System and method for image comparison and retrieval by enhancing, defining, and parameterizing objects in images

• US 6,941,323 B1
• Filed: 08/09/1999
• Issued: 09/06/2005
• Est. Priority Date: 08/09/1999
• Status: Expired due to Fees

• Current Assignee: Almen Laboratories, Inc.
• Original Assignee: Almen Laboratories, Inc.
• Inventors: Galperin, Michael
• Primary Examiner(s): Homere, Jean R.
• Assistant Examiner(s): PHAM, KHANH B
• Application Number:
  US09/370,366
• Time in Patent Office: 2,220 Days
• Field of Search: 707/104.1, 707/3, 382/305, 382/260, 382/168, 382/128, 382/130, 382/132
• US Class Current: 1/1
• CPC Class Codes: G06F 16/532 Query formulation, e.g. graphical querying
• CPC Class Codes: G06F 16/583 using metadata automatically derived from the content
• CPC Class Codes: G06F 18/21 Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
• CPC Class Codes: G06T 2207/30004 Biomedical image processing
• CPC Class Codes: G06T 7/0012 Biomedical image inspection
• CPC Class Codes: G06V 10/70 using pattern recognition or machine learning optical pattern recognition or electronic computations therefor G06V10/88
• CPC Class Codes: G16H 30/20 for handling medical images, e.g. DICOM, HL7 or PACS
• CPC Class Codes: G16H 30/40 for processing medical images, e.g. editing
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems
• CPC Class Codes: Y10S 707/99933 Query processing, i.e. searching
• CPC Class Codes: Y10S 707/99936 Pattern matching access
• CPC Class Codes: Y10S 707/99945 Object-oriented database structure processing
• CPC Class Codes: Y10S 707/99948 Application of database or data structure, e.g. distributed, multimedia, or image

Abstract

An image comparison and retrieval system compares objects and object clusters, or images. User controlled or automatic filtering to enhance object features is performed, and object pixels are defined. An object characterization parameter is computed based on certain object pixel values that characterize one or more aspects of the defined object. Object characterization parameters are compared for objects in different images to produce a measure of object similarity in the same or different images. The query image may be substantially continuously displayed during the image filtering and object definition processes.

Claims

1. A method of retrieving one or more digital images or portions of digital images comprising:

providing a query image;

processing said query image with one or more filters so as to modify pixel values in said query image and to distinguish at least one set of filtered object pixels from background pixels in said query image, wherein said filters include at least one of a look-up table filter, a filter which sharpens small scale features within a distinguished object, and a shading correction filter, wherein a shape defined by said distinguished filtered object pixels depends on said filters, wherein intensity values of said filtered object pixels also depend on said filters, and wherein the visual characteristics of an object which are related to object characterization are enhanced by said filters;

calculating a single object characterization parameter using as at least one set of inputs either (1) the intensity values of substantially all and substantially only said filtered object pixels, (2) the relative position of at least some object pixels on the perimeter of said distinguished object, or (3) the total number of distinguished object pixels;

assigning an object characterization parameter set comprising said object characterization parameter to at least one set of said filtered object pixels in said query image;

comparing said object characterization parameter set with one or more additional object characterization parameter sets associated with sets of object pixels defined in images in an image database or with other sets of object pixels defined within said query image; and

selecting one or more sets of object pixels, clusters of sets of object pixels, or images in response to said comparing.

2. The method of claim 1, wherein said processing comprises filtering said filtered image pixel values with multiple additional filtering functions so as to produce subsequent sets of filtered image pixel values.

3. The method of claim 1, additionally comprising displaying said filtered image pixel values.

4. The method of claim 2, additionally comprising displaying said subsequent sets of filtered image pixel values.

5. The method of claim 1, wherein said processing comprises defining an edge around at least one of said one or more sets of object pixels.

6. The method of claim 1, additionally comprising processing all or a subset of images in said image database in a substantially identical manner to the processing performed on said query image.

