Abstract: The present invention relates to a method for providing information on an object excluded in a visual field of a terminal in a form of augmented reality (AR) by using an image inputted to the terminal and information related thereto. The method includes the steps of: (a) specifying the visual field of the terminal corresponding to the inputted image by referring to at least one piece of information on a location, a displacement and a viewing angle of the terminal; (b) searching an object(s) excluded in the visual field of the terminal; and (c) displaying guiding information on the searched object(s) with the inputted image in a form of the augmented reality; wherein the visual field is specified by a viewing frustum whose vertex corresponds to the terminal.

Abstract: The present invention relates to a method for performing an image matching process for panoramic images. The method includes the steps of: (a) creating a connection(s) among images of a specific object respectively included in at least two panoramic images, if some objects included in the at least two panoramic images are recognized as the specific object by referring to information on shooting places of multiple panoramic images and information on directions of respective objects on the multiple panoramic images; and (b) matching an image of a certain object inputted as a query with at least one of images included in a specific connection and providing a search result for the query by referring to a result of the image matching process and the specific connection.

Abstract: The present invention relates to a method for supporting a collection of an object included in an image inputted through a terminal. The method includes the steps of: recognizing the identity of an object by using at least one of an object recognition technology, an optical character recognition technology, and a barcode recognition technology; getting a collection page including at least part of the information on an auto comment containing a phrase or sentence correctly combined under the grammar of a language by using the recognition information and the information on the image of the recognized object; allowing the collection page to be stored when a request for registration of the page is received; and providing a specific user with the information about a reward system.

Abstract: The present invention includes a method for removing redundancy of panoramic images. The method includes the steps of: (a) specifying respective locations of multiple panoramic images by referring to respective shooting places of the multiple panoramic images; (b) recognizing a specific object included in each of at least two panoramic images as the identical object by referring to the respective locations of the multiple panoramic images and respective directions of the specific object therein; and (c) determining top n images of the specific object considered to have top n degrees of precision in an image matching process among all the object images which are recognized as the identical object as a reference image(s) for the specific object.

Abstract: The present invention relates to a method for providing information on an object excluded in a visual field of a terminal in a form of augmented reality (AR) by using an image inputted to the terminal and information related thereto. The method includes the steps of: (a) specifying the visual field of the terminal corresponding to the inputted image by referring to at least one piece of information on a location, a displacement and a viewing angle of the terminal; (b) searching an object(s) excluded in the visual field of the terminal; and (c) displaying guiding information on the searched object(s) with the inputted image in a form of the augmented reality; wherein the visual field is specified by a viewing frustum whose vertex corresponds to the terminal.

Abstract: Provided are a method for attaching a geographical tag to digital data and a method for providing geographical name information for geotagging. When a digital device periodically provides its position information, the server creates a position database. When the digital device requests geographical name information associated with the digital data, the server estimates the position of the digital device at a time when the digital data was created and transmits geographical name information corresponding to the estimated position to the digital device. The digital device attaches the geographical name information to the digital data.

Abstract: The present invention relates to a method for applying a trimming operation to image. The method includes the steps of: detecting person and object; calculating area of face region and area of detected object and calculating distance between center of face region and that of image and distance between center of detected object and that thereof; and applying trimming operation to the object if area of detected object is by over a first prefixed percent larger than that of face, and applying trimming operation to the object if distance between center of detected object and that of image is a second prefixed value or less and distance between center of face and that of image is by over a third prefixed value larger than distance between center of detected object and that thereof.

Abstract: The present invention relates to a method for providing advertisement by using collection information. The method includes the steps of: allowing recognition reference information on an object from a vendor server to be received; allowing collection information to be acquired; allowing the object corresponding to the basic recognition information to be recognized by comparing between the basic recognition information included in the digital data in the collection information acquired from the user terminal and the recognition reference information received from the vendor server and allowing statistical collection information to be calculated by referring to the information on the recognized object and a user of the user terminal who remits the basic recognition information; and allowing advertising information on a peculiar object to be provided for a user terminal(s) included in a specific user group.

Abstract: The present invention relates to a method for making a user easily replay a scene on which a specific person appears included in a movie. The method includes the steps of: (a) distinguishing persons appearing in the movie by recognizing their faces; (b) obtaining identifier of each distinguished person, feature data of the persons, information on time zone in which each person appears, wherein the information on the time zone includes a starting time and an ending time and wherein the ending time for a person is determined as the last time that the person appeared if the person has not appeared for more than a certain critical time; (c) displaying the identifier at a request of replay of the movie; and (d) replaying the movie from the starting time for a specific person who corresponds to a specific identifier if the specific identifier is selected.

Abstract: The present invention relates to a method for supporting a collection of an object included in an image inputted through a terminal. The method includes the steps of: recognizing the identity of an object by using at least one of an object recognition technology, an optical character recognition technology, and a barcode recognition technology; getting a collection page including at least part of the information on an auto comment containing a phrase or sentence correctly combined under the grammar of a language by using the recognition information and the information on the image of the recognized object; allowing the collection page to be stored when a request for registration of the page is received; and providing a specific user with the information about a reward system.

