Abstract: A method of detecting a facial image includes pre-processing an image; and detecting a face region from the pre-processed image to create facial records of the detected face region. Further, the method of detecting the facial image includes detecting the facial image by creating coordinates of the face and eyes in the input image by using the facial records.

Abstract: A multi-image acquisition apparatus for use in a biometrics system includes a light splitting filter for reflecting or transmitting multi-image lights representing an image of a target subject provided along an identical light path into different bands; a first image sensor for imaging an iris area by capturing a fraction of the multi-image light which has been transmitted through the light splitting filter; and a second image sensor for imaging a facial area by capturing a fraction of the multi-image light which has been reflected from the light splitting filter. The apparatus further includes a control module for controlling the first image sensor and the second image sensor and providing the images obtained by the first sensor and second sensor for image recognition.

Abstract: 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×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.

Abstract: 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.

Abstract: A user authentication method and apparatus using a face image are provided. The method includes transforming a face image in a normalized spatial domain into frequency-domain data, extracting valid transform coefficients from the frequency-domain data based on energy-concentrated region information, extracting a feature vector from the extracted valid transform coefficients, and performing user authentication by comparing the extracted feature vector with a previously registered feature vector. Accordingly, it is possible to perform user authentication using a face image while using a minimum data dimension, thereby improving the speed and precision thereof.

Abstract: Provided is an apparatus and method for automatically controlling power of a video appliance. The apparatus for automatically controlling power of a video appliance includes an image input unit for capturing a viewer's posture, a posture detection unit for detecting posture information from the image captured by the image input unit, a horizontal-level calculation unit for calculating a horizontal level by using the posture information detected by the posture detection unit and comparing the calculated horizontal level with a preset reference horizontal level, an alert-sound output unit for outputting an alert sound corresponding to the horizontal level compared by the horizontal-level calculation unit; and a power-signal transceiver unit for outputting a power-off signal to the video appliance corresponding to the horizontal level compared by the horizontal-level calculation unit.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.