Object recognition and library
An image may be received, a portion of which corresponds to a surface of an object, such as a book, a CD, a DVD, a wine bottle, etc. The portion of the image that corresponds to the surface of the object is located. The portion of the image is compared with previously stored images of surfaces of objects to identify the object. A record of the object is created and added to a library. The record of the object may comprise the image of the object, the portion of the image which corresponds to the surface of the object, and/or the received image itself. The record may comprise an indicator of a location of the object.
1. A method for creating an object library, comprising:
receiving an image, wherein a portion of the image corresponds to a surface of an object;
locating the portion of the received image that corresponds to a surface of an object and an object boundary;
identifying an image of a surface of an object from a plurality of images of surfaces of a plurality of objects that matches the located portion of the received image; and
adding a record of the object corresponding to the identified image of the surface of the object that matches the located portion of the received image to a library.
2. The method of claim 1 , wherein the record of the object comprises the received image.
3. The method of claim 1 , further comprising receiving an indicator of a location of the object and adding the indicator of the location of the object to the record.
4. The method of claim 1 , wherein the plurality of objects are books, and the surfaces of the plurality of objects comprise spines of the books or covers of the books.
5. The method of claim 1 , further comprising transmitting the library to a social networking system.
6. A method for creating an object library, comprising:
receiving an image, wherein the image includes a plurality of portions that correspond to surfaces of a plurality of objects;
locating a portion of the received image that corresponds to one of the surface of one of the plurality of objects by determining an object boundary in the received image and locating at least one portion of the received image that is likely to correspond to at least one surface of the object based on a size and a shape of the object boundary;
comparing the located portion of the received image with at least one of a plurality of images of surfaces of objects;
generating a confidence value for each of the plurality of images of surfaces of objects compared to the located portion;
identifying an image of the plurality of images of surfaces of objects with the highest confidence value as matching the located portion of the received image; and
adding a record of an object corresponding to the identified image that matches the located portion to a library.
7. The method of claim 6 , wherein the image is received from a digital camera.
8. The method of claim 6 , wherein receiving the image comprises receiving a video and extracting the received image from the video.
9. The method of claim 6 , further comprising receiving an indicator of a location of the object and adding the indicator of a location of the object to the record.
10. The method of claim 6 , further comprising:
identifying an external library that has at least one record in common with the library; and
recommending at least one object from the external library.
11. The method of claim 10 , further comprising presenting an offer to purchase one of the recommended at least one objects.
12. The method of claim 6 , wherein the objects are books.
13. The method of claim 6 , further comprising providing the record to a social networking system.
14. The method of claim 6 , wherein the plurality of images of surfaces of objects have characteristics, and further comprising:
identifying text in the located portion of the received image;
identifying images from the plurality of images of surfaces of objects that have characteristics that match the identified text; and
comparing the located portion of the received image only with at least one of the identified plurality of images of surfaces of objects that have characteristics that match the identified text.
15. A system comprising:
a processor;
an object locator adapted to locate a portion of a received image that corresponds to a surface of an object, wherein the surface of the object is distinct from an object boundary of the object in the received image;
an image comparator adapted to identify an image of a surface of an object from a plurality of images of surfaces of a plurality of objects that matches the located portion of the received image; and
a database adapted to store a record of the object corresponding to the identified image of the surface of the object that matches the located portion.
16. The system of claim 15 , wherein the record of the object comprises the received image.
17. The system of claim 15 , wherein the database is further adapted to add an indicator of a location of the object to the record.
18. The system of claim 15 , wherein the plurality of objects are books, and the surfaces of the plurality of objects are spines of the books or covers of the books.
19. The system of claim 15 , wherein the image comparator is further adapted to:
compare the located portion of the received image with one or more of the plurality of images of surfaces of objects;
generate a confidence value for each of the images of surfaces of objects compared to the located portion; and
identify an image of the plurality of images of surfaces of objects with the highest confidence value as matching the located portion of the received image.
20. The system of claim 15 , further comprising a recommendation engine adapted to recommend at least one object based on records of objects in the database.