Method and system of identifying a valid object in a background of an image using a gray level co-occurrence matrix of the image

• US 5,699,452 A
• Filed: 07/29/1994
• Issued: 12/16/1997
• Est. Priority Date: 09/27/1991
• Status: Expired due to Fees

• Current Assignee: E. I. du Pont de Nemours and Company (Corteva, Inc.)
• Original Assignee: E. I. du Pont de Nemours and Company (Corteva, Inc.)
• Inventors: Vaidyanathan, Akhileswar Ganesh
• Primary Examiner(s): Razavi, Michael T.
• Assistant Examiner(s): Patel, Jayanti K.
• Application Number:
  US08/283,134
• Time in Patent Office: 1,236 Days
• Field of Search: 382/168, 382/169, 382/170, 382/291, 382/173, 382/128, 382/171
• US Class Current: 382/168
• CPC Class Codes: G06T 11/40 Filling a planar surface by adding surface attributes, e.g. colour or texture
• CPC Class Codes: G06T 2207/30024 Cell structures in vitro; Tissue sections in vitro
• CPC Class Codes: G06T 2207/30128 Food products
• CPC Class Codes: G06T 7/0012 Biomedical image inspection
• CPC Class Codes: G06T 7/11 Region-based segmentation
• CPC Class Codes: G06T 7/136 involving thresholding
• CPC Class Codes: G06T 9/20 Contour coding, e.g. using detection of edges
• CPC Class Codes: G06V 10/46 Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features colour feature extraction G06V10/56
• CPC Class Codes: G06V 20/695 Preprocessing, e.g. image segmentation

Abstract

The present invention relates to an image analysis method and system for identifying objects in a background by generating a description, which in this case is a co-occurrence matrix, of the gray level space of the image by using an entropic kernel to recursively analyze the gray level space for candidate objects and validating the presence of valid objects by comparing the candidate object attribute values to a defined set of valid object attribute values contained in a driver. The present invention includes recursive, iterative and parallel processing methods. The methods may be used in a wide variety of industrial inspection techniques, including colony counting and the identification of discrete features in carpets and of pigment elements embedded in a polymer.

Claims

1. A method of identifying at least one valid object having at least one predetermined attribute value in a background, comprising the steps of:

(a) generating an image of the object and the background;

(b) generating a gray level co-occurrence matrix of the said image, the gray level co-occurrence matrix having an entropy function;

(c) entropically selecting a threshold gray level such that the entropy function of the co-occurrence matrix is maximized;

(d) searching the image using the entropically selected threshold gray level for at least one candidate object, wherein the candidate object has at least one candidate object attribute value; and

(e) validating the candidate objects having the valid object predetermined attribute values, thereby identifying the valid object.

2. The method as claimed in claim 1, wherein the selecting step includes the sub-steps of:

(i) sequentially partitioning the matrix at each gray level into a first, second, third and fourth quadrant,

(ii) computing the entropy function of the matrix, and

(iii) selecting a threshold gray level such that the entropy function of the matrix maximized.

3. The method as claimed in claim 2, wherein the entropy function of the matrix is defined as the sum of the entropy functions of the second and third quadrants of the co-occurrence matrix.

4. The method as claimed in claim 2, wherein the entropy function of the matrix is defined as the sum of the entropy functions of the first and fourth quadrants of the co-occurrence matrix.

5. A method of identifying at least one valid object having at least one predetermined attribute value in a background, comprising the steps of:

(a) generating an image of the object and the background;

(b) generating a gray level co-occurrence matrix representative of the entire image, the gray level co-occurrence matrix having an entropy function;

(c) generating a plurality of gray level quadrants of the image from the co-occurrence matrix, each gray level quadrant having a respective entropy function;

(d) automatically selecting a threshold gray level value for each gray level quadrant such that the entropy function of each quadrant is maximized;

(e) searching the image using the automatically selected threshold gray level value for each quadrant for at least one candidate object,

wherein the candidate object has at least one candidate object attribute value; and

(f) validating the candidate object having the valid object predetermined attribute value to identify the valid object.

6. A method of identifying at least one valid object in a background, wherein the valid object has at least one predetermined attribute defined by at least one predetermined attribute value, comprising the steps of:

(a) generating an image of an object and a background;

(b) generating a gray level co-occurrence matrix of the image, the gray level co-occurrence matrix having an entropy function;

(c) entropically selecting a threshold gray level value such that the entropy function of the co-occurrence matrix is maximized;

(d) searching the image using the entropically selected threshold gray level value for at least one candidate object, each candidate object having at least one candidate object attribute value;

(e) validating the candidate objects found in step (d) having a valid object predetermined attribute value to identify a valid object;

(f) partitioning the gray level co-occurrence matrix into a first through fourth quadrant, respectively, using the entropic threshold gray level value as defined by step (c) as an upper delimiter and a lower delimiter, wherein the first quadrant defines an upper matrix for a diagonal case, the second quadrant defines an upper matric for an off-diagonal case, the third quadrant defines a lower matrix for the diagonal case, and the fourth quadrant defines a lower matrix for the off-diagonal case; and

(g) recursively repeating steps (c)-(f) for each of the upper and lower matrices for the diagonal or the off-diagonal case, respectively, wherein the repetition of step (c) selects a next successive entropic threshold gray level, thereby recursively partitioning the gray level co-occurrence matrix until a predetermined minimum number of new valid objects is identified.

7. The method as claimed in claim 6, wherein selecting step (c) includes the sub-steps of:

(i) sequentially partitioning the matrix at each gray level into a first, a second, a third and a fourth quadrant,

(ii) computing the entropy function of the matrix, and

(iii) selecting an entropic threshold gray level such that the entropy function of the co-occurrence matrix is maximized.

8. The method as claimed in claim 7, wherein the entropy function of the co-occurrence matrix is defined as the sum of the entropy functions of the second and third quadrants of the co-occurrence matrix.

9. The method as claimed in claim 7, wherein the entropy function of the co-occurrence matrix is defined as the sum of the entropy functions of the first and fourth quadrants of the co-occurrence matrix.