Abstract:
The present invention relates to a motion gesture recognition method and apparatus using sensor information in a user device which has a limited environment such as a smart phone. In particular, a method is provided which generates observation information using motion data generated while the user moves and measured by using acceleration, magnetic field, and gyro sensors embedded in the smart phone, and learns and recognizes gestures using a Hidden Markov Model (HMM). According to the method, various input signals can be generated by compensating individually or mutually for various embedded sensors, and a result sensitive to basic motions can be obtained through a quantization scheme that a rectangular coordinate is converted into a spherical coordinate. Furthermore, when the learning and recognizing process is performed by using motion data of the user, intuitive and individual gestures for each user can be registered and used.
Abstract:
The present invention suggests a technique to detect an intersecting point from a curve such as offline signature data and to track the curve using tensor voting. Firstly, using the result of the tensor voting, the line areas of an intersecting point and a starting point are extracted and a connection path from the starting point to another starting point is found. An intersection point is where more than two curves with different directions meet and has a characteristic that the sum of tensor values is large. Then, thinning and end point extraction are performed on an input image except for the intersecting point area. After the point where the tensor value difference is the biggest is found from the separated line object, the end of the object is found along the unique vector. Among the found end points, the point where the sum of the tensor values is small is considered as a starting point. By tracking the thinned line from the starting point to another starting point, if an intersecting point is found, the intersecting point is connected and the tracking continues in the nearest direction to the progress direction. The extracted online path can be applied to signature verification.
Abstract:
The present invention relates to an emotional messaging apparatus executed by enabling an avatar to have various emotional looks and using the avatar to enable a writer to express the emotions to opponents in the transmission of a message using a portable terminal such as a smartphone. The emotional messaging apparatus comprises a gesture sensing data storing step of storing touch gesture sensing data processed in a touch gesture recognizer by sensing touch gestures with a touch gesture sensor or motion gesture sensing data processed in a motion gesture recognizer by sensing the motion with a motion gesture sensor in a data storage unit; an emotion display data reading step of reading the predetermined emotion display data corresponding to the gesture sensing data among the motion gesture sensing data processed in the motion gesture recognizer by sensing the motion with the motion gesture sensor; and an emotion messaging input display step of displaying the emotion display data on an emotion messaging input display window. [Reference numerals] (321) Conversion selection window;(322) Touch input window;(323) Avatar input display window;(324) Result display window;(325) Transmission window;(326) Text input display window;(327) Key pad unit
Abstract:
PURPOSE: A personal area network subscription method using active scanning is provided to selectively execute the search of PAN by effectively using a service type. CONSTITUTION: A coordinator(3) receives a beacon request message including a first service type(S42). The coordinator determines whether the subscription of a device(2000) transmitting the beacon request message is allowed by using the first service type included in the received beacon request message(S43). When the permission of subscription is determined, the coordinator transmits beacon to the device transmitting the beacon request message(S45). [Reference numerals] (2000) Device; (3) Coordinator; (S41) Start scanning; (S42) Request beacon(including a service type); (S43) Is subscription allowed?; (S44) Ignore; (S45) Beacon; (S46) List up; (S47) Terminate scanning; (S48) Subscribe
Abstract:
PURPOSE: A system for operating a selective search-based host device, a method thereof, and a portable terminal supporting the same are provided to perform selective searches based on a user service for a portable terminal and surrounding host devices. CONSTITUTION: A portable terminal(100) or a specific host device generates a search request message to broadcast. The search request message includes service type information defining one or more specific service types. One or more host devices(200) mutually operate the device information and the service types included in the search request message. The host devices deliver a profile to the portable terminal or a specific host device as a response message according to the operational result.
Abstract:
PURPOSE: A method and a system for searching for a mobile application through activity knowledge database of a person are provided to reduce un-uniformity of words between a user query and a mobile application by using the activity knowledge database. CONSTITUTION: A user interface unit(110) supplies a query input environment to a user. The user interface unit displays a mobile application search result related to a user query. A mobile application search unit(150) receives the user query from the user interface unit. The mobile application search unit searches for the mobile application related to the user query by using activity knowledge database(130).
Abstract:
PURPOSE: A particle resampling method based on an index function and an image object tracking method using the same are provided to enable a user to effectively track an image object according to a purpose. CONSTITUTION: An image object is determined wherein the image object is a tracking target. Particles of a particle filter are initialized(S1000). A location of the image object is determined in a current location(S2000). Prediction particles predicted for determining the image object are generated by initial particles on which prediction particles of a next image are calculated based(S3000). It is determined whether an object determined as the image object is located in the current image(S4000).