Abstract: The method and apparatus of the present invention provide for automatic recognition of fingerprint images. In an acquisition mode, subsets of the feature points for a given fingerprint image are generated in a deterministic fashion. One or more of the subsets of feature points for the given fingerprint image is selected. For each selected subset, a key is generated that characterizes the fingerprint in the vicinity of the selected subset. A multi-map entry corresponding to the selected subset of feature points is stored and labeled with the corresponding key. In the recognition mode, a query fingerprint image is supplied to the system. The processing of the acquisition mode is repeated in order to generate a plurality of keys associated with a plurality of subsets of feature points of the query fingerprint image. For each key generated in the recognition mode, all entries in the multi-map that are associated with this key are retrieved.

Abstract: A reference storage process populates a data structure so that the data structure contains all of the molecular structures and/or rigid substructures in the database classified according to attributes of tuples. In a preferred embodiment, the tuples are derived from sites (e.g. atomic sites) of the molecular structures and the attributes can be derived from geometric (and other) information related to the tuples. The attributes are used to define indices in the data structure that are associated with invariant vector information (e.g. information about rotatable bond(s) in skewed local coordinate frames created from tuples). These representations are invariant with respect to the rotation and translation of molecular structures and/or the rotation of substructures about attached rotatable bond(s). Accordingly, the invariant vector information is classified in the data structure with the respective tuple attributes in locations determined by the index derived from the respective tuple.

Abstract: This method non sequentially compares a reference sequence of tokens to an original sequence of tokens to determine subsequences of tokens which exactly or similarly match. The method has a novel approach for creating a large number of indexes by partitioning strings of tokens into substrings, appending non contiguous substrings together to form tuples, and creating indexes from the tuples. Indexes are created in this manner for both the original and reference strings. Techniques are also provided to approximately or exactly locate the substrings which where used to create the tuples and indexes from the original sequence of tokens. Original and reference indexes are compared and matches are tracked. Higher numbers of matches result in higher scores (votes) in a table and indicate a stronger similarity between the sequences on the the original and reference strings. Using this method, the degree of similarity can also be determined.

Abstract: The invention provides automatic acquisition and recognition of complex visual shapes within images. During an acquisition phase, models are derived from interest points acquired from a target shape. The models are stored in and can be retrieved from a lookup table via high dimension indices. When an image is inputted, triplets of interest points in the image are used to compute local shape descriptors, which describe the geometry of local shapes in the image. In turn, triplets of local shape descriptors are used to compute high dimension indices. These indices are used for accessing the lookup table having the models. The models are used for the automatic recognition of target shapes.

Abstract: Geometric features in image data are extracted by correlation of local information contained in multiple neighborhoods or windows comprising the image. Features of interest are extracted from data contained in the neighborhoods. Nodes are created for each feature. Support values are assigned to each node as well as a list of neighborhoods containing the feature parameters. Inhibitory links are built between the nodes based upon the list of neighborhoods and the geometric properties of the feature. Competitive integration is performed until the surviving nodes are no longer connected by inhibitory links. The result is a complete segmentation of the image in terms of the features.