Method and system for identifying and rendering hand written content onto digital display interface

Patent metadata

Field	Value
Publication number	US-2020293613-A1
Application number	US-201916359063-A
Country	US
Kind code	A1
Filing date	Mar 20, 2019
Priority date	Mar 12, 2019
Publication date	Sep 17, 2020
Grant date	—

Abstract

The present disclosure discloses method and a content providing system for identifying and rendering hand written content onto digital display interface of electronic device. The content providing system receives content handwritten by user using digital pointing device and identifies one or more digital objects from content based on coordinate vector formed between digital pointing device and boundary within which user writes along with coordinates of boundary. The content providing system converts one or more digital objects to predefined standard size and identifies one or more characters associated with one or more digital objects based on plurality of predefined character pair and corresponding coordinates. A dimension space required for each of digital objects is determined based on corresponding coordinate vector. Thereafter, the one or more digital objects and the one or more characters handwritten by the user are rendered in predefined standard format on digital display interface.

First claim

1 . A method of identifying and rendering hand written content onto digital display interface of an electronic device, the method comprising:
receiving, by a content providing system, content handwritten by a user in real-time using a digital pointing device; identifying, by the content providing system, one or more digital objects from the content based on coordinate vector formed between the digital pointing device and a boundary within which the user writes along with coordinates of the boundary using a trained neural network, wherein the coordinate vector provides multi-dimensional coordinate details of the content handwritten or gestured by the user, and wherein the coordinate vector and the coordinates of the boundary are retrieved from one or more sensors attached to the digital pointing device; converting, by the content providing system, the one or more digital objects to a predefined standard size; identifying, by the content providing system, one or more characters associated with the one or more digital objects based on a plurality of predefined character pair and corresponding coordinates; determining, by the content providing system, a dimension space required for each of the one or more digital objects based on corresponding coordinate vector to render on the digital display interface, wherein each of the one or more digital objects are converted to the determined dimension space; and rendering, by the content providing system, the one or more digital objects and the one or more characters handwritten by the user in a predefined standard format on the digital display interface.

2 . The method as claimed in claim 1 , wherein the one or more digital objects comprises paragraphs, text, alphabets, table, graphs and figures.

3 . (canceled)

4 . The method as claimed in claim 1 , wherein identifying the one or more digital objects comprises:
identifying, the one or more digital object as character when the digital pointing device is identified to be not lifted; identifying, the one or more digital object as a table when the digital pointing device is identified to be lifted a plurality of times based on number of rows and columns in the table; identifying the one or more digital object as figures based on tracing of coordinates and relations; and identifying the one or more digital object as a graph based on contours or points in the boundary.

5 . The method as claimed in claim 1 further comprising generating a user specific contour, stored in a database, based on handwritten content previously provided by the user.

6 . The method as claimed in claim 1 further comprising converting each character in the one or more digital objects to a predefined standard size.

7 . The method as claimed in claim 1 further comprising providing visual interactive feedback to the user while writing in order to check correctness of the content being provided in the predefined standard format.

8 . A content providing system for identifying and rendering hand written content onto digital display interface of an electronic device, comprising:
a processor; and a memory communicatively coupled to the processor, wherein the memory stores processor instructions, which, on execution, causes the processor to:
receive content handwritten by a user in real-time using a digital pointing device;
identify one or more digital objects from the content based on coordinate vector formed between the digital pointing device and a boundary within which the user writes along with coordinates of the boundary using a trained neural network, wherein the coordinate vector provides multi-dimensional coordinate details of the content handwritten or gestured by the user, and wherein the coordinate vector and the coordinates of the boundary are retrieved from one or more sensors attached to the digital pointing device;
convert the one or more digital objects to a predefined standard size;
identify one or more characters associated with the one or more digital objects based on a plurality of predefined character pair and corresponding coordinates;
determine a dimension space required for each of the one or more digital objects based on corresponding coordinate vector to render on the digital display interface, wherein each of the one or more digital objects are converted to the determined dimension space; and
render the one or more digital objects and the one or more characters handwritten by the user in a predefined standard format on the digital display interface.

9 . The content providing system as claimed in claim 8 , wherein the one or more digital objects comprises paragraphs, text, alphabets, table, graphs and figures.

10 . (canceled)

11 . The content providing system as claimed in claim 8 , wherein the processor identifies the one or more digital objects by:
identifying the one or more digital object as character when the digital pointing device is identified to be not lifted; identifying the one or more digital object as a table when the digital pointing device is identified to be lifted a plurality of times based on number of rows and columns in the table; identifying the one or more digital object as figures based on tracing of coordinates and relations; and identifying the one or more digital object as a graph based on contours or points in the boundary.

12 . The content providing system as claimed in claim 8 , wherein the processor generates a user specific contour, stored in a database, based on user handwritten content previously provided by the user.

13 . The content providing system as claimed in claim 8 , wherein the processor converts each character in the one or more digital objects to a predefined standard size.

14 . The content providing system as claimed in claim 8 , wherein the processor provides visual interactive feedback to the user while writing in order to check correctness of the content being provided in the predefined standard format.

15 . A non-transitory computer readable medium including instruction stored thereon that when processed by at least one processor cause a content providing system to perform operation comprising:
receiving content handwritten by a user in real-time using a digital pointing device; identifying one or more digital objects from the content based on coordinate vector formed between the digital pointing device and a boundary within which the user writes along with coordinates of the boundary using a trained neural network, wherein the coordinate vector provides multi-dimensional coordinate details of the content handwritten or gestured by the user, and wherein the coordinate vector and the coordinates of the boundary are retrieved from one or more sensors attached to the digital pointing device; converting the one or more digital objects to a predefined standard size; identifying one or more characters associated with the one or more digital objects based on a plurality of predefined character pair and corresponding coordinates; determining a dimension space required for each of the one or more digital objects based on corresponding coordinate vector to render on the digital display interface, wherein each of the one or more digital objects are converted to the determined dimension space; and rendering the one or more digital objects and the one or more characters handwritten by the user in a predefined standard format on the digital display interface.

16 . The method as claimed in claim 1 , wherein identifying the one or more digital objects further comprises segregating the one or more digital objects based on the coordinate vectors a

Assignees

• Wipro Ltd

Inventors

• Ramachandra Iyer Manjunath

Classifications

• G06F40/174

  Form filling; Merging · CPC title

• G06F40/171 Primary

  by use of digital ink · CPC title

• G06V30/32

  Digital ink · CPC title

• G06V30/10

  Character recognition · CPC title

• G06V10/82

  using neural networks · CPC title