Abstract: Disclosed is a stereo matching method for calculating disparity from binocular images. The stereo matching method extracting distance information of objects included in images by using binocular images, includes receiving the binocular images acquired from a first camera and a second camera for acquiring the binocular images; processing the images so as to increase contrast between objects and background objects included in the received images by using a predetermined first algorithm; and performing, stereo matching using the processed images. An exemplary embodiment of the present invention outputs a disparity map in which objects and background are divided, thereby robustly recognizing a person or obstacles.

Abstract: Disclosed are a method and an apparatus for controlling power of a display device using a frontal face detecting device. The method for controlling power of a display device includes: determining whether a face of a user is present in front of the display device; confirming a power state of the display device; and repeatedly performing the determining of whether the face of a user is present according to determined presence of the face and the confirmed power state to control power of the display device. The method intelligently recognizes a use purpose of a user from the display device, thereby managing power of the display device, and controlling power of the display device without requiring a separate action by a user for managing device power.

Abstract: Disclosed are an apparatus and a method for extracting an edge to be used for extracting a feature point of an object in an image. The present invention proposes an image edge extracting apparatus and method that remove noise in an input image, calculate a gradient of an image in a noise-removed image, measure magnitude of the gradient, extract an edge having a maximum thickness value, and then calculate a threshold using a ratio of the extracted edge, and detect a final edge robust against noise based on the threshold.

Abstract: An image matching apparatus includes a bilateral filter that filters a left image and a right image to output a second left image and a second right image; a census cost calculation unit performing census transform on a window based on a first pixel of the second left image and a window based on a second pixel of the second right image to calculate a census cost corresponding to a pair of pixels of the first and second pixels; a support weight calculation unit obtaining support weights of the left and right images or the second left and second right images; a cost aggregation unit obtaining energy values of nodes corresponding to the pair of pixels of the first and second pixels using the census cost and the support weights; and a dynamic programming unit performing image matching using dynamic programming by the energy values of each node obtained.

Abstract: An image-based hand detection apparatus includes a hand image detection unit for detecting a hand image corresponding to a shape of a hand clenched to form a fist from an image input. A feature point extraction unit extracts feature points from an area, having lower brightness than a reference value, in the detected hand image. An image rotation unit compares the feature points of the detected hand image with feature points of hand images stored in a hand image storage unit, and rotates the detected hand image or the stored hand images. A matching unit compares the detected hand image with the stored hand images and generates a result of the comparison. If at least one of the stored hand images is matched with the detected hand image, a hand shape recognition unit selects the at least one of the stored hand images as a matching hand image.

Abstract: The system for detecting a face pattern from an input image includes a window extraction unit, a cost calculation unit, and a face pattern discrimination unit. The window extraction unit receives a pre-processed image corresponding to the input image to scan the preprocessed image in a certain window size, and parallelly outputs pre-processing coefficient values corresponding to the scanned pre-processed image. The cost calculation unit parallelly receives the pre-processing coefficient values corresponding to the window size, calculates cost values corresponding to the pre-processed coefficient values, and sums the cost values. The face pattern discrimination unit compares the sum of the cost values with a preset threshold value and discriminates if the pre-processed image corresponding to the window size is the face pattern.

Abstract: Provided are a human recognition apparatus and a human recognition method identifying a user based on a walking pattern. The human recognition apparatus includes a detecting unit detecting a vibration according to a user's walking, and outputting an electric signal, a pattern calculating unit acquiring a walker's walking pattern from the electric signal, and a user determining unit comparing the walking pattern with a previously measured reference data by user and identifying the user based on the comparison result. The human recognition apparatus and the human recognition method are robust against peripheral noise and can increase an acceptance rate through a simple structure and procedure by using the waling pattern, which is one-dimensional time information requiring no vast data throughput, as the user identification data.

Abstract: A robot vision system for outputting a disparity map includes a stereo camera for receiving left and right images and outputting a disparity map between the two images; an encoder for encoding either the left image or the right image into a motion compensation-based video bit-stream; and a decoder for extracting an encoding type of an image block, a motion vector, and a DCT coefficient from the video bit-stream. Further, the system includes a person detector for detecting and labeling person blocks in the image using the disparity map between the left image and the right image, the block encoding type, and the motion vector, and detecting a distance from the labeled person to the camera; and an obstacle detector for detecting a closer obstacle than the person using the block encoding type, the motion vector, and the DCT coefficient extracted from the video bit-stream, and the disparity map.