7. The method of claim 1, wherein said object characterization parameter set is defined at least in part by filtered pixel brightness values within said one or more sets of object pixels.

8. The method of claim 1, wherein said object characterization parameter set comprises an ordered series of numeric parameters.

9. The method of claim 8, wherein at least a portion of said numeric parameters are representative of aspects of the visual appearance of said filtered set of object pixels to a user.

10. The method of claim 1, wherein said query image is provided to an Internet server over a communications link, and wherein said processing, assigning, and comparing are performed on said Internet server or other available Internet tools and capacities.

11. An image retrieval system comprising:

an image database comprising a plurality of images;

at least one query image stored in a memory;

a filter set receiving said query image and receiving said images from said database as inputs and configured to provide a filtered query image and filtered database images as outputs, wherein said filter set includes at least one of a look-up table filter, a filter which sharpens small scale features, and a shading correction filter;

a display configured to display under user control the query image both before and after filtering by said filter set, and also to display database images both before and after filtering by said filter set;

an object definition module in data communication with said filter receiving said filtered query image and said filtered database images as inputs, and configured to define sets of object pixels within said filtered query image and said filtered database images, and wherein the definition and intensity values of at least some of said object pixels depend on the filter set and wherein characterizing features within objects are enhanced by application of said filter set;

an object parameterization module configured to calculate a parameter set associated with at least one set of object pixels in said filtered query image and a parameter set associated with at least one set of object pixels in said filtered database images, said parameter sets each including at least one parameter calculated using as at least one set of inputs either (1) the intensity values of substantially all and substantially only said filtered object pixels, (2) the relative position of at least some object pixels on the perimeter of said distinguished object, or (3) the total number of distinguished object pixels; and

a parameter set comparison module receiving said parameter sets as inputs, and configured to compare the content of said parameter sets.

12. The image retrieval system of claim 11, wherein said parameter set comparison module is configured to calculate a similarity index from said parameter sets representative of content similarity between said query image and at least one image in said image database.

13. A method of analyzing digital images so as to verify a suspected biological, medical, chemical, physical or clinical condition of a patient comprising:

processing a first image of a portion of a first human body having a suspected clinical condition with a one or more filter functions so as to modify at least some pixel intensity values and so as to define at least one separated portion of said first image, wherein said separated portion comprises a first set of object pixels distinguished from background pixels, and wherein said first set of object pixels is associated with a physical structure in said first human body potentially related to said suspected biological, medical, chemical, physical or clinical condition;

parameterizing said separated portion of said first image to produce a corresponding parameter set associated with said separated portion of said first image, said parameter set including at least one parameter selected from area, perimeter, maximum diameter, minimum diameter, form factor, equivalent circular diameter, aspect ratio, optical density, integrated density, relief, and homogeneity;

processing a second image of a portion of a second human body having a known biological, medical, chemical, physical or clinical condition with substantially the same one or more filter functions so as to define at least one separated portion of said second image, wherein said separated portion comprises a second set of object pixels distinguished from background pixels, and wherein said second set of object pixels is associated with a physical structure in said second human body related to said known biological, medical, chemical, physical or clinical condition;

parameterizing said separated portion of said second image to produce a corresponding parameter set associated with said separated portion of said second image, said parameter set including at least one parameter selected from area, perimeter, maximum diameter, minimum diameter, form factor, equivalent circular diameter, aspect ratio, optical density, integrated density, relief, and homogeneity; and

comparing the content of a parameter set associated with at least one separated portion of said first image with the content of a parameter set associated with at least one separated portion of said second image so as to produce a measure of similarity between the structure in the first human body having the suspected biological, medical, chemical, physical or clinical condition and the structure in the second human body having a known biological, medical, chemical, physical or clinical condition.

14. The method of claim 13, wherein said comparing comprises calculating a similarity index using the content of said parameter sets.