Abstract:
An electronic device is disclosed. The electronic device comprises a storage unit for storing a training model of a multi-dimensional long short-term memory (MDLSTM), and a processor for acquiring an image including at least one of handwritten text and printed text, identifying each text line region in the image through image processing, and recognizing text included in the each identified text line region, on the basis of the training model.
Abstract:
A method of performing a command of a user on a target object by using a tag and a visual descriptor of the target object obtained through human computer interaction (HCl) is provided. The method includes obtaining a plurality of images including a target object, detecting a motion of the user manipulating the target object, based on the plurality of images, obtaining a visual descriptor of the target object including visual information for identifying the target object, obtaining a tag of the target object by receiving information related to the target object, by marking the target object, and in response to receiving an input signal corresponding to the tag, performing an operation corresponding to the input signal on the target object, based on the visual descriptor.
Abstract:
A device is provided. The device includes an accelerometer configured to measure an acceleration of the device, a controller configured to acquire acceleration data of the device in a first time period and a second time period adjacent to the first time period from the accelerometer, determine a first movement state of a user in the first time period based on the acceleration data corresponding to the first time period, and determine a second movement state of the user in the second time period in consideration of the acceleration data corresponding to the second time period and the determined first movement state, and a display configured to display the first movement state and the second movement state.