Abstract: The invention is a system and method for determining alignment parameters (rotation angle and translation vector) between two images of scene based on the attributes of segments associated with a pair of corresponding points, each point extracted from each of the images.

Abstract: The present system and apparatus uses image processing to recognize object size within a scene. The system includes novel image processing apparatus and methods to segment one or more object images from a background image of the scene. A processed image (that can be used to characterize size features) of the object(s) is then compared to stored reference images. The object size is recognized when a match occurs. The system can recognize object sizes independent of number of objects present and the objects may be touching each other and overlapping. The system can be trained to recognize object sizes that it was not originally programmed to recognize.

Abstract: A method to hide small messages in a wavelet compressed fingerprint image is presented. The method is characterized by random placement of the message bits in the compressed and quantized indices. The compressed image can be decompressed by any certified decompressor without any visible difference. However, the decoder aware of the decompression can only retrieve the hidden message in the image and additionally decompress the image without any error in pixel values.

Abstract: A reliable estimate of image pixel (fingerprint ridge) orientations, and block orientations for a given block is determined by finding an optimal block size in an area of an image, e.g., a fingerprint image. An initial block size is chosen. Then a block direction is determined, e.g., by analyzing intensity gradients in two directions, preferably two orthogonal directions, at a plurality (preferably all) of the pixels locations in the block. Block directions of blocks in a given area of the images (fingerprint) are compared. If the compared directions are within a tolerance of one another, the determined direction of the block is considered correct. However, if the compared directions are not within a tolerance of one another, the block size is changed and the process is repeated.

Abstract: A computer based image processing system uses an extraction process to include a pressure invariant feature for measuring distances between minutiae. The feature extraction process identifies one or more of the following features of the fingerprint: an orthogonal image contrast, a parallel image contrast, and a feature confidence. A ridge counter process, executing on the computer system, determines the number of ridges (ridge count) running across two given points and further qualifies (invalidates) this count if the confidence value of the pixels in the region adjoining the region is not reliable. The ridge count feature between minutiae is used for determining reliable features when matching fingerprints.

Abstract: Disclosed in a system and method for segmenting foreground pixel from background pixels in a digital image, specifically a fingerprint image. First the image is divided into blocks of optimal size. Then, for a given block, an overall gradient magnitude and a projected gradient magnitude is determined. The overall gradient magnitude is a measure of the amount of intensity variation in the current block. If a large number (or all) of the pixels have a direction that is the same as the overall gradient direction, the projected gradient magnitude will be nearly equal (will be equal) to the overall gradient magnitude. This indicates that the current block is a block in the foreground of the image. A relationship, e.g., a ratio, of the over gradient magnitude to the overall projected gradient magnitude is taken certainty level that the current block is in the foreground or background of the image.

Abstract: The invention is a system and method for matching a two dimensional pattern of lines, e.g. a fingerprint, by creating a one dimensional representation of one or more points (e.g., minutiae) on the lines in the patterns to be matched. The one dimensional representations are created by finding a corresponding reference point (minutiae) in each of the patterns and creating an index of other points in each of the respective patterns with respect to the reference point (minutiae). The indexes are adaptively compared taking into account the elastic distortions of the lines.

Abstract: A computer based image processing system uses an extraction process to include a pressure invariant feature for measuring distances between minutiae. The feature extraction process identifies one or more of the following features of the fingerprint: an orthogonal image contrast, a parallel image contrast, and a feature confidence. A ridge counter process, executing on the computer system, determines the number of ridges (ridge count) running across two given points and further qualifies (invalidates) this count if the confidence value of the pixels in the region adjoining the region is not reliable. The ridge count feature between minutiae is used for determining reliable features when matching fingerprints.

