39 results about "Automated fingerprint identification" patented technology

A method of identifying a donor of a fingerprint image exhibiting a pattern of minutiae. The method comprises deriving a donor index code and a donor match code associated with the donor fingerprint image. A database of records is accessed—each record being associated with an identity and indicative of a respective index code and a respective match code—in an attempt to identify at least one record for which the respective index code corresponds to the donor index code. Responsive to the attempt being successful, it is determined whether any of these “candidate” records includes a particular record for which the respective match code corresponds to the donor match code. Upon indeed determining that this is so for a particular record, an output is generated, such output being indicative of a conclusion that the donor of the fingerprint image has the identity associated with the particular record.

A method and system for performing automated biological identification. The system including a preprocessing module with a histogram transform for locally and globally enhancing biological data such as fingerprints. An enhancement module with a fast smoothing and enhancement function. A feature extraction module with a fingerprint oriented thinning function. A matching module with a resolution-enhanced Hough transform function for fingerprint registration and matching score function.

The present invention discloses a rapid fingerprint identification method based on the singular point topology structure, and the rapid fingerprint identification method can fast process and identifythe fingerprint images in the automated fingerprint identification system by using singular point topology structure in fingerprints. The present invention classifies the fingerprint database accordingto the classification property and position stability of the singular point in fingerprint images, and selects the most reliable singular point as a reference point to build the singular point topolo gy structure of fingerprints and a module to identify; the present invention firstly detects the authenticity of singular points in a fingerprint image, and then classifies the database according tothe relative position of singular points to build a topology structure adjacent to the singular point; and the topology structure can be used to build the fingerprint module to speed up the comparisonprocess of the fingerprints; the rapid matching of fingerprints in the automated fingerprint identification system is a difficulty of the fingerprint recognition technology; the rapid fingerprint identification method, on one hand, can guarantee the recognition performance, on the other hand, can significantly improve the recognition speed of the automated fingerprint identification system, and can widen the scope of application; moreover, the method reforms the prior system slightly.

The invention discloses a fingerprint image registration method based on global information. It mainly solves the problems of inaccurate registration and high time complexity in the existing fingerprint matching technology. The implementation steps are: 1. Input the input fingerprint image and the template fingerprint image, and calculate the direction field and frequency field of these two images; 2. Set the initial transformation registration parameters, and determine whether the fingerprint image registration can be performed. , then select six groups of new transformation registration parameters in the neighborhood of initial transformation registration parameters for fingerprint image registration; 3. Determine whether there is an optimal group of new transformation registration parameters among the six groups of new transformation registration parameters, if If it does not exist, use the initial transformation registration parameters as the final fingerprint image registration parameters, and end the registration; otherwise, use the best set of new transformation registration parameters as the initial transformation registration parameters, and return to step 2 until the registration ends. The invention can accurately register fingerprint images and can be used in an automatic fingerprint identification system.

The invention relates to a fingerprint identification method and a system thereof, relates to a fingerprint image enhancement method and discloses an image enhancement method in an automatic fingerprint identification technology. The method is characterized by: firstly, constructing a two-dimensional sine filter which has a consistent with a fingerprint; then, using a two-dimensional Gaussian function to carry out modulation on the two-dimensional sine filter so as to obtain a Gaussian modulation two-dimensional sine filter; and carrying out correction on the Gaussian modulation two-dimensional sine filter, constructing the filter which accords with an actual need of fingerprint image processing; using a frequency parameter and a direction parameter of each fingerprint image area to construct an appropriate enhancement template of the Gaussian modulation two-dimensional sine filter; finally carrying out convolution operation on the corresponding Gaussian modulation two-dimensional sine filter template and the corresponding fingerprint image area, carrying out enhancement processing on the fingerprint image, and carrying out normalization processing on an enhancement result so as to obtain the final enhancement fingerprint image.

This invention relates to an automatic fingerprint identification and sorting system and method, which divides the fingerprint into six kinds: arch, sharp arch, left rotation, right rotation and whirl and singular and is based on the number of the fingerprint singular points and surround ridge line direction. The method comprises the following steps: to divide the fingerprint images into front area and back area through the dividing program; to form a block field image to the print image in the front area; to determine the position and direction of the singular points by use of block direction field; to divide the print into six kinds according to the number and direction of the singular points and the pre-set rules.

The invention discloses a fingerprint image quality evaluation method based on main component analysis. The method comprises the following steps of: blocking an input fingerprint image; acquiring field pixel information of each pixel point in the image blocks, and forming a block sample matrix; acquiring a projection matrix and a characteristic value vector of the block sample matrix by a main component analyzing method; calculating characteristics for image block quality judgment from the projection matrix and the characteristic value vector; obtaining the local block quality of the image blocks by the multiplication rule; and obtaining the overall quality of the input fingerprint image through the combination of block Harris strength. The method is simple; a result is intuitive; the quality of the input fingerprint image can be accurately and quantitatively reflected by the method; and the high performance of automatic fingerprint identification technology is ensured by the method.

The invention belongs to the technical field of fingerprint registration point extraction, and discloses a fingerprint registration point extraction method based on a central singular point, which calculates the index value PI of all pixels in the singular point area 1 (i,j) and PI 2 (i,j), according to the index value, find the block where the central singular point appears, and take the geometric center of the block center as the registration point; if there is no central singular point, use the descending iteration method to find the convergence point of the ridge line, and use the convergent point As a registration point; find the initial point of iteration, find four equidistant points around the initial point, find the nearest ridge line of each point, and make a vertical line on the ridge line, get the intersection point of the vertical line, as the next iteration point ; If the Euclidean distance between the initial iteration point and the new iteration point is less than a certain threshold, the iteration ends, and the new iteration point is the reference point; otherwise, the new iteration point is used as the initial point to continue the iteration. The invention can quickly and accurately calculate the coordinates of the fingerprint registration point, and can be used in an automatic fingerprint identification system.