Image processing apparatus, image processing method and program

• US 8,369,621 B2
• Filed: 08/21/2009
• Issued: 02/05/2013
• Est. Priority Date: 08/26/2008
• Status: Expired due to Fees

• Current Assignee: Sony Corporation (Sony Group Corp.)
• Original Assignee: Sony Corporation (Sony Group Corp.)
• Inventors: Nomura, Yoshikuni
• Primary Examiner(s): Park, Chan S
• Assistant Examiner(s): PERLMAN, DAVID S
• Application Number:
  US12/545,389
• Publication Number:
  US 20100054611A1
• Time in Patent Office: 1,264 Days
• Field of Search: 382190-201
• US Class Current: 382/190
• CPC Class Codes: G06V 10/50 by performing operations within image blocks; by using histograms, e.g. histogram of oriented gradients [HoG]; by summing image-intensity values; Projection analysis
• CPC Class Codes: G06V 10/758 Involving statistics of pixels or of feature values, e.g. histogram matching

Abstract

An image processing apparatus includes: a first distribution calculation unit calculating a distribution of luminance gradient vectors in a first local area that includes a feature point on an image; a second distribution calculation unit calculating distributions of the luminance gradient vectors in second local areas close to the feature point on the image; a selection unit comparing the distribution of the luminance gradient vectors of the first local area with the distributions of the luminance gradient vectors of the second local areas to select the most different distribution of the luminance gradient vectors of the second local area; and a feature descriptor calculation unit calculating a feature descriptor at the feature point on the basis of the distribution of the luminance gradient vectors of the first local area and the distribution of the luminance gradient vectors of the second local area selected by the selection unit.

Claims

1. An image processing apparatus comprising:

first distribution calculation means that calculates a distribution of luminance gradient vectors in a first local area that includes a feature point on an image;

second distribution calculation means that calculates distributions of the luminance gradient vectors in second local areas close to the feature point on the image;

selection means that compares the distribution of the luminance gradient vectors of the first local area with the distributions of the luminance gradient vectors of the second local areas to select the distribution of the luminance gradient vectors of the second local area of which the distribution is most different from the distribution of the luminance gradient vectors of the first local area from among the distributions of the luminance gradient vectors of the plurality of second local areas; and

feature descriptor calculation means that calculates a feature descriptor at the feature point on the basis of the distribution of the luminance gradient vectors of the first local area and the distribution of the luminance gradient vectors of the second local area selected by the selection means.

2. The image processing apparatus according to claim 1, wherein respective center positions of the plurality of second local areas are located on a circumference of a circle of which a center is the feature point.

3. The image processing apparatus according to claim 2, wherein a plurality of the respective center positions equally divides the circumference.

4. The image processing apparatus according to claim 1, wherein

a luminance gradient histogram is calculated as a distribution of the luminance gradient vectors to indicate a frequency, which is calculated for each direction of the luminance gradient vector and at which the luminance gradient vector having that direction appears, and

the selection means calculates a similarity of the luminance gradient histogram of each second local area with respect to the luminance gradient histogram of the first local area, and selects the luminance gradient histogram of the second local area, having the lowest degree of similarity indicated by the similarity from among the luminance gradient histograms of the plurality of second local areas.

5. An image processing method for an image processing apparatus that includes

first distribution calculation means that calculates a distribution of luminance gradient vectors in a first local area that includes a feature point on an image;

second distribution calculation means that calculates distributions of the luminance gradient vectors in second local areas close to the feature point on the image;

selection means that compares the distribution of the luminance gradient vectors of the first local area with the distributions of the luminance gradient vectors of the second local areas to select the distribution of the luminance gradient vectors of the second local area of which the distribution is most different from the distribution of the luminance gradient vectors of the first local area from among the distributions of the luminance gradient vectors of the plurality of second local areas; and

feature descriptor calculation means that calculates a feature descriptor at the feature point on the basis of the distribution of the luminance gradient vectors of the first local area and the distribution of the luminance gradient vectors of the second local area selected by the selection means, the image processing method comprising the steps of;

calculating a distribution of the luminance gradient vectors of the first local area using the image by the first distribution calculation means;

calculating distributions of the luminance gradient vectors of the second local areas using the image by the second distribution calculation means;

selecting the distribution of the luminance gradient vectors of the second local area, of which the distribution is most different from the distribution of the luminance gradient vectors of the first local area by the selection means; and

calculating a feature descriptor at the feature point using the feature descriptor calculation means.

6. A non-transitory computer readable storage medium having stored thereon a program for causing a computer to execute a process comprising the steps of:

calculating a distribution of luminance gradient vectors in a first local area that includes a feature point on an image;

calculating distributions of the luminance gradient vectors in second local areas close to the feature point on the image;

comparing the distribution of the luminance gradient vectors of the first local area with the distributions of the luminance gradient vectors of the second local areas to select the distribution of the luminance gradient vectors of the second local area of which the distribution is most different from the distribution of the luminance gradient vectors of the first local area from among the distributions of the luminance gradient vectors of the plurality of second local areas; and

calculating a feature descriptor at the feature point on the basis of the distribution of the luminance gradient vectors of the first local area and the distribution of the luminance gradient vectors of the selected second local area.

7. An image processing apparatus comprising:

a first distribution calculation unit that calculates a distribution of luminance gradient vectors in a first local area that includes a feature point on an image;

a second distribution calculation unit that calculates distributions of the luminance gradient vectors in second local areas close to the feature point on the image;

a selection unit that compares the distribution of the luminance gradient vectors of the first local area with the distributions of the luminance gradient vectors of the second local areas to select the distribution of the luminance gradient vectors of the second local area of which the distribution is most different from the distribution of the luminance gradient vectors of the first local area from among the distributions of the luminance gradient vectors of the plurality of second local areas; and

a feature descriptor calculation unit that calculates a feature descriptor at the feature point on the basis of the distribution of the luminance gradient vectors of the first local area and the distribution of the luminance gradient vectors of the second local area selected by the selection unit.