Method and apparatus for analyzing image structures
First Claim
1. A method for identifying structural image components in a discrete pixel image, the method comprising the steps of:
- (a) computing gradient values for each pixel of the image, including gradient magnitude and direction values;
(b) identifying a gradient threshold value by selecting an initial threshold value prior to identifying the pixels representative of structural edges, counting candidate pixels representative of structural edges, and identifying a final gradient threshold value based upon the number of pixels representative of structural edges;
(c) based at least in part on the final gradient threshold value and the gradient magnitude and direction values, identifying pixels representative of structural edges; and
(d) binary rank order filtering the structural edges to identify pixels representative of structural components in the image.
1 Assignment
0 Petitions
Accused Products
Abstract
Structures are identified in pixel data representative of a discrete pixel image and are differentiated from non-structures. The structures are identified by comparing gradient magnitudes with a selected gradient value and by comparing gradient directions of adjacent pixels. Pixels having desired relationships are counted and a focus parameter is applied to the resulting count. A final gradient threshold value is identified based upon the count and the focus parameter. The threshold value identifies structural pixels. Isolated adjacent regions may be eliminated from the structures. Edges defined by the structures are binary rank order filtered to arrive at the final structural definition. The structural and non-structural pixels may be further processed to enhance the image for subsequent display.
-
Citations
28 Claims
-
1. A method for identifying structural image components in a discrete pixel image, the method comprising the steps of:
-
(a) computing gradient values for each pixel of the image, including gradient magnitude and direction values;
(b) identifying a gradient threshold value by selecting an initial threshold value prior to identifying the pixels representative of structural edges, counting candidate pixels representative of structural edges, and identifying a final gradient threshold value based upon the number of pixels representative of structural edges;
(c) based at least in part on the final gradient threshold value and the gradient magnitude and direction values, identifying pixels representative of structural edges; and
(d) binary rank order filtering the structural edges to identify pixels representative of structural components in the image. - View Dependent Claims (2, 3, 4, 5, 6)
-
-
7. A method for identifying pixels in a discrete pixel image representative of features of interest, the method comprising the steps of:
-
(a) determining gradient magnitude and direction values for each pixel;
(b) generating a gradient histogram for the pixels;
(c) identifying a gradient threshold value from the gradient histogram and from the gradient magnitude and direction values for each pixel; and
(d) identifying pixels representative of features of interest from the gradient threshold value and the gradient histogram. - View Dependent Claims (8, 9, 10, 11, 12, 13, 14)
-
-
15. A method for identifying pixels of interest in a discrete pixel image, the method comprising the steps of:
-
(a) determining gradient magnitude and direction values for each pixel;
(b) identifying contiguous pixels of interest based upon the gradient magnitude and direction values; and
(c) eliminating from the pixels of interest regions of adjacent pixels including a number of pixels less than a desired minimum number. - View Dependent Claims (16, 17, 18, 19, 20, 21)
-
-
22. An apparatus for identifying features of interest in a discrete pixel image, the apparatus comprising:
-
an image sensing device for generating raw data representative of a plurality of discrete pixels in an image matrix;
a signal processing circuit coupled to the sensing device, the signal processing circuit being configured to determine gradient magnitude and direction values for each pixel, generate a gradient histogram for the pixels, identify a gradient threshold value from the gradient histogram and from the gradient magnitude and direction values, and identify pixels representative of features of interest from the gradient threshold value and the gradient histogram; and
a memory circuit coupled to the signal processing circuit and configured to receive and save values representative of the pixels of interest. - View Dependent Claims (23, 24, 25)
-
-
26. An imaging system comprising:
-
a sensing station for detecting signals representative of discrete pixels in a subject of interest and for generating digital values representative of the detected signals;
a memory circuit for storing a predetermined routine for processing the digital values;
a signal processing circuit coupled to the sensing station and to the memory circuit, the signal processing circuit being configured to execute the routine to identify and enhance features of interest based upon a gradient threshold value determined from gradient magnitude and direction values for each digital value; and
an output device for producing an operator perceivable image including features of interest identified and enhanced by the signal processing circuit. - View Dependent Claims (27, 28)
-
Specification