Abstract: Disclosed herein are image-based object recognition method and system by and in which a learning server performs image-based object recognition based on the learning of environment variable data. The image-based object recognition method includes: receiving an image acquired through at least one camera, and segmenting the image on a per-frame basis; primarily learning labeling results for one or more objects in the image segmented on a per-frame basis; performing primary reasoning by performing object detection in the image through a model obtained as a result of the primary learning; performing data labeling based on the results of the primary reasoning, and performing secondary learning with weights allocated to respective boxes obtained by the primary reasoning and estimated as object regions; and finally detecting one or more objects in the image through a model generated as a result of the secondary learning.

Abstract: A light emitting element includes: a light emitting stack pattern including a first semiconductor layer, an active layer, and a second semiconductor layer that are sequentially stacked along one direction; and an insulating film surrounding an outer surface of at least one of the first semiconductor layer, the active layer, and the second semiconductor layer. The insulating film including a zinc oxide (ZnO) thin film layer.

Abstract: Disclosed herein are image-based object recognition method and system by and in which a learning server performs image-based object recognition based on the learning of environment variable data. The image-based object recognition method includes: receiving an image acquired through at least one camera, and segmenting the image on a per-frame basis; primarily learning labeling results for one or more objects in the image segmented on a per-frame basis; performing primary reasoning by performing object detection in the image through a model obtained as a result of the primary learning; performing data labeling based on the results of the primary reasoning, and performing secondary learning with weights allocated to respective boxes obtained by the primary reasoning and estimated as object regions; and finally detecting one or more objects in the image through a model generated as a result of the secondary learning.

Abstract: In training a target model initialized by borrowing the structure and parameters of a pre-trained source model, the present disclosure provides a transfer learning apparatus and method capable of improving the performance of the target model by fine-tuning the target model using sample-based regularization that increases the similarity between features extracted from training samples belonging to the same class.

Abstract: Disclosed are a GUI voice control apparatus and method. More particularly, a GUI voice control apparatus according to an embodiment of the present disclosure includes a context information generator configured to dynamically reflect GUI status information and DB information in a language model to generate context information; a voice recognizer configured to convert a voice signal into text in real time to update text information; a natural language recognizer configured to reduce the number of command patterns matchable with the text information based on the context information as the text information is updated, and recognize an intent and entity of the voice signal by matching with a final command pattern; and a voice controller configured to output a control signal according to the recognized intent and entity.

Abstract: Disclosed herein is a method and system for providing a ringback tone (RBT). The system for providing an RBT to a user comprises: a sound file storage for storing a sound file; a user database receiving sound selection information from a user terminal, recording a sound identifier of the sound file corresponding to the sound selection information, receiving output position information of the selected sound file from the user terminal, and recording the sound position information; and an RBT providing unit reproducing a region which corresponds to the output position information from the sound file corresponding to the sound identifier with reference to the sound file storage and the user database so as to be provided as an RBT.

Abstract: An application interoperation method includes: maintaining a handler table including data type information, function information and calling information associated with each application installed in a portable device; receiving input information on a menu key of the portable device, from a user, while a first application is active; extracting, in response to the receipt of the input information, at least one function information associated with data type information, which is being processed or requested by the first application, from the handler table; dynamically generating a menu including the extracted function information to provide the user with the generated menu; receiving selection information on particular function information among the provided menu, from the user; and identifying calling information associated with the selected particular function information by referring to the handler table and executing a second application based on the identified calling information.

Abstract: Disclosed herein is a method and system for providing a ringback tone (RBT). The system for providing an RBT to a user comprises: a sound file storage for storing a sound file; a user database receiving sound selection information from a user terminal, recording a sound identifier of the sound file corresponding to the sound selection information, receiving output position information of the selected sound file from the user terminal, and recording the sound position information; and an RBT providing unit reproducing a region which corresponds to the output position information from the sound file corresponding to the sound identifier with reference to the sound file storage and the user database so as to be provided as an RBT.

