Method for identifying color in machine and computer vision applications

• US 8,064,691 B2
• Filed: 04/22/2008
• Issued: 11/22/2011
• Est. Priority Date: 05/15/2007
• Status: Expired due to Fees

• Current Assignee: Vision Interface Technologies, LLC
• Original Assignee: Creative LifeStyles, Inc., Vision Interface Technologies, LLC
• Inventors: Meyer, Frank, Smith, Peter, Tekkanat, Bora
• Primary Examiner(s): BALI, VIKKRAM
• Application Number:
  US12/107,092
• Publication Number:
  US 20080285848A1
• Time in Patent Office: 1,309 Days
• Field of Search: 382/133, 382/162, 382164-167, 382/172, 382/190, 382/224, 382260-264, 382276-277, 358/1.13, 358/1.9, 358/3.02, 358502-505, 358/515, 358/518, 358/520, 358/523, 358/525, 358/530, 348/223.1, 348/528, 348/645, 348/E9.037, 345/589, 345/591, 345600-604
• US Class Current: 382/165
• CPC Class Codes: G01J 3/462 Computing operations in or between colour spaces; Colour management systems
• CPC Class Codes: G01J 3/465 taking into account the colour perception of the eye; using tristimulus detection
• CPC Class Codes: G06T 2207/10024 Color image
• CPC Class Codes: G06T 2207/30176 Document
• CPC Class Codes: G06T 7/11 Region-based segmentation
• CPC Class Codes: G06T 7/90 Determination of colour characteristics
• CPC Class Codes: G06V 10/56 relating to colour

Abstract

A method for identifying color in a target creates a ratio color space by determining the largest color component value of each pixel in an image and creating a ratio of all of the color component value with the largest component value for each pixel. The ratio for the color component of each pixel undergoes a threshold test to identify each color component as a rich shade or a fade shade. The ratio space color components are converted to a black and white image. Color information of adjacent pixels are clumped together to form blobs of the same color. The blobs are filtered by shape, color, location, or orientation and sorted to find targets that consist of a predefined pattern with the desired characteristics.

Claims

1. A method of identifying color comprising the steps of:

using at least one processor to perform the steps of;

defining a ratio color space including determining the largest color component value for each pixel in an image; and

dividing all of the color component values of each pixel by the largest color component value of each pixel.

2. The method of claim 1 further comprising the step of developing a filter for use with a color space including the step of:

creating a threshold black and white image for one color of interest in each pixel of an image;

setting the threshold so that pale shades of the color of interest are separated from rich shades of the color of interest; and

repeating the steps for each color component in each pixel.

3. The method of claim 2 further comprising the steps of:

if any color component for each pixel of the images is above or below the threshold, setting all three color components for each pixel to black; and

if all color components of each pixel of the image matches the threshold, setting all three color components for each pixel to white.

4. The method of claim 1 further comprising the step of:

performing a threshold test on the ratio of space values of each pixel.

5. The method of claim 4 further comprising the steps of:

if any color component for each pixel of the images is above or below the threshold, setting all three color components for each pixel to black; and

if all color components of each pixel of the image matches the threshold, setting all three color components to white.

6. The method of claim 4 further comprising the step of:

converting the color information for each pixel, in ratio space values, to achromatic color information.

7. The method of claim 6 further comprising the steps of:

reducing the color information of a target image into black and white, with black representing color information that passed the threshold test as a rich shade of a color of interest and white representing the color information that failed the threshold test as a fade shade of a color of interest.

8. The method of claim 6 wherein the converting step further comprises:

employing a scaled parameter for each primary component of a color of interest.

9. The method of claim 8 wherein the step of employing a scaled parameter further comprises the step of:

setting the scale parameter to a negative large value for primary components for the color of interest.

10. The method of claim 9 wherein the converting step further comprises the step of:

solving a distance equation in terms of ratio color components for each pixel of the target according to;

Dist=POS(Sr*(r−

Tr))+POS(Sg*(g−

Tg))+POS(Sb*(b−

Tb))

where Sr, Sg, and Sb are scale parameters for the primary color component values r,g and b, Tr,Tg and Tb are threshold values for each of the color components r,g and b; and

POS (q)=0 if q is less than or equal to 0, POS (q)=q.

11. The method of claim 1 wherein color component values are included in RGB color space.

12. A robust method for rapidly finding the location of a color target within an image, the method comprising one or more of the steps of:

using at least one processor to perform the steps of;

as a one time step prior to processing a set of images, defining a color ratio space and creating a corresponding look-up-table for each primary color and secondary color used in a target;

capturing an image and subtracting from each pixel in the image the bias of each camera color component;

applying the look-up-table to each pixel in the image for each primary and each secondary color used in the target;

clumping together the adjacent color information of adjacent pixels to form blobs of the same color;

filtering the blobs of the same color by at least one of shape, size, location and orientation;

sorting all of the filtered blobs to find targets that have of a predefined pattern formed of a set of different colored blobs with at least one of a specific size and a specific shape at relative locations and orientations to each other;

tracking a plurality of targets to determine one of the absolute and the relative location and to determine if any changes occurred in one of a sequence of images and compared to an ideal image; and

using the changes of interest introduced to the field of view as a triggering mechanism to perform one of running macros and applications and initiating interaction between the user and the processor.

13. A method for identifying color information of a target image in a field of view of a camera on a pixel by pixel basis, the method comprising the steps of:

using at least one processor to perform the steps of;

receiving the color information of camera output in three color component values for each pixel of the target image;

defining a ratio color space by determining the largest value of the three color component values and dividing the three components value by the largest value for each pixel;

defining the components of the ratio space such that the largest component value is always 1.0 and the other two components are any of 0, 1.0, and a value between 0 and 1.0;

putting the ratio space values of each pixel to a threshold test;

identifying the color information of each pixel as one of rich shade of the color of interest if it passes the threshold test and as a fade shade of the color of interest if it fails the threshold test;

filtering the color information of each pixel into a binary black and white outputs, with black representing color information that passed the threshold test as a rich shade of a color of interest and white representing color information that failed the threshold test as a fade shade of a color;

clumping together the black outputs into black blobs for each color of interest in a white matrix of the target image;

sorting the black blobs of the same color by at least one of shape, size, location and orientation as targets and generating a plurality of distinct black and white outputs of the target image for each colored of red, green, blue, yellow, cyan, and magenta; and

identifying the information targets may carry with respect to each other at least one of color, shape, size, location and orientation.

14. A method of identifying color in a color space comprising the steps of:

using at least one processor to perform the steps of;

determining the largest color component for each of a plurality of pixels of an image;

subtracting each color component value in each pixel from the largest color component value; and

normalizing the resulting values.

15. The method of claim 14 wherein the normalizing step further comprises the step of:

multiplying each color component value by a scale factor.

16. The method of claim 14 wherein each color component value is included in RGB color space.