APPARATUS AND METHOD FOR MULTI-MEDIA RECOGNITION, DATA CONVERSION, CREATION OF METATAGS, STORAGE AND SEARCH RETRIEVAL
First Claim
1. An apparatus that:
- a) captures and records image, video audio, speech and other data, interprets the received audio as speech, converts the speech to text, parses the text into a set of searchable tags and embeds the tags into the image(s) video or audio for retrieval; and
b) provides automatically-derived searchable tags such as color, shape, texture, of image, video and other data, performs recognition comparison, parses the data into a set of searchable tags and embeds the tags into the image(s), video or other data for retrieval.
3 Assignments
0 Petitions
Accused Products
Abstract
This invention relates to the storage and search retrieval of all types of digital media files, whether allowing the user to create index keys, metatags within each media file(s), provides search and indexing capability. The search terms and index keys are based on contextual elements within the media, including meta data such as time, date and location, but including as well elements within the media itself, such as people or elements (car, animals, street, events, historical location and other) within a picture or a video, audio, voice, spoke word, instruments used in a musical work, or scenes in a movie. An authorized client can then retrieve the media from the remote location. Specific works can then be referenced by means of the generated search terms and index keys. When the user transmits these media files via e-mail, FTP, public server, or copies to a digital media or other distribution method, these index keys are contained within the media files, therefore allowing the third party to search and retrieve the media files based on metatags.
109 Citations
22 Claims
-
1. An apparatus that:
-
a) captures and records image, video audio, speech and other data, interprets the received audio as speech, converts the speech to text, parses the text into a set of searchable tags and embeds the tags into the image(s) video or audio for retrieval; and
b) provides automatically-derived searchable tags such as color, shape, texture, of image, video and other data, performs recognition comparison, parses the data into a set of searchable tags and embeds the tags into the image(s), video or other data for retrieval. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10, 11)
-
-
12. A method for capturing information, comprising the steps of:
-
capturing in a first capturing step a first set of information and converting the first set of information to a first format;
capturing in a second capturing step a second set of information temporally related to the first set of information and converting the second set of information to a second format;
combining the first set of information in the first format with the second set of information in the second format into a combined set of information in a combination format;
transmitting the combined set of information in the combination format to a remote location;
extracting the first and second set of information in the respective first and second formats from the combined set of information in the combination format;
converting the second set of information to an intermediate set of information that retains substantially all of the information in the second set of information; and
combining the intermediate set of information with the first set of information in the first format to provide a modified set of information representing the combination of the first set of information and substantially all of the first set of information. - View Dependent Claims (13, 14, 15, 16, 17, 18)
-
-
19. A method for capturing image information, comprising the steps of:
-
capturing in a first capturing step image information and converting the captured image information to digitized image information in a digital image format;
capturing in a second capturing step an audio information related to the captured image information and converting the captured audio information to digitized audio information in a digitized audio format;
combining the captured image information in the digitized image format with the captured audio information in the digitized audio format into a combined set of information in a combination format;
transmitting the combined set of information in the combination format to a storage medium;
extracting the digitized image and audio information in the respective digital image and audio formats from the combined set of information in the combination format;
converting the digitized audio information to an intermediate set of information that retains substantially all of the information in the captured audio information; and
combining the intermediate set of information with the digitized image information in a digital combination format supporting the combination of digitized image information and the intermediate set of information to provide a modified digitized image with embedded information that represents substantially all of the captured audio information. - View Dependent Claims (20, 21, 22)
-
Specification