Electronics and Telecommunications Research Institute

Sk Innovation Co., Ltd.

Postech Academy-industry Foundation

Hye-Jin Kim

Jae-Yeon Lee

Kye-Kyung Kim

Soo-Hyun Cho

Do-Hyung Kim

Jong Dae Kim

Woo Seok Yang

Hyun-Chul Park

Young-Jo Cho

Kun-Hong Lee

Woon-Bong Hwang

Ho-Sub Yoon

Jae-Eun Lee

Su-Young Chi

Suyoung Chi

Won-Yeob Kim

Chul-Soon Moon

Young-Deuk Kim

Ho-Chul Yoon

Jong-Eun Lee

Sang-Yun Oh

Jong-Nam Ahn

Youngjune Park

An apparatus for detecting a dimension error obtains an image of a target object, estimates dimensional data for a region of interest (ROI) for which dimensions are to be measured from the image of the target object using a learned dimensional measurement model, and determines whether there is a dimension error in the ROI from the estimated dimension data using a learned dimension error determination model.

Method and apparatus for detecting dimension error

Disclosed herein are a neural-network-lightening method using a repetition-reduction block and an apparatus for the same. The neural-network-lightening method includes stacking (accumulating) an output layer (value) of either one or both of a layer constituting a neural network and a repetition-reduction block in a Condensed Decoding Connection (CDC), and lightening the neural network by reducing a feature map, generated to correspond to data stacked in the CDC, based on a preset reduction layer.

Method for neural-network-lightening using repetition-reduction block and apparatus for the same

The disclosure relates to a method and an apparatus for extracting depth information from an image. A method for extracting depth information based on machine learning according to an exemplary embodiment of the present disclosure includes generating a depth information model corresponding to at least one learning image by performing machine learning using the at least one learning image and a plurality of depth information corresponding to the at least one learning image; and extracting depth information of a target image by applying the depth information model into the target image. Embodiments of the disclosure may allow extracting precise depth information from a target image.

Depth information extracting method based on machine learning and apparatus thereof

The present invention relates to a composition for forming a hard coating layer, which may form a hard coating layer having significantly improved hardness as well as excellent flexibility such that curling is minimized.

Composition for making hard coating layer

Disclosed is a piezoelectric speaker including: a piezoelectric layer that converts electrical signals into oscillation and outputs sound; an electrode that is formed on a top or a bottom of the piezoelectric layer to apply the electrical signals to the piezoelectric layer; an acoustic diaphragm that is made of a hetero material including a first acoustic diaphragm and a second acoustic diaphragm and is attached to the bottom of the piezoelectric layer on which the electrode is formed; and a frame attached in a form enclosing a side of the acoustic diaphragm.

Piezoelectric speaker

Disclosed are a humidity sensor and a fabricating method thereof. The humidity sensor includes a substrate, an anodic aluminum oxide layer formed on the substrate and having a plurality of holes, and electrodes formed on the anodic aluminum oxide layer, in order to improve sensitivity and accuracy of the humidity sensor. Further, the fabricating method of a humidity sensor includes preparing an aluminum substrate, forming an anodic aluminum oxide layer by oxidizing the aluminum substrate, and forming electrodes on the anodic aluminum oxide layer.

Humidity sensor having anodic aluminum oxide layer, and fabricating method thereof

A target detecting system and method for detecting a target from an input image is provided. According to the target detecting system and method, when a target is detected from an input image and there are moving areas in the input image, camera movement parameters are obtained, image frames are transformed, and movement candidate areas are extracted from the image frame and the previous input image frame. In addition, image feature information is extracted from the input image, and based on the movement candidate areas and the image feature information a shape of the target is extracted. Therefore, the target can be exactly and rapidly extracted and tracked.

Target detecting system and method

A user recognizing system and method is provided. According to the user recognizing system and method, user ID and predetermined user feature information are stored, first and second user feature information are extracted from the user image data transmitted from the image input unit, and first and second probabilities that the extracted first and second user feature information determine the predetermined user are respectively generated based on the information stored at the user information database, the first user feature information being absolutely unique biometric information and the second user feature information being unique semibiometric information under a predetermined condition, and ID of the input image is finally determined by combining the first probability and the second probability. According to the user recognizing system and method, a user identity can be authenticated even when the user freely moves.

User authentication system and method thereof

Growing community of inventors

Daejeon, South Korea

Hye-Jin Kim