IP Library Granted Patent US 7,609,892
Granted Patent B2
US 7,609,892 · App. 11/922,013 · Granted Oct 27, 2009

Image processing method, image processing system, and image processing program

View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 7,609,892
App. No.
11/922,013
Filed
Dec 11, 2007
Granted
Oct 27, 2009
Kind
B2
Examiner
DANG, DUY M
Art Unit
2624
USPC
382/190
Abstract

The process captures a plurality of images under a light source whose luminance varies over time, such as a fluorescent lamp, under such an imaging condition that a plurality of images that are different from one another in terms of light source conditions can be captured (S 11 ). The process detects a temporal luminance variation from the plurality of captured images (S 12 ), estimates a shadow area by using the temporal luminance variation (S 13 ), and performs an image process such as a process of synthesizing a linearized image or an image segmentation based on optical characteristics (S 14 ).

Claims (23)

1. An image processing method performed by a processor, comprising:

an imaging step of imaging a same object a plurality of times by means of an imaging device under a light source whose luminance varies over time under such an imaging condition that a plurality of images that are different from one another in terms of light source conditions can be imaged; and

an image processing step of performing an image process by using a plurality of images imaged in the imaging step,

wherein the image processing step includes:

a step of detecting a temporal luminance variation from the plurality of images;

a step of estimating a shadow area in the plurality of images by using the detected temporal luminance variation; and

a step of performing an image segmentation based on optical characteristics by using information of the estimated shadow area and the plurality of images.

2. The image processing method of claim 1 , wherein:

the light source is a light source whose luminance varies periodically; and

an exposure time that is sufficiently short with respect to a luminance variation cycle of the light source is set as the imaging condition.

3. The image processing method of claim 1 , wherein the light source is a fluorescent lamp, an LED or a display.

4. The image processing method of claim 1 , wherein the imaging condition is at least one of an exposure time, an imaging timing and an imaging cycle.

5. The image processing method of claim 1 , comprising:

a step of obtaining light source information of the light source; and

a step of determining the imaging condition based on the obtained light source information.

6. The image processing method of claim 5 , wherein the light source information is at least one of a luminance variation cycle, a luminance variation range and position information of the light source.

7. An image processing program residing on computer-readable memory being a program for instructing a computer to perform an image process, wherein the program instructs the computer to perform:

an imaging step of imaging a same object a plurality of times by means of an imaging device under a light source whose luminance varies over time under such an imaging condition that a plurality of images that are different from one another in terms of light source conditions can be imaged; and

an image processing step of performing an image process by using a plurality of images imaged in the imaging step,

wherein the image processing step includes:

a step of detecting a temporal luminance variation from the plurality of images;

a step of estimating a shadow area in the plurality of images by using the detected temporal luminance variation; and

a step of performing an image segmentation based on optical characteristics by using information of the estimated shadow area and the plurality of images.