Image recognition/reproduction method and apparatus

• US 20030044073A1
• Filed: 10/07/2002
• Published: 03/06/2003
• Est. Priority Date: 02/02/1994
• Status: Active Grant

• Current Assignee: Katsumi Iijima, Masakazu Matsugu
• Original Assignee: Katsumi Iijima, Masakazu Matsugu
• Inventors: Matsugu, Masakazu, Iijima, Katsumi
• Granted Patent: US 6,907,140 B2
• Time in Patent Office: Days
• US Class Current: 382/195
• CPC Class Codes: G06T 11/60 Editing figures and text; Combining figures or text
• CPC Class Codes: G06V 10/44 Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
• CPC Class Codes: G06V 40/168 Feature extraction; Face representation

Abstract

An image recognition/reproduction method includes an extraction step of extracting local feature elements of an image, and a selection step of selecting a pair composed of a prescribed local feature element and position information indicative thereof, this pair being such that the distance between a pair composed of a prescribed local feature element and position information indicative thereof and a pair composed of a local feature element extracted at the extraction step and position information indicative thereof is less than a prescribed distance.

Claims

1. An image recognition method comprising:

an extraction step of extracting local feature elements in an input image;

a conversion step of assembling the local feature elements extracted at said extraction step and generating array data from the local feature elements on the basis of a predetermined lattice pattern; and

a matching step of estimating a resemblance between the local feature elements array data and a reference plurality of local feature elements array data stored in a memory by computing a differential value and selecting model array data for which the differential value is less than a predetermined threshold value,

wherein said conversion step includes the steps of;

generating a pair composed of a prescribed local feature element and position information indicative thereof in which the pair composed of a prescribed local feature element and position information indicative thereof is scaled at scaling ratios corresponding to respective ones of the resolutions; and

selecting a pair composed of a scaled prescribed local feature element and position information indicative thereof, this pair being such that the distance between a pair composed of the scaled prescribed local feature element and position information indicative thereof and a pair composed of a local feature element, whose resolution corresponds to the scaling ratio, extracted at said extraction step and position information indicative thereof is less than a prescribed distance.