Electronics and Telecommunications Research Institute

Jang Hee Yoo

Kyo Il Chung

Yun Su Chung

Sung Uk Jung

Youn Hee Gil

Jong Gook Ko

Jin Woo Choi

Hyun Sook Cho

Kyung Hee Lee

Ki Young Moon

Ji Young Kwak

Hyung Keun Jee

Dae Sung Moon

Geon Woo Kim

Jong Wook Han

Han Sung Lee

Heung Nam Kim

Dong Myung Sul

Disclosed is a video recording apparatus for a vehicle, which includes a camera unit formed so as to change a capturing direction; a driver's viewing direction detecting unit configured to detect a driver's viewing direction; a control unit configured to control the camera unit so that the detected viewing direction corresponds to the capturing direction; and a storing unit configured to store a video obtained by the camera unit. Therefore, a video in a direction at which the driver views is obtained and stored without mounting a plurality of cameras so that it is possible to obtain a video for a situation of an accident of a vehicle of the driver or a vehicle of another driver occurring not only in the front of the driver's vehicle but also in the side of the driver's vehicle.

Video recording apparatus for vehicle and video recording method for vehicle

Disclosed are a method and apparatus for masking a privacy area of an image. The method for masking a privacy area of an image includes: detecting a privacy area required to be protected in an image; and performing masking on the image. An important area (a face area of a person, a number plate area of a vehicle, a window area of a house, etc.) detected from an image inputted through a CCTV camera can be effectively and easily encrypted, scrambled, decoded, and descrambled. Also, the position of the important area detected before or after the important area is scrambled can be maintained to be consistent without having to use a metadata file. In addition, a scrambling algorithm of the same key value can be applicable regardless of the size of the important area. As a result, the system efficiency can be enhanced by effectively protecting personal information compared with a CCTV-based video security system.

Method and apparatus for masking privacy area of image

Provided are a method and an apparatus for accurately detecting positions of eyes in an input face image. The method includes extracting a symmetric face region from a face image based on magnitude and phase of gradient in each pixel of the face image; detecting available eye positions based on brightness information of the extracted face region; verifying regions around each of the detected eye positions with a classifier which determines whether an input image is an eye image using information obtained by supervised learning on sample images. According to the present invention, faulty eye detection is prevented by removing obscuring elements such as illumination, glasses and hair from an input face image. Also, eye coordinates can be extracted more accurately using an eye classifier.

Method and apparatus for detecting eyes in face region

A face recognition and apparatus are provided. According to the method, an SVM classifier is created through machine learning on the basis of a degree of similarity of a divided facial image, and a facial image to be authenticated is normalized to a predetermined size using a center between two eyes. The normalized image is divided into more than one image in horizontal and vertical directions, respectively. Next, predetermined characteristic vectors from the divided images are extracted and a similarity vector based on a degree of similarity with respect to a registered characteristic vector is created. The similarity vector is input to the SVM classifier, so that authentication is performed.

Face recognition by dividing an image and evaluating a similarity vector with a support vector machine

An iris recognition method is provided. In the iris recognition method, binary image data is obtained by receiving eye image data and filtering the received eye image data using a predetermined threshold value. Then, candidate center search regions are searched for finding a pupil center using profile information of rows and columns of the binarized image. a pupil boundary and a center point are detected by performing a mask operation using 8 pupil boundary mask templates for each of concentric circles formed of pointes in the searched candidate center search regions as candidate pupil centers and different radiuses. An iris boundary region is detected by performing a masking operation using 6 iris boundary mask templates corresponding to 6 locations for concentric circles formed of the pupil center as an origin and different radiuses.

Iris recognition method and apparatus thereof

A virtual mouse driving apparatus and method for processing a variety of gesture commands as equivalent mouse commands based on two-handed gesture information obtained by a video camera are provided. The virtual mouse driving method includes: keeping track of an input gesture input with the video camera; removing a background portion of the input gesture image and extracting a left-hand region and a right-hand region from the input gesture image whose background portion has been removed; recognizing a left-hand gesture and a right-hand gesture from the extracted left-hand region and the extracted right-hand region, respectively, and recognizing gesture commands corresponding to the recognition results; and executing the recognized gesture commands.

Virtual mouse driving apparatus and method using two-handed gestures

A method of iris recognition using a cumulative-sum-based change point analysis and an apparatus using the same are disclosed. The method includes: transforming an iris image to a polar coordinated image having n&#xd7;m pixel size and dividing the polar coordinated image into at least one cell; grouping the divided iris images into at least one of first groups having a predetermined number of cells, and at least one of second groups each having more cells than the first group has; performing a cumulative-sum-based change point analysis using a predetermined characteristic pattern value of each cell as a representative value; and generating a pattern vector by assigning a predetermined value to a cell having the change point and assigning a different value to other cells.

Method of iris recognition using cumulative-sum-based change point analysis and apparatus using the same

Provided are a method and apparatus of detecting an eye using symmetrical and moment characteristics of an object. According to the method, an eye band is extracted from a facial image, and eye candidates each having symmetry are detected by extracting symmetrical component from the eye band. After that, a moment line integral is calculated on the basis of contrast of the eye band image and a coordinate of each of the eye candidates is inputted, so that each of the detected eye candidates is verified.

Growing community of inventors

Daejeon, South Korea

Jang Hee Yoo