Object identification and inventory management

摘要

A method/apparatus for identifying an object based on a pattern of structural features located in a particular region wherein the pattern comprises at least one fingerprint feature. The region may be recognized and used to identify the object. A first feature vector (FV) may be extracted from a first image of the pattern and may be mapped to an object identifier. To authenticate the object, a second FV may be extracted from a second image of the same region. The FVs may be compared and difference(s) determined. A match correlation value (MCV) may be calculated based on the difference(s). The difference(s) may be dampened if associated with expected wear and tear reducing the impact of the difference(s) on the MCV. The differences may be enhanced if associated with changes that are not explainable as wear and tear increasing the impact of the difference(s) on the MCV.

主权项

1. A machine-implemented method comprising:
recognizing a structural feature of an object; selecting a region of the object based on the structural feature; provisioning a database coupled to a network for communications; capturing a first image of the selected region so as to form first image data, wherein the first image has sufficient resolution to show at least one fingerprint feature; processing the first image data to extract a first feature vector expressing the fingerprint feature, wherein the first feature vector comprises a first set of numeric values, each of the numeric values responsive to light intensity in a corresponding sub-region of the first image; and storing the first feature vector in the database in association with a unique identifier associated with the object; after said storing, performing a process with respect to an article, the process comprising:
selecting a region of an article, the selected region of the article corresponding to the selected region of the object;capturing a second image of the selected region of the article, so as to form second image data, wherein the second image has substantially the same resolution as the first image;processing the second image data to extract a second feature vector, wherein the second feature vector comprises a second set of numeric values, the second set of numeric values responsive to the same respective sub-regions of the second image as the first set of numeric values are to the first image;querying the database using the identifier of the object as an index to access the first feature vector;comparing the second feature vector to the stored first feature vector, by comparing the first set of numeric values to the second set of numeric values to determine difference values;responsive to the comparison, augmenting or modifying a difference between the first and second feature vectors, the augmenting or modifying comprising at least one of reducing at least one of said difference values or increasing at least one of said difference values;calculating a match correlation value responsive to the augmenting or modifying; andidentifying a match between the object and the article in the case that the match correlation value exceeds a predetermined threshold.