Abstract: Techniques for generating a gradient characterization for a first fingerprint image are provided. One or more fingerprint feature points are selected from the first fingerprint image. A region is obtained for each of the one or more selected fingerprint feature points. The region is a representation of an area proximate a given fingerprint feature point. Each of the obtained regions is divided into a plurality of sub-regions. A histogram is generated for each of the plurality of sub-regions. For each of the one or more selected fingerprint feature points, the one or more generated histograms are combined into a concatenated histogram. The concatenated histogram is used for identification purposes.

Abstract: Techniques for generating a distorted fingerprint representation for a given fingerprint image are provided. First, at least one fingerprint feature point from a given fingerprint image is selected. At least one representation of a region proximate to the selected fingerprint feature point is then generated. Next, the representation of the region proximate to the selected fingerprint feature point is distorted. The distortion comprises applying a random projection to the representation to generate a randomly projected representation of the region proximate to the selected fingerprint feature point. A distorted template is then formed, wherein the distorted template comprises the randomly projected representation of the region proximate to the selected fingerprint feature point.

Abstract: In one embodiment, the invention is a method and apparatus for repeatable facial distortion. One embodiment of a method for generating a secure facial image from an original facial image includes receiving the original facial image and a key, the key being associated with a subject depicted in the original facial image, and distorting the original facial image, in accordance with the key, to produce the secure facial image, where the distorting includes transforming at least one of: the albedo of the original facial image or the shape of the original facial image.

Abstract: A system and method for processing fingerprints includes representing each minutiae in a fingerprint by determining quantized Gabor coefficients to represent texture content of the minutiae. A distance is computed between represented minutiae and stored minutiae. The minutiae matches are ranked based on the distance to identify the fingerprint.

Abstract: Techniques for generating a gradient characterization for a first fingerprint image are provided. One or more fingerprint feature points are selected from the first fingerprint image. A region is obtained for each of the one or more selected fingerprint feature points. The region is a representation of an area proximate a given fingerprint feature point. Each of the obtained regions is divided into a plurality of sub-regions. A histogram is generated for each of the plurality of sub-regions. For each of the one or more selected fingerprint feature points, the one or more generated histograms are combined into a concatenated histogram. The concatenated histogram is used for identification purposes.

Abstract: In one embodiment, the invention is a method and apparatus for repeatable facial distortion. One embodiment of a method for generating a secure facial image from an original facial image includes receiving the original facial image and a key, the key being associated with a subject depicted in the original facial image, and distorting the original facial image, in accordance with the key, to produce the secure facial image, where the distorting includes transforming at least one of: the albedo of the original facial image or the shape of the original facial image.

Abstract: Techniques for generating a distorted fingerprint representation for a given fingerprint image are provided. First, at least one fingerprint feature point from a given fingerprint image is selected. At least one representation of a region proximate to the selected fingerprint feature point is then generated. Next, the representation of the region proximate to the selected fingerprint feature point is distorted. The distortion comprises applying a random projection to the representation to generate a randomly projected representation of the region proximate to the selected fingerprint feature point. A distorted template is then formed, wherein the distorted template comprises the randomly projected representation of the region proximate to the selected fingerprint feature point.

Abstract: A system and method for processing fingerprints includes representing each minutiae in a fingerprint by determining quantized Gabor coefficients to represent texture content of the minutiae. A distance is computed between represented minutiae and stored minutiae. The minutiae matches are ranked based on the distance to identify the fingerprint.

Abstract: A system and method for processing fingerprints includes representing each minutiae in a fingerprint by determining quantized Gabor coefficients to represent texture content of the minutiae. A distance is computed between represented minutiae and stored minutiae. The minutiae matches are ranked based on the distance to identify the fingerprint.

Abstract: A method of doing business is disclosed that transforms a biometric used by a user in a transaction. The transformation creates a distorted biometric. The distorted biometric is used to identify the user to another party without requiring the user to provide actual physical or behavioral characteristics about himself to the other party.

Abstract: This invention uses a novel biometrics, called resultant fingerprints and palm-prints, for authentication. The novel biometrics are consecutive traditional print images where the subject physically changes the appearance of the print images by rotating or rotating and translating, or rotating, translating, and shearing the finger or palm. That is, it is a sequence of finger or palm-print images over a short interval of time where the images are modified according to the rotation or a combination of rotation and translation or a combination of rotation, translation, and shear. The rotational and translational and shear components of the motion in the sequence of print images are determined from the image-to-image flow. This flow is either computed from motion-compensation vectors of the sequence compressed in MPEG formats or directly from the uncompressed images.

