Abstract: Provided are an image stabilizing apparatus and method thereof. The image stabilizing apparatus performs image stabilization by using both an image sensor and a motion sensor. Image distortion and movement are stably corrected by using both the position of a feature point, which is extracted by the image sensor and image processing, and the movement position of the feature point, which is predicted by the motion sensor.

Abstract: The present invention discloses a non-invasive blood glucose measurement method, applied to noninvasive blood glucose measuring instruments including measuring hosts and fingertip measuring probes, comprising pre-storing a random forest algorithm and a neural network prediction algorithm in the measuring host; measuring energy metabolism parameters of a fingertip of an individual to be measured and transmitting the parameters to the measuring host by the fingertip measuring probe; calling the random forest algorithm to predict the blood glucose type of the energy metabolism parameters of the fingertip of the individual to be measured and calling the corresponding neural network prediction algorithm to calculate the blood glucose value of the fingertip of the individual to be measured by the measuring host. The present invention also provides a fingertip-measuring probe.

Abstract: Provided are an image stabilizing apparatus and method thereof. The image stabilizing apparatus performs image stabilization by using both an image sensor and a motion sensor. Image distortion and movement are stably corrected by using both the position of a feature point, which is extracted by the image sensor and image processing, and the movement position of the feature point, which is predicted by the motion sensor.

Abstract: A foreground extracting method is provided. The foreground extracting method includes: generating a plurality of sampling images; detecting contours from the sampling images to generate a plurality of contour images including a current frame and a previous frame; comparing first positions of a first plurality of pixels in a first decision-making area of the current frame with second positions of a second plurality of pixels in a second decision-making area of the previous frame; determining directions from the second positions to the first positions and distances between the first positions and the second positions; excluding, from the first decision-making area, at least one pixel of the first plurality of pixels in response to the distance of the at least one pixel being less than or equal to a preset critical magnitude.

Abstract: Provided are a re-wandering detecting device and method. The method includes: detecting an object and positional information about the object from an input image; determining whether the object wanders based on the positional information about the object; in response to determining that the object wanders, determining whether the object re-wanders by determining whether a database stores information about an object identical to the object detected from the input image; and providing information about wandering of the object according to whether the object re-wanders.

Abstract: Provided are a system and method for determining a color of a foreground and a computer readable recording medium therefor. The system includes: at least one processor configured to implement a motion detector which detects a motion region from an image; and a color determiner which determines the color of the foreground in the motion region based on a difference between colors of the motion region and colors of a surrounding region of the motion region, for displaying the determined foreground color with the foreground at a display device.

Abstract: Provided are a system and method for determining at least one color of a foreground and a computer readable recording medium therefor. The system includes: a motion detector configured to detect a motion region from an image of an area; and a color determiner configured to determine at least one color of the foreground included in the motion region based on a difference between at least one color of the motion region and at least one color of a background which is a region outside the motion region in the image, for displaying the foreground color with the foreground at a display device.

Abstract: Provided are a system and method for determining at least one color of a foreground and a computer readable recording medium therefor. The system includes: a motion detector configured to detect a motion region from an image of an area; and a color determiner configured to determine at least one color of the foreground included in the motion region based on a difference between at least one color of the motion region and at least one color of a background which is a region outside the motion region in the image, for displaying the foreground color with the foreground at a display device.

Abstract: Provided are a system and method for determining a color of a foreground and a computer readable recording medium therefor. The system includes: at least one processor configured to implement a motion detector which detects a motion region from an image; and a color determiner which determines the color of the foreground in the motion region based on a difference between colors of the motion region and colors of a surrounding region of the motion region, for displaying the determined foreground color with the foreground at a display device.

Abstract: A foreground extracting method is provided. The foreground extracting method includes: generating a plurality of sampling images; detecting contours from the sampling images to generate a plurality of contour images including a current frame and a previous frame; comparing first positions of a first plurality of pixels in a first decision-making area of the current frame with second positions of a second plurality of pixels in a second decision-making area of the previous frame; determining directions from the second positions to the first positions and distances between the first positions and the second positions; excluding, from the first decision-making area, at least one pixel of the first plurality of pixels in response to the distance of the at least one pixel being less than or equal to a preset critical magnitude.

Abstract: Provided are a re-wandering detecting device and method. The method includes: detecting an object and positional information about the object from an input image; determining whether the object wanders based on the positional information about the object; in response to determining that the object wanders, determining whether the object re-wanders by determining whether a database stores information about an object identical to the object detected from the input image; and providing information about wandering of the object according to whether the object re-wanders.

Abstract: Provided are an image stabilizing method and apparatus, which are capable of performing robust operations in a moving environment. The image stabilizing apparatus includes: an image pre-processor configured to receive a current image and a reference image corresponding to the current image; a feature point selector configured to select at least one feature point corresponding to a background from a plurality of feature points, comprising the background and at least one moving object, in the reference image; a motion estimator configured to estimate a motion of a current image, based on the selected feature point in the reference image and at least one corresponding feature point, corresponding to the selected feature point in the reference image, in the current image; and an image corrector configured to generate a stabilized current image by converting the current image by using the estimated motion.

Abstract: The present invention discloses a non-invasive blood glucose measurement method, applied to noninvasive blood glucose measuring instruments including measuring hosts and fingertip measuring probes, comprising pre-storing a random forest algorithm and a neural network prediction algorithm in the measuring host; measuring energy metabolism parameters of a fingertip of an individual to be measured and transmitting the parameters to the measuring host by the fingertip measuring probe; calling the random forest algorithm to predict the blood glucose type of the energy metabolism parameters of the fingertip of the individual to be measured and calling the corresponding neural network prediction algorithm to calculate the blood glucose value of the fingertip of the individual to be measured by the measuring host. The present invention also provides a fingertip-measuring probe.

Abstract: Provided are an image stabilizing method and apparatus, which are capable of performing robust operations in a moving environment. The image stabilizing apparatus includes: an image pre-processor configured to receive a current image and a reference image corresponding to the current image; a feature point selector configured to select at least one feature point corresponding to a background from a plurality of feature points, comprising the background and at least one moving object, in the reference image; a motion estimator configured to estimate a motion of a current image, based on the selected feature point in the reference image and at least one corresponding feature point, corresponding to the selected feature point in the reference image, in the current image; and an image corrector configured to generate a stabilized current image by converting the current image by using the estimated motion.