Method and apparatus for determining image similarity and position
May 15, 2017. Estimated Expiration Date is calculated based on simple USPTO term provisions. It does not account for terminal disclaimers, term adjustments, failure to pay maintenance fees, or other factors which might affect the term of a patent.Patent ReferencesMeans and method of processing optical image edge data Image recognition system Method and apparatus for detection of parallel edges in image processing Image forming apparatus with edge smoothing Method and device for dividing and drawing polygons Image compression technique Image inspection/recognition method, method of generating reference data for use therein, and apparatuses therefor Method and apparatus for detecting non-uniformities in reflective surafaces Method and apparatus for processing images with symbols with dense edges Object edge point filtering system for machine vision InventorsAssigneeApplicationNo. 856598 filed on 05/15/1997US Classes:382/219, Determining both similarities and differences382/151, Alignment, registration, or position determination382/220Calculating weighted similarity or difference (e.g., don`t-care areas)ExaminersPrimary: Mehta, Bhavesh M.Assistant: Patel, Kiran Attorney, Agent or FirmInternational ClassG06K 009/68Foreign Application Priority Data1996-05-15 JPAbstractAn apparatus for determining a similarity between model image and inputted image, which is robust even if the background of said inputted image is partly changed. The similarity is calculated from an edge direction of an inputted image, an edge direction of a model image and a weight related to the model image. The calculating steps used are (1) calculating an edge direction difference between an inputted model image and a model image, (2) calculating weights related to model image, (3) multiplying edge directions and weights, (4) calculating a sum of the multiplication, (5) calculating a sum of the weights, and (6) calculating a similarity by dividing the sum of the multiplication by the sum of the weights.Field of SearchDetermining both similarities and differencesCalculating weighted similarity or difference (e.g., don`t-care areas) Contour or chain coding (e.g., Bezier) Alignment, registration, or position determination Pattern boundary and edge measurements Comparator Detecting alignment marks Directional codes and vectors (e.g., Freeman chains, compasslike codes) Point features (e.g., spatial coordinate descriptors) Global features (e.g., measurements on image as a whole, such as area, projections, etc.) Template matching (e.g., specific devices that determine the best match) Edge or contour enhancement | |