Abstract: An integrated signal sensor with processing power to augment a challenge from server and compute the response is proposed to guarantee that the sensed signal is live and not stored. The sensor-processor computes the response to the augmented challenge based on the signal charactersitics of the sensed signal and then transmits both the signal and the response. The host or the server can verify the response to authenticate liveness of the input image/signal and reject it if the response is different. Areas of application include automated biometrics and remote medical imaging.

Abstract: Authentication methods are very important in several applications. Existing methods of authentication based on possessions or knowledge have several problems that can be overcome by using biometrics. Unfortunately biometrics-based authentication is unrevocable today and has many privacy concerns in users' minds. The proposed technique employs signal scrambling and morphing techniques to intentionally distort the original biometrics signal in a non-invertible fashion. If the security is compromised, the system can cancel a particular distortion and reacquire the signal with a new distortion function. This provides functionality as good as non-biometric authentication methods in terms of their power of revocation.

Abstract: Smart cards systems that are utilized in biometric authentication are slow in processing and have the cards themselves have the added disadvantage of being misplaced or lost. Moreover, storing biometric data (on a database) over a network poses security issues that in extreme instances can be compromised. Significant security can be achieved if the biometric templates are stored locally in a portable device. A user can use the portable device to either transmit wirelessly the stored biometric for authentication purposes, or a user can locally measure a biometric using the portable device and match it against a biometric which is also stored locally (in the portable device).

Abstract: This invention uses a novel biometrics, called resultant fingerprints and palm-prints, for authentication. The novel biometrics are consecutive traditional print images where the subject physically changes the appearance of the print images by rotating or rotating and translating, or rotating, translating, and shearing the finger or palm. That is, it is a sequence of finger or palm-print images over a short interval of time where the images are modified according to the rotation or a combination of rotation and translation or a combination of rotation, translation, and shear. The rotational and translational and shear components of the motion in the sequence of print images are determined from the image-to-image flow. This flow is either computed from motion-compensation vectors of the sequence compressed in MPEG formats or directly from the uncompressed images.

Abstract: A method of doing business is disclosed that transforms a biometric used by a user in a transaction. The transformation creates a distorted biometric. The distorted biometric is used to identify the user to another party without requiring the user to provide actual physical or behavioral characteristics about himself to the other party.

Abstract: This invention is a scaleable system to perform exact matching or similarity matching between a large store of reference temporal media sequences and a query target temporal media sequence. The system is not limited to finding exact matching media segments but also can find media segments that are similar. One kind of similarity between media segments is the similarity between a long commercial and a short commercial, where the short commercial is formed by sub-segments of the longer commercial. Another kind of similarity of two media segment is when they depict three-dimensional actions that are similar and imaged from similar viewpoints. Given a reference media segment, a multitude of features are computed in a consistent way from either predetermined or media content-dependent key intervals. These features are stored in segment index tables along with identifiers of the corresponding reference media segments.

Abstract: The invention is a system and method for constructing a rolled surface image from a set of partial surface images. A sequence of individual partial surface images is acquired as an object is progressively rolled across the surface of an imaging device. The imaging device is configured so that only that part of the object's surface which is in close proximity is imaged. To produce a complete rolled surface image, i.e. a composite image, the value of each pixel of the composite image is derived by performing a suitable pixel operation on the set of corresponding pixels in the input partial surface images. This is possible because each partial image is represented as a fixed size and each pixel in each of the partial images has a unique position in the partial image. The system can also directly produce a list of salient surface features. Localized features are extracted from each individual partial image whereas other specific attributes of each image are ignored.

Abstract: The invention is a system and method for deriving a single dimensional representation for a set of points e.g.,minutiae, in image of a two dimensional pattern of lines, e.g. a fingerprint, by creating a one dimensional (string) representation of one or more points (e.g., minutiae) and the respective attributes of each point therein. A landmark point is selected from the two dimensional image, preferably from the set of the points to be represented in single dimension. The relationships of each of the points with reference to the landmark determines a linear order for the points and the attributes associated with each point.

Abstract: The present system and apparatus use image processing to recognize object size with a scene. The system includes novel image processing apparatus and method 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.