Independently processing plurality of regions of interest

Patent metadata

Field	Value
Publication number	US-11023762-B2
Application number	US-201716323561-A
Country	US
Kind code	B2
Filing date	Aug 11, 2017
Priority date	Aug 12, 2016
Publication date	Jun 1, 2021
Grant date	Jun 1, 2021

Abstract

In some examples, a method includes determining, by a computing device, a plurality of regions of interest of an image for independently processing relative to a plane of interest; determining, by the computing device and for respective regions of interest of the plurality of regions of interest, a distance from objects within the respective regions of interest to the plane of interest; and processing, by the computing device and independently for the respective regions of interest, the respective regions of interest of the image based on the determined distance from the objects to the plane of interest.

First claim

What is claimed is:

1. A method comprising:
receiving, by a computing device, an image captured by a camera or via a platen of an apparatus that includes the computing device;
determining, by a computing device, a plurality of regions of interest within the captured image; and
processing, by the computing device, the captured image relative to a plane of interest that is defined by at least one of an image plane of the camera or by the platen of the apparatus that includes the computing device, by:
determining, by the computing device, for each respective region of interest of the plurality of regions of interest, a respective distance from one or more objects within the respective region of interest to the plane of interest; and
processing, by the computing device, each respective region of interest independently of any other regions of interest included in the plurality of regions of interest, based on the respective distance from the one or more objects of each respective region of interest to the plane of interest.

2. The method of claim 1 , further comprising:
forming, by the computing device, prior to determining the plurality of regions of interest within the captured image, a distance map that includes respective distances for one or more portions of the captured image, the respective distances being based on distances from objects within the one or more portions of the captured image to the plane of interest,
wherein determining the plurality of regions of interest comprises determining the plurality of regions of interest using the respective distances included in the distance map, and
wherein determining the distances from the objects to the plane of interest comprises determining the distances from the objects to the plane of interest based on the respective distances included in the distance map.

3. The method of claim 2 , wherein forming the distance map comprises applying a segmentation algorithm to at least a portion of the captured image to identify the one or more portions of the captured image.

4. The method of claim 2 , wherein forming the distance map comprises identifying the one or more portions of the captured image as block-sized areas of the captured image.

5. The method of claim 2 , wherein forming the distance map comprises determining, by the computing device, for respective sub-portions of the one or more portions of the captured image, an average distance to the plane of interest for respective areas of the captured image defined by the respective sub-portions.

6. The method of claim 2 , wherein forming the distance map comprises:
determining, by the computing device, respective distances between each respective area of a plurality of areas of the captured image and the plane of interest;
merging, by the computing device, at least two respective areas of the plurality of areas of the captured image to form a first portion of the one or more portions of the captured image; and
determining a representative distance for the first portion with respect to the plane of interest.

7. The method of claim 6 , wherein determining the representative distance comprises applying, by the computing device, a smoothing factor to the at least two areas merged to form the first portion.

8. The method of claim 2 , wherein the captured image is a first captured image and wherein the camera is a first camera, the method further comprising:
receiving, by the computing device, from a second camera, a second captured image; and
determining, by the computing device, prior to forming the distance map, a disparity map that represents a disparity between a first perspective of the one or more objects as represented in the first captured image and a second perspective of the one or more objects as represented in the second captured image,
wherein forming the distance map comprises forming the distance map based on the disparity between the first perspective and the second perspective as represented in the disparity map.

9. The method of claim 8 , wherein determining the disparity comprises determining, by the computing device, the disparity in a pixel space.

10. The method of claim 8 , wherein determining the disparity map comprises:
identifying, by the computing device, one or more areas of the plurality of areas of the first captured image with respect to which to determine the disparity based on similarity between the first perspective of the one or more areas as represented in the first captured image and the second perspective of the one or more areas as represented in the second captured image; and
determining respective disparities with respect to the first perspective of the one or more areas as represented in the first captured image and the second perspective of the one or more areas as represented in the second captured image.

11. The method of claim 10 , wherein identifying the one or more areas of the first captured image comprises identifying blocks of pixels of the first captured image.

12. The method of claim 8 , wherein forming the distance map based on the disparity comprises forming the distance map based on the equation: z=bf/x, wherein z is a distance, b is a separation distance between a first camera that captures the image from the first perspective and a second camera that captures the image from the second perspective, f is a focal length of the first camera and the second camera, and x is the disparity.

13. The method of claim 1 , wherein the captured image represents a friction ridge surface.

14. The method of claim 13 , wherein the friction ridge surface represented in the captured image is associated with at least one of a palm print, a fingerprint, or a footprint.

15. A device comprising:
a memory configured to store an image an image captured by a camera or via a platen of an apparatus that includes the device; and
one or more processors in communication with the memory, the one or more processors being configured to process the image stored to the memory relative to a plane of interest that is defined by at least one of an image plane of the camera or by the platen of the apparatus that includes the computing device, wherein to process the captured image stored to the memory relative to the plane of interest, the one or more processors are configured to:
determine a plurality of regions of interest within the captured image stored to the memory;
determine, for each respective region of interest of the plurality of regions of interest, a respective distance from one or more objects within the respective region of interest to the plane of interest; and
process each respective region of interest independently of any other regions of interest included in the plurality of regions of interest, based on the respective distance from the one or more objects of each respective region of interest to the plane of interest.

16. The device of claim 15 , wherein the captured image stored to the memory represents a friction ridge surface associated with at least one of a palm print, a fingerprint, or a footprint.

Assignees

• 3M Innovative Properties Co

Inventors

• Shannon Robert W
• Dunn Douglas S
• Casner Glenn E
• Gandrud Jonathan D
• Scott Shannon D
• Singh Gautam

Classifications

• G06T7/593 Primary

  from stereo images · CPC title

• G06V40/1347

  Preprocessing; Feature extraction · CPC title

• G06V20/64

  Three-dimensional [3D] objects · CPC title

• G06V40/1312

  direct reading, e.g. contactless acquisition · CPC title

• G06T7/74

  involving reference images or patches · CPC title