Method and apparatus for enhancing discrete pixel images
AssigneeGeneral Electric Company
InventorGopal B. Avinash
Life of this patent
Estimating the term…
Abstract
Pixel data representative of a discrete pixel image is processed to identify structures and non-structures in the image defined by the pixel data. The structures and non-structures are processed in different manners. The structures are identified by computing gradient information on each pixel and by comparing the gradient information to a gradient threshold, and by comparing gradient directions for adjacent pixels to one another. The edges defining the structures are binary rank order filtered. The structures are orientation smoothed and sharpened. The non-structures are homogenization smoothed and original texture is blended back into non-structural regions.
Claims24
A method for enhancing an image defined by a plurality of discrete pixels, the method comprising the steps of:
- (a) identifying a group of structural pixels representative of structures of interest and a group of non-structural pixels representative of non-structural regions in the image, the structural pixels being identified by determining gradient values for each pixel, identifying a gradient threshold value and identifying pixels having a desired relationship to the gradient threshold value, the gradient threshold value being identified by comparing gradient values for the pixels to a desired value and by comparing gradient directions for the pixels to one another, and by counting pixels based upon the comparisons;
- (b) orientation smoothing the structures of interest;
- (c) homogenization smoothing the non-structural regions;
- (d) orientation sharpening the structures of interest;
- and
- (e) blending textural data into the non-structural regions.
A method for enhancing a discrete pixel image, the method comprising the steps of:
- (a) identifying structural pixels representative of features of interest and non-structural pixels based upon gradient values for each pixel of the image, including identifying a gradient threshold value and comparing gradient values for each pixel to the threshold value to identify structural and non-structural pixels, the gradient threshold value being identified by comparing the gradient values to an initial threshold value, comparing a gradient direction for each pixel to gradient directions for adjacent pixels, and counting pixels satisfying desired relationships with the initial threshold value and adjacent pixel directions;
- (b) filtering the structural pixels in a first manner to enhance the features of interest by smoothing and sharpening the features;
- and
- (c) filtering the non-structural pixels in a second manner by smoothing and retexturing non-structural regions.
A system for processing a discrete pixel image, the system comprising:
- an acquisition unit for detecting signals representative of discrete pixels in an image;
- a signal processing circuit coupled to the acquisition unit, the signal processing circuit being configured to identify structural and non-structural pixels from the detected signals, to orientation smooth structures in the image defined by the structural pixels, to homogenization smooth non-structural regions in the image defined by the non-structural pixels, and to blend texture into the non-structural regions by computing a weighted average of filtered and unfiltered values for non-structural pixels;
- a memory circuit coupled to the signal processing circuit for storing values representative of pixel data filtered by the signal processing circuit;
- and
- an output device coupled to the signal processing circuit for producing an operator perceivable image based upon the pixel data filtered by the signal processing circuit.
A method for enhancing an image defined by a plurality of discrete pixels, the method comprising the steps of:
- (a) identifying a group of structural pixels representative of structures of interest and a group of non-structural pixels representative of non-structural regions in the image;
- (b) orientation smoothing the structures of interest;
- (c) homogenization smoothing the non-structural regions;
- (d) orientation sharpening the structures of interest;
- and
- (e) blending textural data into the non-structural regions including computing a weighted average of filtered and unfiltered values for non-structural pixels.
A system for processing a discrete pixel image, the system comprising:
- an acquisition unit for detecting signals representative of discrete pixels in an image;
- a signal processing circuit coupled to the acquisition unit, the signal processing circuit being configured to identify a group of structural pixels representative of structures of interest and a group of non-structural pixels representative of non-structural regions in the image, the structural pixels being identified by determining gradient values for each pixel, identifying a gradient threshold value, and identifying pixels having a desired relationship to the gradient threshold value, the gradient threshold value being identified by comparing gradient values for the pixels to a desired value and by comparing gradient directions for the pixels to one another, and by counting pixels based upon the comparisons, the signal processing circuit being further configured to perform orientation smoothing of the structures of interest, homogenization smoothing of the non-structural regions, orientation sharpening of the structures of interest, and blending of textural data into the non-structural regions;
- a memory circuit coupled to the signal processing circuit for storing values representative of pixel data filtered by the signal processing circuit;
- and
- an output device coupled to the signal processing circuit for producing an operator perceivable image based upon the pixel data filtered by the signal processing circuit.
A system for processing a discrete pixel image, the system comprising:
- an acquisition unit for detecting signals representative of discrete pixels in an image;
- a signal processing circuit coupled to the acquisition unit, the signal processing circuit being being configured to identify structural pixels representative of features of interest and non-structural pixels based upon gradient values for each pixel of the image, including identifying a gradient threshold value and comparing gradient values for each pixel to the threshold value to identify structural and non-structural pixels, the gradient threshold value being identified by comparing the gradient values to an initial threshold value, comparing a gradient direction for each pixel to gradient directions for adjacent pixels, and counting pixels satisfying desired relationships with the initial threshold value and adjacent pixel directions, the signal processing circuit being further configured to filter the structural pixels in a first manner to enhance the features of interest by smoothing and sharpening the features and to filter the non-structural pixels in a second manner by smoothing and retexturing non-structural regions;
- a memory circuit coupled to the signal processing circuit for storing values representative of pixel data filtered by the signal processing circuit;
- and
- an output device coupled to the signal processing circuit for producing an operator perceivable image based upon the pixel data filtered by the signal processing circuit.
Dependencies are inferred from the claim text.