Abstract: The present invention relates to a method for providing information on an object by using viewing frustums. The method includes the steps of: (a) specifying at least two viewing frustums whose vertexes are visual points of respective user terminals; and (b) calculating a degree of interest in the object by referring to the object commonly included in both a first viewing frustum whose vertex is a visual point of a first user terminal and a second one whose vertex is a visual point of a second user terminal.

Abstract: There are provided a method and an apparatus for acquiring information on products which are located on the body of a person appearing in image data. More particularly, a method and an apparatus for analyzing a posture of a person from image data, i.e., a face posture and a body posture of the person, displaying, according to information on the posture of the person, at least one of candidate regions in which products are attached to the body of the person in the image data on a screen of a terminal of a user, and, if the user selects any one of the candidate regions, providing the terminal with information on products same as or similar to an image of a specific product included in the selected candidate region.

Abstract: The present invention relates to a method and a system for filtering the harmful content (s) which includes a filter group for providing an optimized filter for each category; a matching engine for monitoring harmfulness of the content by matching it with existing lewd contents recorded in a pornographic content database and/or advertising contents recorded in an advertising content database; an interface part which provides a user with information on a degree of similarity between the inputted content and the harmful contents recorded in the above-mentioned database which is calculated through the matching process in order to increase the filtering accuracy; and information on a degree of harmfulness of the content calculated in the filter group; and information on a user who created or distributed the content. Accordingly, it is possible to filter adult contents or advertising contents with much higher accuracy by three harmful content blocking steps.

Abstract: The present invention relates to a method for hierarchically matching a building image. The method includes the steps of: matching a wall of a specific building in the building image inputted as a query with a wall(s) of a building(s) in at least one panoramic image by using a technology of matching a building's shape or repeated pattern; selecting a candidate panoramic image(s) which includes a building(s) recognized to have the same or similar wall to the specific building in the panoramic image(s) as a result of matching its wall with others; matching at least one local region, if containing a recognizable string or figure, in the specific building with local region(s) in the building(s) of the candidate panoramic image(s) by using a technology of recognizing a string or a figure; and determining top n panoramic image(s) as the result of matching the local region.

Abstract: The present invention relates to a method for providing information on an object included in a visual field of a terminal in a form of augmented reality (AR) by using an image inputted to the terminal and its relating information. The method includes the steps of: (a) specifying the visual field of the terminal corresponding to the inputted image by referring to at least one piece of information on a location, a displacement and a viewing angle of the terminal; and (b) acquiring a graphic element corresponding to the object, included in the visual field of the terminal, whose identity is recognized by using a technology for matching a building image and displaying the acquired graphic element with the inputted image in the form of the augmented reality by providing the graphic element on a location of the object displayed on a screen of the terminal.

Abstract: The present invention relates to a method for applying a trimming operation to image. The method includes the steps of: detecting person and object; calculating area of face region and area of detected object and calculating distance between center of face region and that of image and distance between center of detected object and that thereof; and applying trimming operation to the object if area of detected object is by over a first prefixed percent larger than that of face, and applying trimming operation to the object if distance between center of detected object and that of image is a second prefixed value or less and distance between center of face and that of image is by over a third prefixed value larger than distance between center of detected object and that thereof.

Abstract: The present invention relates to a method for providing augmented reality (AR) by using an image inputted to a terminal and information relating to the inputted image. The method includes the steps of: (a) acquiring recognition information on an object included in the image inputted through the terminal; (b) instructing to search detailed information on the recognized object and providing a tag accessible to the detailed information, if the searched detailed information is acquired, on a location of the object appearing on a screen of the terminal in a form of the augmented reality; and (c) displaying the detailed information corresponding to the tag, if the tag is selected, in the form of the augmented reality; wherein, at the step (b), the information on the location of the object is acquired by applying an image recognition process to the inputted image.

Abstract: The present invention relates to a method for providing information on an object excluded in a visual field of a terminal in a form of augmented reality (AR) by using an image inputted to the terminal and information related thereto. The method includes the steps of: (a) specifying the visual field of the terminal corresponding to the inputted image by referring to at least one piece of information on a location, a displacement and a viewing angle of the terminal; (b) searching an object(s) excluded in the visual field of the terminal; and (c) displaying guiding information on the searched object(s) with the inputted image in a form of the augmented reality; wherein the visual field is specified by a viewing frustum whose vertex corresponds to the terminal.

Abstract: The present invention relates to a method for adaptively performing an image matching process according to a situation. The method includes the steps of: (a) recognizing the situation of a subject included in an inputted image; and (b) selecting an image group including at least one image to be compared with the inputted image of the subject for the image matching process among multiple images stored on a database, as a qualified reference image group, according to the recognized situation; wherein the images included in the qualified reference image group are dynamically changed according to the recognized situation.

Abstract: The present invention includes a method for performing visual search based on a movement and/or an angular position of a terminal. The method includes the steps of: (a) sensing a movement and/or an angular position of a terminal by using at least one of sensors; (b) determining whether a triggering event occurs or not by referring to at least one of the sensed movement and the sensed angular position of the terminal; and (c) if the triggering event occurs, allowing visual search to be performed for at least one of objects included in an output image displayed on the terminal at the time of the occurrence of the triggering event; wherein the output image is generated in a form of augmented reality by combining an image inputted through the terminal in real time with information relevant thereto.