IP Library › Granted Patent US 10,803,593
Granted Patent B2
US 10,803,593 · App. 15/706,950 · Granted Oct 13, 2020

Method and system for image compression

Inventor: Mohana Krishna Munukutla (Bangalore, IN)
Assignee: Siemens Healthcare GmbH
G06T7/181G06T7/11G06T7/13G06T7/174G06T9/00G06T2207/20112
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 10,803,593
App. No.
15/706,950
Granted
Oct 13, 2020
Kind
B2
Abstract

The disclosure relates to method and system for compressing an image. The method involves receiving an image of the one or more images. Further, at least one segmentation algorithm is applied on the image and dividing the image into a plurality segments. The method further includes comparing the plurality of segments of the image with a seed image, where seed images include a seed image identifier. Further, a seed image is associated with the segments of the image in case there is a match between the seed image and the plurality of segments. The method also includes storing the image as a residual image and a seed image along with one or more seed image identifiers. Further, the image may be reconstructed based on the residual image and one or more seed images associated with the image. Thereafter, the image may be displayed on a display unit.

Claims (63)

1. A method of compressing an image, the method comprising:

receiving an image of one or more images, wherein the image comprises pixel data;

applying at least one segmentation algorithm on the image for dividing the image into a plurality segments;

determining if there is at least one seed image;

when there is the at least one seed image, comparing the plurality of segments of the image with the at least one seed image;

associating the at least one seed image with the plurality of segments of the image in case there is a match between the at least one seed image and the plurality of segments;

generating at least one of a residual image and a seed image from the plurality of segments that do not match with the at least one seed image, wherein the generating comprises:

retaining a segment of the plurality of segments of the image as a residual image, wherein the residual image does not match with the at least one seed image; and

storing a segment of the plurality of segments of the image as a seed image, wherein the seed image is assigned a unique seed image identifier;

storing the image as the residual image along with the seed image identifier, wherein the seed image identifier links to the seed image; and

repeating the receiving, the applying, the comparing, the associating, the generating, and the storing for all images obtained subsequent to the image.

2. The method of claim 1 , further comprising:

receiving a request for the image;

retrieving at least one of a residual image and one or more seed images associated with the image;

reconstructing the image using the at least one of the residual image and the one or more seed images associated with the image,

wherein the one or more seed images are retrieved based on the seed image identifier;

displaying the image on a display device.

3. The method of claim 1 , wherein the segmentation algorithm comprises segmenting the image based on an edge detection algorithm, pixel values, a histogram value an imaging modality type, a body region, or any combination thereof.

4. The method of claim 1 , wherein the determining comprises analyzing an image database for seed images stored from earlier images.

5. The method of claim 1 , wherein the comparing comprises comparing features of the plurality of segments of the image with the at least one seed image based on a pixel value comparison, a histogram comparison, an application of a machine learning algorithm, or any combination thereof.

6. The method of claim 1 , wherein the associating comprises replacing pixel data of the plurality segments of the image with the seed image identifier, and

wherein the seed image identifier is an alphanumeric string.

7. The method of claim 1 , wherein the determining comprises searching at least one of a database and a medical imaging modality for at least one seed image, and

wherein the at least one seed image is generated by one or more medical diagnostic images generated before processing the image.

8. The method of claim 1 , wherein the image is a medical diagnostic image.

9. The method of claim 1 , wherein the image is obtained from at least one of an image repository and a medical imaging modality.

10. A computing device comprising:

one or more processors;

an image capture device;

a display; and

one or more memory units comprising:

an image compression module, wherein the image compression module comprises an image segmentation module configured to apply at least one segmentation algorithm to divide an image into a plurality of segments;

an image comparison module configured to determine if there is at least one seed image, and when there is the at least one seed image, compare the plurality of segments of the image with the at least one seed image;

an image association module configured to associate the at least one seed image with the plurality of segments in case there is a match between the at least one seed image and the plurality of segments;

an image generation module configured to generate at least one of a residual image and a seed image from the plurality of segments that do not match with the at least one seed image, wherein the image generation module is further configured to:

retain the plurality of segments as a residual image, wherein the residual image does not match with the at least one seed image; and

store the plurality of segments as seed images, wherein the seed images are assigned at least one unique seed image identifier; and

an image storage module configured to store the image as the residual image along with the at least one seed image identifier linking to the at least one seed image.

11. The computing device of claim 10 , wherein the image compression module comprises an image reconstruction module configured to:

receive a request for the image;

retrieve at least one of the residual image and the one or more seed images associated with the image;

reconstruct the image using the at least one of the residual image and the one or more seed images associated with the image; and

display the image on a display device.

12. The computing device of claim 10 , wherein the image comparison module is further configured for comparing features of the plurality of segments of the image with the at least one seed image based on a pixel value comparison, a histogram comparison, an application of a machine learning algorithm, or any combination thereof.

13. The computing device of claim 10 , wherein the image association module is further configured to replace pixel data of the one or more segments of the image with the seed image identifier, where the seed image identifier includes an alphanumeric string.

14. The computing device of claim 10 , wherein the computing device is communicatively coupled with an image server.

15. The computing device of claim 10 , wherein the computing device is a mobile computing device, a stationary computing device, or an imaging modality.

16. The computing device of claim 10 , wherein the image capture device is a medical imaging modality.

17. A system for compressing an image, the system comprising:

a processor communicatively coupled to an image server, one or more client devices, and one or more medical imaging modalities;

a memory unit coupled to the processor, wherein the memory unit comprises an image compression module having:

an image segmentation module configured to apply at least one segmentation algorithm to divide the image into a plurality of segments;

an image comparison module configured to determine if there is at least one seed image, and when there is the at least one seed image, compare the plurality of segments of the image with the at least one seed image;

an image association module configured to associate the at least one seed image with the plurality of segments in case there is a match between the at least one seed image and the plurality of segments;

an image generation module configured to generate at least one of a residual image and a seed image from the plurality of segments that do not match with the at least one seed image, wherein the image generation module is further configured to:

retain the plurality of segments as a residual image, wherein the residual image does not match with the at least one seed image; and

store the plurality of segments as seed images, wherein the seed images are assigned at least one unique seed image identifier; and

an image storage module configured to store the image as the residual image along with the at least one seed image identifier linking to the at least one seed image.

18. The system of claim 17 , wherein the image compression module further comprises an image reconstruction module configured to:

receive a request for the image;

retrieve the at least one of the residual image and the one or more seed images associated with the image;

reconstruct the image using the at least one of the residual image and the one or more seed images associated with the image; and

display the image on a display device.

Assignments (3)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Dec 20, 2023
From: SIEMENS HEALTHCARE GMBH
To: SIEMENS HEALTHINEERS AG
Reel/Frame 066267/0346 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 7, 2017
From: MUNUKUTLA, MOHANA KRISHNA
To: SIEMENS HEALTHCARE PRIVATE LTD.
Reel/Frame 044050/0452 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 7, 2017
From: SIEMENS HEALTHCARE PRIVATE LTD.
To: SIEMENS HEALTHCARE GMBH
Reel/Frame 044050/0490 →
Priority Claims (1)
IN 201631031831 · Sep 19, 2016 · national
Continuity (1)
Related Publication 20180082427A1 · Mar 22, 2018