Abstract: An application interoperation method including the steps of: maintaining a handler table including data type information, function information and calling information which are associated with each application installed in a portable device; receiving input information on a menu key of the portable device, from a user, while a first application is active; extracting, in response to the receipt of the input information, at least one function information associated with data type information of data, which is being processed or requested by the first application, from the handler table; dynamically generating a menu including the extracted at least one function information to provide the user with the generated menu; receiving selection information on particular function information among the provided menu, from the user; and identifying calling information associated with the selected particular function information by referring to the handler table and executing a second application on the basis of the identi

Abstract: Disclosed herein is a method and system for providing a ringback tone (RBT). The system for providing an RBT to a user comprises: a sound file storage for storing a sound file; a user database receiving sound selection information from a user terminal, recording a sound identifier of the sound file corresponding to the sound selection information, receiving output position information of the selected sound file from the user terminal, and recording the sound position information; and an RBT providing unit reproducing a region which corresponds to the output position information from the sound file corresponding to the sound identifier with reference to the sound file storage and the user database so as to be provided as an RBT.

Abstract: An application interoperation method includes: maintaining a handler table including data type information, function information and calling information associated with each application installed in a portable device; receiving input information on a menu key of the portable device, from a user, while a first application is active; extracting, in response to the receipt of the input information, at least one function information associated with data type information, which is being processed or requested by the first application, from the handler table; dynamically generating a menu including the extracted function information to provide the user with the generated menu; receiving selection information on particular function information among the provided menu, from the user; and identifying calling information associated with the selected particular function information by referring to the handler table and executing a second application on the basis of the identified calling information.

Abstract: Techniques and apparatus for limiting a sound pressure level produced by an audio output device driven by an audio player. During play, the audio player monitors the current sound pressure level of the audio output device, and in response thereto limits the sound pressure level by controlling an output level of audio signals it generates so as to reduce hearing loss caused by excess volume.

Abstract: The present invention relates to a system for providing executable web content to a terminal. The present invention provides a system comprising a server, which provides an executable web content comprising a declarative language part in declarative language and a non-declarative part, and a gateway, which receives the executable web content from the server, converts it into a format executable in a web browser of the terminal, and transmits the converted content to the terminal.

Abstract: Disclosed herein is a method and system for providing a ringback tone (RBT). The system for providing an RBT to a user comprises: a sound file storage for storing a sound file; a user database receiving sound selection information from a user terminal, recording a sound identifier of the sound file corresponding to the sound selection information, receiving output position information of the selected sound file from the user terminal, and recording the sound position information; and an RBT providing unit reproducing a region which corresponds to the output position information from the sound file corresponding to the sound identifier with reference to the sound file storage and the user database so as to be provided as an RBT.

Abstract: Since music signals are encoded by a voice encoding method optimized to human voice signals such as EVRC (Enhanced Variable Rate Coding) in a cellular communication system, the music signals are often distorted by such encoding method, and listeners experience pauses in music caused by such voice-optimized encoding method. To improve the perceptual sound quality of music, a method for preprocessing digital audio data is provided in order to prevent the problem of pause in music signals in a cellular phone. In particular, AGC (Automatic Gain Control) preprocessing and PHE (Pitch Harmonics Enhancement) is performed to the digital audio data having low dynamic range. By this method, the number of pauses in music signal is reduced, and the perceptual sound quality of the music is improved.

Abstract: An application interoperation method including the steps of: maintaining a handler table including data type information, function information and calling information which are associated with each application installed in a portable device; receiving input information on a menu key of the portable device, from a user, while a first application is active; extracting, in response to the receipt of the input information, at least one function information associated with data type information of data, which is being processed or requested by the first application, from the handler table; dynamically generating a menu including the extracted at least one function information to provide the user with the generated menu; receiving selection information on particular function information among the provided menu, from the user; and identifying calling information associated with the selected particular function information by referring to the handler table and executing a second application on the basis of the identi

Abstract: Recently, with the wider use of cellular phones, more and more users listen to music via their cellular phones, and thus, the sound quality of music provided via the cellular phones became more critical. Since music signals are encoded by a voice encoding method optimized to human voice signals such as EVRC (Enhanced Variable Rate Coding) in a cellular communication system, the music signals are often distorted by such encoding method, and listeners experience pauses in music caused by such voice-optimized encoding method. To improve the sound quality of music, a method for preprocessing audio data is provided in order to prevent the problem of pause in music signals in a cellular phone. In particular, AGC (Automatic Gain Control) preprocessing is performed to the audio data having low dynamic range. By this method, the number of pauses in music signal is reduced, and the sound quality of the music is improved.