Abstract: A computer based image processing system uses an extraction process to extract one or more features from a target fingerprint image. The feature extraction process identifies one or more of the following features of the fingerprint: orthogonal image contrast, parallel image contrast, feature confidence, distance between two minutia, neighbor information, angle-distance between two minutia, angle-distance neighbor information, minutiae density, ridge length, ridge density, and wiggle factor. A pruner process, executing on the computer system, determines if one or more of the features meet any one or more of a set of pruning criteria, and that deletes the minutiae if the pruning criteria is met. The pruning process is based on (i) locations and image contrast, (ii) the distances, orientations of minutiae and (iii) spatial distributions of minutiae and ridges of the fingerprint. The minutiae that remain after the pruning can be used for feature matching.

Abstract: A computer system and method determines the force and/or torque applied during the image acquisition stage of a biometric characteristic. Images with very high or very low pressure or high shear torque are rejected and user/operator is notified to re-acquire the image. Alternatively, the application of force and torque by the subject is restricted mechanically so that the images are acquired while the force and/or torque are within acceptable ranges.

Abstract: The invention is a system and method for determining a correspondence between a point selected from a set of points extracted from one image and an another point selected from the second set of points extracted from another image based on similarity of relationships of attributes associated with segments attached to the points.

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: The present system and apparatus uses image processing to recognize object size within a scene. The system includes novel image processing apparatus and methods to segment one or more object images from a background image of the scene. A processed image (that can be used to characterize size features) of the object(s) is then compared to stored reference images. The object size is recognized when a match occurs. The system can recognize object sizes independent of number of objects present and the objects may be touching each other and overlapping. The system can be trained to recognize object sizes that it was not originally programmed to recognize.

Abstract: A fingerprint image is divided into blocks of pixels. The blocks are also determined to be within the foreground or background of the image. A dryness process determines a mean intensity of pixels within each foreground block, a second mean intensity of pixels for those pixels whose intensities are smaller than the mean intensity, a standard deviation of intensities of all pixels within the respective foreground block, and a contrast measure being a function of a first ratio of the second mean intensity to the standard deviation. A comparator that determines that the foreground block is a dry block if the contrast measure is larger than a dryness threshold and that the image is a dry image if a second ratio of the number of dry blocks to total number of foreground blocks is larger than a third dryness threshold.

Abstract: A fingerprint image is divided into blocks of pixels. The blocks are marked as directional or non-directional. The blocks are also determined to be within the foreground or background of the image. Contiguous regions of blocks that are in the foreground and are directional are selected. The quality measure is the ratio of the area of all these selected contiguous regions to the total area of the fingerprint image (i.e., the foreground.) The contribution of each of the blocks of the regions to the quality measure can be given by a distance from a block containing a reference point (a block of reference) within the foreground. Further, the block of reference can be located at the centroid of the foreground. Images are judged to be of poor quality if the quality measure is below a quality threshold and are judged to be of good quality if the quality measure is above the quality threshold. Optionally, poor quality images are examined further to determine if they are smudged or come from a dry finger.

Abstract: A fingerprint image is divided into blocks of pixels. The blocks are determined to be within the foreground or background of the image. Poor quality images are examined to determine if the imaging process is corrupted, e.g. by a wet finger, by determining if a smudginess measure is above a smudginess threshold. For each foreground block, a mean intensity (.mu.) of pixels is computed for those pixels whose intensities are smaller than the mean intensity of all pixels within the respective foreground block. Further the standard deviation (.cuberoot.) of intensities of all pixels within the respective foreground block is computed. For a foreground block with good contrast, .mu. is small and .cuberoot. is large. But for a block with low contrast due to smudginess, .mu. is small and .cuberoot. is small. Subsequently, to measure the contrast (a contrast measure) within a block, a function of the product (C.sub.S) of corresponding .mu. and corresponding .cuberoot. is determined.

Abstract: One or more sets of prototype descriptions for a number of classes of objects stored on a computer database are maintained. These prototypes are used as a basis for identifying the class of a presented object. A trainer determines when a new prototype is required to be added to the database based on current match results. This allows the system to be trained to recognize items in classes that deviate significantly from the items that were initially used to determine the classification rules. A determination is made about which prototypes can be deleted on the basis of their match histories. This allows the system to automatically optimize itself to work with a bounded collection of prototypes. In addition, it allows the system to track variations in class characteristics over time and adjust the corresponding set of prototypes appropriately.