System for feature detection for low contrast images

• US 8,971,632 B2
• Filed: 08/19/2010
• Issued: 03/03/2015
• Est. Priority Date: 08/19/2010
• Status: Expired due to Fees

• Current Assignee: Sharp Kabushiki Kaisha (Hon Hai Precision Industry Co., Ltd.)
• Original Assignee: Sharp Laboratories of America Incorporated (Hon Hai Precision Industry Co., Ltd.)
• Inventors: Yanase, Masakazu, Yuan, Chang, Xu, Xinyu
• Primary Examiner(s): Carter, Aaron W
• Application Number:
  US12/859,637
• Publication Number:
  US 20120045135A1
• Time in Patent Office: 1,657 Days
• Field of Search: 382/190, 382/199, 382/205, 382/228
• US Class Current: 382/190
• CPC Class Codes: G06V 10/28 Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
• 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

Abstract

A system for the identification of feature points in low contrast images.

Claims

1. A method for identifying feature points comprising:

(a) receiving an image;

(b) calculating a feature measure associated with a feature point for a plurality of pixels of said image, said feature point indicative of the content depicted in said image and used to automatically detect said content from among a plurality of images;

(c) calculating a statistical measure with respect to one of said plurality of pixels;

(d) based upon said statistical measure determining a threshold;

(e) determining automatically, without user input, whether said one of said plurality of pixels is a said feature point using said threshold and said feature measure;

(f) wherein said threshold is set to a fixed value if said statistical measure falls below a second threshold.

3. The method of claim 1 wherein said threshold is set to a second fixed value if said statistical measure exceeds a third threshold.

4. The method of claim 3 wherein said threshold varies between said fixed value and said second fixed value.

2. A method for identifying feature points comprising:

(a) receiving an image;

(b) calculating a feature measure associated with a feature point for a plurality of pixels of said image, said feature point indicative of the content depicted in said image and used to automatically detect said content from among a plurality of images;

(c) calculating a statistical measure with respect to one of said plurality of pixels;

(d) based upon said statistical measure determining a threshold;

(e) determining automatically, without user input, whether said one of said plurality of pixels is a said feature point using said threshold and said feature measure;

(f) wherein said threshold is set to a fixed value if said statistical measure exceeds a second threshold.

5. A method for identifying feature points comprising:

(a) receiving an image;

(b) providing a feature measure indicative of a feature point for a plurality of pixels of said image;

(c) calculating a statistical measure with respect to one of said plurality of pixels;

(d) based upon said statistical measure determining a threshold;

(e) determining automatically, without user input, whether said one of said plurality of pixels is a said feature point using said threshold and said feature measure wherein said threshold is set to a fixed value when either;

(i) said statistical measure falls below a second threshold;

or (ii) said statistical measure exceeds a third threshold.

6. The method of claim 5 wherein said statistical measure is a standard deviation.

7. The method of claim 5 wherein said statistical measure is a variance.

8. The method of claim 5 wherein said determining is further based upon whether said one of said plurality of pixels is a maximum in a region of said image.