Generation of imagery from descriptive text

Patent metadata

Field	Value
Publication number	US-10074200-B1
Application number	US-201514693608-A
Country	US
Kind code	B1
Filing date	Apr 22, 2015
Priority date	Apr 22, 2015
Publication date	Sep 11, 2018
Grant date	Sep 11, 2018

Abstract

Imagery may be generated for a written work based on textual descriptions in the written work using an automated or partially automated process. The imagery may be used to create a trailer for the written work, for insertion into a digital version of the written work, to visually represent the written work, and/or for other reasons. Descriptive text from the written work may be identified and associated with a catalog of imagery, which include image objects that are discrete images of subjects. The image objects may be compiled with other image objects to create an initial image. The initial image may be edited by a user or other person to add more detail, modify subjects, add an additional subject, remove subjects, change attributes, and/or make other changes to the initial image.

First claim

What is claimed is:

1. A method of creating an image based on textual content of an electronic book (eBook), the method comprising:
receiving an indication that a portion of text from the eBook has been annotated a number of times that is equal to or above a threshold amount;
selecting, based upon the indication that the portion of text from the eBook has been annotated the number of times that is equal to or above the threshold amount, the portion of text from the eBook;
analyzing the portion of the text to isolate descriptive words within the portion of the text, the descriptive words including subjects, objects, and adjectives used in the portion of the text;
creating a parse tree using the descriptive words, the creating the parse tree including:
determining a subject that is a character described in the eBook; and
determining an attribute of the subject, the attribute describing an appearance of the character;

selecting an image object by associating metadata of the subject of the parse tree with metadata of the image object to select the image object as a character image object that visually represents the character described in the eBook;
modifying the character image object based on the attribute of the parse tree, the modifying including changing a size or a color associated with the appearance of the character;
generating the image by including the character image object within a scene, the scene including at least background imagery associated with the eBook;
causing the image to be displayed to a user for review via a user device;
receiving an editing command from the user via the user device to edit an appearance of the character image object within the image, the editing command being natural language input that includes one or more additional descriptive words;
modifying the character image object within the image based on the additional descriptive words in the editing command; and
generating a second version of the eBook, after modification of the character image object within the image based on the editing command, by inserting the image into the eBook at a specific location proximate to the location of the portion of text from which the image is generated.

2. The method as recited in claim 1 , wherein the editing command is an instruction to modify a position of the character image object within the image; and
wherein modifying the character image object within the image comprises:
determining a new position for the character image object based on the editing command, the new position being different than an original position of the character image object in the image as determined by the generating the image; and
moving the character image object to the new position in the image.

3. The method as recited in claim 1 , further comprising determining a verb associated with the subject, and wherein the creating the parse tree includes the subject, the attribute, and the verb, and wherein the selecting the object image includes associating metadata of the verb with the metadata of the image object.

4. The method as recited in claim 1 , further comprising generating a second image from a different portion of text from the eBook and inserting the second image into the second version of the eBook at a second specific location proximate to the location of the different portion of text from the eBook.

5. A system comprising:
one or more processors; and
memory to store computer-executable instructions that, when executed, cause the one or more processors to perform acts comprising:
receiving an indication that a portion of text from an electronic book (eBook) has been annotated a number of times that is equal to or above a threshold amount;
selecting, based upon the indication that the portion of text from the eBook has been annotated the number of times that is equal to or above the threshold amount, the portion of text;
analyzing the portion of text to identify descriptive words including a subject of the portion of text;
associating an attribute of the descriptive words with the subject;
selecting an image object that visually represents the subject using a relationship that associates text with imagery;
determining an attribute value associated with the image object to cause the image object to visually represent the attribute;
generating an image containing the image object;
causing display of the image to a user for review via a user device;
receiving an editing command from the user via the user device to edit an appearance of one or more objects within the image, the editing command being natural language input that includes one or more additional descriptive words;
modifying the appearance of the one or more objects within the image based on the additional descriptive words in the editing command; and
generating a second version of the eBook, after modifying the appearance of the one or more objects within the image in response to receipt of the editing command, by inserting the image into the eBook at a specific location proximate to the location of the portion of text from which the image is generated.

6. The system as recited in claim 5 , wherein the editing command is an instruction to modify a position of the one or more objects within the image.

7. The system as recited in claim 5 , wherein the natural language input is text entered by the user after the user's review of the imagery.

8. The system as recited in claim 5 , wherein the one or more processors further perform acts comprising:
determining a start location and an end location of each of a plurality of chapters of the eBook based on headings, blank portions of pages, or both; and
selecting the portion of text from a chapter of a plurality of chapters of the eBook.

9. The system as recited in claim 5 , wherein selecting the portion of text is based on input received from crowd sourcing data.

10. The system as recited in claim 5 , wherein the image object includes metadata, and wherein the relationship associates the text with the image object based on the metadata.

11. The system as recited in claim 5 , wherein the one or more processors further perform acts comprising:
creating a plurality of additional images based on the descriptive text; and
creating a trailer associated with the text to visually represent the text, the trailer including the plurality of additional images arranged temporally.

12. The system as recited in claim 5 , wherein the determining the attribute value includes determining a color associated with the descriptive words, and further comprising representing at least a portion of the image object with the color.

13. The system as recited in claim 5 , wherein the image object is a three dimensional (3D) image object, and wherein the one or more processors further perform acts comprising:
receiving an additional editing command to edit a perspective of the image object within the image, and
determining the perspective of the image object by rotating the 3D image object.

14. The system as recited in claim 5 , wherein the image object is a first-image object, and wherein the one or more processors further perform acts comprising:
determining a second-image object; and
compiling the first image object and the second image object into the image.

15. The system as recited in claim 14 , wherein the one or more processors further perform acts comprising locating the first image object relative to the second image object within the image based on a portion of the descriptive text that provides location information.

16. A method comprising:
receiving,

Assignees

• Amazon Tech Inc

Inventors

• Yeturu Kalidas

Classifications

• G06F40/103

  Formatting, i.e. changing of presentation of documents (automatic justification G06F40/189; automatic line break hyphenation G06F40/191) · CPC title

• G06T11/00

  Two-dimensional [2D] image generation · CPC title

• G06F40/169

  Annotation, e.g. comment data or footnotes · CPC title

• G06F40/279 Primary

  Recognition of textual entities · CPC title

• G06F40/10 Primary

  Text processing (natural language analysis G06F40/20; semantic analysis G06F40/30; processing or translation of natural language G06F40/40) · CPC title