Methods of content-based image area selection

Patent metadata

Field	Value
Publication number	US-9678642-B2
Application number	US-201514725248-A
Country	US
Kind code	B2
Filing date	May 29, 2015
Priority date	May 29, 2015
Publication date	Jun 13, 2017
Grant date	Jun 13, 2017

Abstract

A system and methods for selecting a region of pixels in an image displayed on a touch-sensitive interface is disclosed. The method for selecting the region of pixels is based on determined connectivity of pixels in the image indicating content of the image and includes determining connected pixels on the image representing the content without performing character recognition, detecting a text selection gesture indicative of selecting the region in the image, determining coordinates of the text selection gesture performed on the touch-sensitive interface and selecting the region in the image by bounding a first set of pixels located at a proximity from the coordinates of the text selection gesture.

First claim

The invention claimed is:

1. A method for selecting a region in an image having substantially connected pixels representing content of the image, the image displayed in a touch-sensitive user interface, comprising:
identifying one or more areas in the image having the substantially connected pixels indicating the content of the image without performing character recognition;
receiving coordinates of a touch input on the touch-sensitive user interface that indicates the region in the image the user requests to select via the touch input;
if the coordinates of the touch input are located in the one or more areas having the substantially connected pixels indicating the content of the image, determining the substantially connected pixels in the image that are located at a specified proximity from the coordinates of the touch input; and
bounding the substantially connected pixels located at the specified proximity from the coordinates, the bounded substantially connected pixels indicating the region the user selects using the touch input,
wherein the touch input is a text selection gesture and the identifying the one or more areas in the image having substantially connected pixels representing content of the image includes applying a morphology dilation filter to the image to form one or more lines of connected pixels and forming a bounding box having a left side corresponding to starting lines of the lines of connected pixels, a right side corresponding to end lines of the lines of connected pixels and a centroid corresponding to a mean position of each of the lines of the connected pixels.

2. The method of claim 1 , further comprising determining if the coordinates of the touch input is in an area within the bounding box, and upon positive determination, selecting the lines of connected pixels within the bounding box as the region by highlighting the lines of connected pixel components within the bounding box with a first color.

3. The method of claim 1 , further comprising associating an action performed by the user using the touch input for selecting the region with an action to be performed on the bounded region of interest.

4. The method of claim 3 , wherein the associating the action includes determining if the touch input is moved from one direction to a second direction when selecting the region and upon positive determination, deleting the selected region of interest by replacing the highlighted one or more connected pixels with a color different from a color of the one or more connected pixels.

Assignees

• Lexmark Int Inc

Inventors

• Daniel Stuart Willard
• Eid Ahmed Hamad Mohamed
• Love Shaun Timothy

Classifications

• G06V30/18076

  by analysing connectivity, e.g. edge linking, connected component analysis or slices · CPC title

• G06V30/1456

  based on user interactions · CPC title

• G06V30/10

  Character recognition · CPC title

• G06F3/04842 Primary

  Selection of displayed objects or displayed text elements (G06F3/0482 takes precedence) · CPC title

• G06K9/4604

  Physics · mapped topic