IMAGE PROCESSING APPARATUS, IMAGE PROCESSING METHOD, AND PROGRAM

• US 20110096995A1
• Filed: 10/22/2010
• Published: 04/28/2011
• Est. Priority Date: 10/27/2009
• Status: Active Grant

• Current Assignee: Canon Kabushiki Kaisha (Canon Inc.)
• Original Assignee: Canon Kabushiki Kaisha (Canon Inc.)
• Inventors: Ito, Yoshinori
• Granted Patent: US 8,577,098 B2
• Time in Patent Office: Days
• US Class Current: 382/190
• CPC Class Codes: G06F 16/51 Indexing; Data structures therefor; Storage structures
• CPC Class Codes: G06F 16/5838 using colour
• CPC Class Codes: G06V 20/10 Terrestrial scenes scenes under surveillance with static cameras G06V20/52; scenes perceived from the exterior of a vehicle G06V20/56; scenes perceived from the interior of a vehicle G06V20/59

Abstract

An image processing apparatus comprising: a first detection unit adapted to detect a first subject from an object image; a first extraction unit adapted to extract a first feature amount for identifying an attribute of the first subject; a second extraction unit adapted to extract a second feature amount for detecting the second subject; a first storage unit adapted to store the first feature amount; and a second storage unit adapted to store the second feature amount, wherein when the first detection unit detects the first subject, the first extraction unit extracts the first feature amount and the first storage unit stores the amount, and when the first detection unit cannot detect the first subject, the second extraction unit extracts the second feature amount and the second storage unit stores the amount.

Claims

1. An image processing apparatus comprising:

a designation unit adapted to designate an object image to be registered;

a first detection unit adapted to detect a first subject from the designated object image;

a first extraction unit adapted to extract a first feature amount for identifying an attribute of the first subject;

a second extraction unit adapted to extract a second feature amount for detecting the second subject;

a first storage unit adapted to store the first feature amount; and

a second storage unit adapted to store the second feature amount,

wherein when said first detection unit detects the first subject, said first extraction unit extracts the first feature amount from the object image and said first storage unit stores the extracted first feature amount, and

when said first detection unit cannot detect the first subject, said second extraction unit extracts the second feature amount from the object image and said second storage unit stores the extracted second feature amount.

2. The apparatus according to claim 1, wherein the image processing apparatus further comprises a first identification unit adapted to identify an attribute of an object in an input image detected by said first detection unit based on the first feature amount stored in said first storage unit.

3. The apparatus according to claim 1, wherein the image processing apparatus further comprises a second detection unit adapted to detect the second subject in an input image based on the second feature amount stored in said second storage unit.

4. The apparatus according to claim 1, wherein when said first detection unit cannot detect the first subject in the object image designated by said designation unit, said second storage unit stores the second feature amount after a user confirms to store the second feature amount in said second storage unit.

5. The apparatus according to claim 1, wherein the image processing apparatus further comprises an input unit adapted to prompt a user to input a title indicating the attribute of the first subject when storing the first feature amount in said first storage unit.

6. The apparatus according to claim 2, wherein when said first identification unit identifies that the attribute of the object image designed by said designation unit does not match the first feature amount stored in said first storage unit, said first storage unit stores the feature amount which is extracted from the object image as a new first feature amount of a different first subject.

7. The apparatus according to claim 2, wherein when said first identification unit identifies that the attribute of the object image designed by said designation unit matches the first feature amount stored in said first storage unit, said first storage unit asks a user whether the feature amount extracted from the object image is to be stored as a new first feature amount.

8. The apparatus according to claim 1, wherein said designation unit designates the object image while an object to be registered is captured within a predetermined frame.

9. An image processing method comprising:

a designation step of designating an object image to be registered;

a first detection step of detecting a first subject from the designated object image;

a first extraction step of extracting a first feature amount for identifying an attribute of the first subject from the object image, when the first subject is detected in said first detection step;

a second extraction step of extracting a second feature amount for detecting the second subject from the object image, when the first subject cannot be detected in said first detection step;

a first storage step of storing the first feature amount in a first storage unit, when the first feature amount is extracted in said first extraction step; and

a second storage step of storing the second feature amount in a second storage unit, when the second feature amount is extracted in said second extraction step.

10. A computer-readable storage medium storing a program for causing a computer to execute an image processing method defined in claim 9.