IMAGE RECOGNIZING APPARATUS, IMAGE RECOGNIZING METHOD, AND PROGRAM

• US 20130064425A1
• Filed: 09/05/2012
• Published: 03/14/2013
• Est. Priority Date: 09/13/2011
• Status: Active Grant

• Current Assignee: Canon Kabushiki Kaisha (Canon Inc.)
• Original Assignee: Canon Kabushiki Kaisha (Canon Inc.)
• Inventors: Sagawa, Naotsugu, Yano, Kotaro
• Granted Patent: US 9,147,105 B2
• Time in Patent Office: Days
• US Class Current: 382/103
• CPC Class Codes: G06V 10/25 Determination of region of interest [ROI] or a volume of interest [VOI]
• CPC Class Codes: G06V 40/10 Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
• CPC Class Codes: G06V 40/16 Human faces, e.g. facial parts, sketches or expressions

Abstract

An image recognizing apparatus is equipped with: a detecting unit configured to detect, from an input image, a candidate area for a target of recognition, based on a likelihood of a partial area in the input image; an extracting unit configured to extract, from a plurality of candidate areas detected by the detecting unit, a set of the candidate areas which are in an overlapping relation; a classifying unit configured to classify an overlapping state of the set of the candidate areas; and a discriminating unit configured to discriminate whether or not the respective candidate areas are the target of recognition, based on the overlapping state of the set of the candidate areas and the respective likelihoods of the candidate areas.

Claims

1. An image recognizing apparatus comprising:

a detecting unit configured to detect, from an input image, a candidate area for a target of recognition, based on a likelihood of a partial area in the input image;

an extracting unit configured to extract, from a plurality of candidate areas detected by the detecting unit, a set of the candidate areas which are in an overlapping relation;

a classifying unit configured to classify an overlapping state of the set of the candidate areas; and

a discriminating unit configured to discriminate whether or not the respective candidate areas are the target of recognition, based on the overlapping state of the set of the candidate areas and the respective likelihoods of the candidate areas.

2. The image recognizing apparatus according to claim 1, wherein the discriminating unit discriminates whether or not the respective candidate areas are the target of recognition, by comparing a threshold determined according to the overlapping state of the set of the candidate areas and the likelihood of each candidate area with each other.

3. The image recognizing apparatus according to claim 2, wherein the overlapping state of the set of the candidate areas includes a positional relation of the mutual candidate areas in the set extracted by the extracting unit.

4. The image recognizing apparatus according to claim 3, wherein the positional relation includes at least one of directions of the mutual candidate areas, positional displacements of the mutual candidate areas, a ratio of widths of the mutual candidate areas, and a ratio of heights of the mutual candidate areas.

5. The image recognizing apparatus according to claim 1, wherein the extracting unit extracts, as the set of the candidate areas which are in the overlapping relation, the set of the candidate areas in which one of the candidate areas includes the other of the candidate areas.

6. An image recognizing method comprising:

detecting, from an input image, a candidate area for a target of recognition, based on a likelihood of a partial area in the input image;

extracting, from a plurality of detected candidate areas, a set of the candidate areas which are in an overlapping relation;

classifying an overlapping state of the set of the candidate areas; and

discriminating whether or not the respective candidate areas are the target of recognition, based on the overlapping state of the set of the candidate areas and the respective likelihoods of the candidate areas.

7. A computer-readable storage medium storing a program for causing a computer to perform the image recognizing method according to claim 6.