Automatic natural content detection in video information

• US 20040161152A1
• Filed: 12/09/2003
• Published: 08/19/2004
• Est. Priority Date: 06/15/2001
• Status: Abandoned Application

• Current Assignee: Koninklijke Philips Electronics N.V. (Koninklijke Philips N.V.)
• Original Assignee: Koninklijke Philips Electronics N.V. (Koninklijke Philips N.V.)
• Inventors: Marconi, Matteo, Carrai, Paola, Ferretti, Giulio
• Application Number:
  US10/480,126
• Publication Number:
  US 20040161152A1
• Time in Patent Office: Days
• US Class Current: 382/190
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 7/11 Region-based segmentation
• CPC Class Codes: G06V 30/413 Classification of content, e.g. text, photographs or tables

Abstract

A method of distinguishing areas of natural and synthetic content in video information represented by pixels arranged in a matrix of lines is disclosed. A luminance histogram (hist(L)) of pixel values for each line of the matrix is created. The distances (d) between each of the histogram values for each line are then determined. A line is classified as containing natural content if the majority of distances (d) is less than or equal to a predetermined value. Neighboring lines containing natural content are then grouped together to create groups of natural content. The process can then be repeated a predetermined number of times to more precisely define areas with natural content.

Claims

1. A method of distinguishing areas of natural and synthetic content in video information, comprising the steps of:

analyzing the video information;

grouping together neighboring sections of the video information which contain similar features found during the analysis;

designating groups of neighboring sections which have a first feature, as being natural content, and designating any remaining groups as being synthetic content.

2. The method according to claim 1, wherein the neighboring sections are cross-sections of rows and columns of the video information which contain similar features.

3. The method according to claim 1, wherein the analyzing step comprises the steps of:

determining luminance histogram values of pixels in a row, respectively a column; and

determining distances between non-zero histogram values within a histogram;

wherein the first feature is that a majority of the distances are less than a predetermined threshold.

4. The method according to claim 3, wherein the predetermined threshold is equal to two.

5. The method according to claim 1, further comprising the step of:

reanalyzing groups which likely contain natural content a predetermined number of times to more clearly define boundaries of the groups.

6. The method according to claim 5, wherein the boundaries of a group are defined by row and column coordinates.

7. The method according to claim 5, wherein the predetermined number of times is equal to three.

8. The method according to claim 1 wherein the information is represented by pixels in a matrix of lines of rows and columns and the analyzing comprises:

(a) creating a luminance histogram of pixel luminance values for each line of the matrix;

(b) determining distances between consecutive luminance histogram values for each line;

(c) calculating a distance probability function for each line from the determined distances; and

the first feature is that the distance probability has a maximum below a predetermined distance value.

9. The method according to claim 8, wherein the classification rule is:

10. A device for distinguishing areas of natural and synthetic content in video information, comprising:

means for analyzing the video information

means for grouping together neighboring sections of the video information which contain similar features found during the analysis;

means for designating groups of neighboring sections which have a first feature as being natural content, and designating any remaining group as being synthetic content.

11. An apparatus for distinguishing areas of natural and synthetic content in video information represented by pixels arranged in a matrix of lines, comprising:

means for creating a luminance histogram of pixel values for each line of the matrix;

means for determining the distances between each of the histogram values for each line;

means for calculating a distance probability function for each line from said determined distances;

means for classifying a line as containing natural content if the distance probability function has a maximum below a predetermined distance value; and

means for grouping together neighboring lines containing natural content to create clusters of natural content.