, the user indicates a specific image number corresponding to one of the plurality of discrete images and an estimate of a fractional percent thereof. In the second cell, the user indicates another specific image number and estimate of a fractional percentage thereof. Software calculates a delta between the specific image numbers and their corresponding estimated fractions. Scroll and position bars provide user-aid for navigating between discrete images. Example subjects include horses in a horse race activity while an action includes a horse stride length.

Abstract: A method for determining a circle in an image is disclosed. The method extracts a first pair of edge points along an x-axis of the image, extracts a second pair of edge points along a y-axis of the image, determines an intersection of a first and second line extending perpendicular from a pair of midpoints of the first and second pair of edge points respectively, and determines a radius from the intersection to any edge point.

Abstract: Apparatus and method are described for measuring and controlling the crimp characteristics of a moving crimped tow. A light source illuminates a section of the moving crimped tow and at least one progressive scanning camera acquires a non-interlaced video image of the tow. The acquired image is digitized and a processor analyzes the non-interlaced image. Crimp characteristics are derived based on this analysis.

Abstract: A rectangle finder tool automatically locates rectangles in an image that correspond to substantially rectangular devices in the image. The rectangle finder tool can be used to automatically locate rectangles in an image or to generate abstract rectangular models of devices in the image. The tool determines the properties of and locates the rectangular device by searching for pairs of lines in an image at a specified orientation.

Abstract: A video information processing apparatus includes an input device which inputs video, a memory device which stores identification information corresponding to the blinking pattern of a blinking light source, a blinking light decoder which converts the blinking pattern of the light source blinking in the video information input by the input device into corresponding identification information on the basis of the identification information stored in the memory device, and an output device which outputs together with the input video the identification information converted by the blinking light decoder.

Abstract: A medical analysis system for reading and interpreting an occult blood test (OBT) device is provided. The instant system comprises an image sensor for capturing an image of the entire test area of the fecal occult blood test (FOBT) device and for converting the image into a digital data. The system further comprises a data processor conventionally coupled to the image sensor. The data processor compares the digital data with pre-determined threshold conditions of a positive FOBT by utilizing a spectrographic and morphologic image analysis algorithm and determines a presence of the occult blood in the sample. A hue angle analysis for data processing may be used. A method of performing FOBT on a sample is also provided.

Abstract: A method and apparatus are provided for identifying diffe rences between a stored pattern and a matching image subset, where variations in pattern position, orientation, and size do not give rise to false differences. The invention is also a system for analyzing an object image with respect to a model pattern so as to detect flaws in the object image. The system includes extracting pattern features from the model pattern; generating a vector-valued function using the pattern features to provide a pattern field; extracting image features from the object image; evaluating each image feature, using the pattern field and an n-dimensional transformation that associates image features with pattern features, so as to determine at least one associated feature characteristic; and using at least one feature characteristic to identify at least one flaw in the object image. The invention can find at least two distinct kinds of flaws: missing features, and extra features.

Abstract: A monitoring system suitable for a vehicle has a display which displays an image of the road area traveled by the vehicle. The system further comprises a controller which is capable of allocating differing sets of grey values held in its memory to the objects in the image. Changes in the allocation of grey values are made in response to a user input, which in a preferred embodiment comprises a grey value allocation switch.

Abstract: Mark detection and position determination are improved by use of directional elongated filters, symmetry, gray scale image processing, structural constraints, and learning. Directional elongated filters are used to pre-process images of registration marks to create masks and enhanced images. Working sequentially, portions of the mark are detected and classified. The input gray scale image of the mark is processed using its structural constraints in conjunction with a mask for the detected mark. A cost function estimation determines mark position and orientation with sub-pixel accuracy. Learning is used to improve specific application performance.

Abstract: A method and apparatus are provided for identifying differences between a stored pattern and a matching image subset, where variations in pattern position, orientation, and size do not give rise to false differences. The invention is also a system for analyzing an object image with respect to a model pattern so as to detect flaws in the object image. The system includes extracting pattern features from the model pattern; generating a vector-valued function using the pattern features to provide a pattern field; extracting image features from the object image; evaluating each image feature, using the pattern field and an n-dimensional transformation that associates image features with pattern features, so as to determine at least one associated feature characteristic; and using at least one feature characteristic to identify at least one flaw in the object image. The invention can find at least two distinct kinds of flaws; missing features, and extra features.

Abstract: An apparatus and method for the biometric identification of a person, who has an authentication area containing biometric features, the apparatus including a sensor having an identification area for detecting the biometric features of the part of the person's authentication area which is situated on the identification area, a comparison device for comparing the detected biometric features with the biometric features, stored in a memory, of a part of the authentication area of an authorized person or of a number of authorized persons in order to determine the relative position of the biometric features detected by the sensor within the part of the authentication area, and a computation device for calculating an identification code, which identifies the person detected by the sensor, from the detected biometric features which are not stored in the memory on the basis of the relative position of the biometric features which are stored in the memory within the stored authentication area.

Abstract: To provide an apparatus for rough classification of words that allows features of words to be stored in a vocabulary storage division to be generated from character codes of the words so that the words can be efficiently selected. A candidate character selection division 1 detects areas likely to be characters from a word image, and a character recognition division 2 recognizes candidate characters generated in candidate character selection division 1 and converts them into character codes. A number-of-characters estimation division 3 estimates the number of characters of the entire word image and the number of characters of the areas between candidate characters, a word description division 4 generates word description equivalent to a state transition graph from the recognition results of candidate characters and the estimated number of characters of candidate character separations.

Abstract: A system identifies a character code. This character code may be received from keyboard entry, read from memory, or acquired from an external network, for example. This character code can comprise an arrangement of bytes. Each byte can be identified as a group, plane, row, or cell. The row and plane values of the character code can be mapped to corresponding row and plane values of an optimized character code. Character attributes associated with each optimized character code can be accessed. The row and plane values of optimized character codes can be mapped to corresponding row and plane values of character codes.

Abstract: A system and method for determining image similarity. The method includes the steps of automatically providing perceptually significant features of main subject or background of a first image; automatically providing perceptually significant features of main subject or background of a second image; automatically comparing the perceptually significant features of the main subject or the background of the first image to the main subject or the background of the second image; and providing an output in response thereto. In the illustrative implementation, the features are provided by a number of belief levels, where the number of belief levels are preferably greater than two. The perceptually significant features include color, texture and/or shape. In the preferred embodiment, the main subject is indicated by a continuously valued belief map.