Abstract: A method and an image processing apparatus for image-based object feature description are provided. In the method, an object of interest in an input image is detected and a centroid and a direction angle of the object of interest are calculated. Next, a contour of the object of interest is recognized and a distance and a relative angle of each pixel on the contour to the centroid are calculated, in which the relative angle of each pixel is calibrated by using the direction angle. Then, a 360-degree range centered on the centroid is equally divided into multiple angle intervals and the pixels on the contour are separated into multiple groups according to a range covered by each angle interval. Afterwards, a maximum among the distances of the pixels in each group is obtained and used as a feature value of the group. Finally, the feature values of the groups are normalized and collected to form a feature vector that serves as a feature descriptor of the object of interest.

Abstract: A method and an image processing apparatus for image-based object feature description are provided. In the method, an object of interest in an input image is detected and a centroid and a direction angle of the object of interest are calculated. Next, a contour of the object of interest is recognized and a distance and a relative angle of each pixel on the contour to the centroid are calculated, in which the relative angle of each pixel is calibrated by using the direction angle. Then, a 360-degree range centered on the centroid is equally divided into multiple angle intervals and the pixels on the contour are separated into multiple groups according to a range covered by each angle interval. Afterwards, a maximum among the distances of the pixels in each group is obtained and used as a feature value of the group. Finally, the feature values of the groups are normalized and collected to form a feature vector that serves as a feature descriptor of the object of interest.

Abstract: An image dynamic range compression with local contrast enhancement method for an image processing device is provided. The method includes the following steps. A plurality of input pixels of an image including a first input pixel are received, and an input luminance pixel value of each of the input pixels as well as a darkness intensity level of the image are obtained. A filter result of the first input pixel is obtained according to filter computation on the input luminance pixel values; an image-related parameter is obtained according to image-related computation on the darkness intensity level. The image-related parameter, the filter result of the first input pixel, and the input luminance pixel value of the first input pixel are transformed into an output luminance pixel value of the first input pixel according to a non-linear intensity transfer function and a dynamic range compression with local contrast enhancement algorithm.

Abstract: An image dynamic range compression method for an image processing device is provided. The method includes receiving a plurality of input pixels which include a first input pixel, obtaining a luminance pixel value of each of the input pixels, executing a filter execution according to the luminance pixel values of the input pixels to obtain a filter result corresponding to the first input pixel, transforming the filter result into a function result according to a function, and obtaining an output luminance pixel value of the first input pixel according to the luminance pixel value of the first input pixel and a transforming ratio between the function result and the filter result. Accordingly, the method reserves the details in an image and color information, and increases the execution speed.

Abstract: An image dynamic range compression with local contrast enhancement method for an image processing device is provided. The method includes the following steps. A plurality of input pixels of an image including a first input pixel are received, and an input luminance pixel value of each of the input pixels as well as a darkness intensity level of the image are obtained. A filter result of the first input pixel is obtained according to filter computation on the input luminance pixel values; an image-related parameter is obtained according to image-related computation on the darkness intensity level. The image-related parameter, the filter result of the first input pixel, and the input luminance pixel value of the first input pixel are transformed into an output luminance pixel value of the first input pixel according to a non-linear intensity transfer function and a dynamic range compression with local contrast enhancement algorithm.

Abstract: An image dynamic range compression method for an image processing device is provided. The method includes receiving a plurality of input pixels which include a first input pixel, obtaining a luminance pixel value of each of the input pixels, executing a filter execution according to the luminance pixel values of the input pixels to obtain a filter result corresponding to the first input pixel, transforming the filter result into a function result according to a function, and obtaining an output luminance pixel value of the first input pixel according to the luminance pixel value of the first input pixel and a transforming ratio between the function result and the filter result. Accordingly, the method reserves the details in an image and color information, and increases the execution speed.

Abstract: An image processing method includes the following steps. First, noise of a first image is filtered, and the first image is converted to obtain a first luminance signal. Second, a color space converting process is performed upon the first image to obtain a second image. Third, the second image is stored and outputted. Fourth, noise of the second image is filtered, and the second image is converted to obtain a second luminance signal. Fifth, a linear computing is performed to obtain a third image. Sixth, an error compensation is performed upon the third image and the second image, and the third image is outputted. Seventh, the color space converting process is performed to obtain and output a fourth image. The linear computing and the error compensation are performed upon a single image to filter the noise of the images, and thus a load of a system may be decreased.

Abstract: The invention relates to a method and module for regulating color distribution. In this method, a reference point in a first gamut and a second reference point in a second gamut are found, and then the first gamut is converted to the second gamut based on the first and second reference point.

Abstract: An image processing method and an image processing system adapted to processing image information with multiple process pixels are disclosed. The image processing method includes steps of: setting a group of parameters; establishing a luminance lookup table; establishing a chrominance-luminance lookup table; retrieving the image information; determining a format of the image information; and if the format of the image is a first format, utilizing the chrominance-luminance lookup table to generate an adjusted chrominance and a first adjusted luminance corresponding to one of the process pixels; if the format of the image is a second format, utilizing the chrominance-luminance lookup table and the luminance lookup table to generate an adjusted chrominance, a first adjusted luminance, and a second adjusted luminance corresponding to one of the process pixels.

Abstract: The invention relates to a method and module for regulating saturation degree. In this method, a curvature of a special function in all position is regulated by a saturation parameter to obtain a regulated function. A color input signal is assigned as an independent variable of the regulated function to calculate a color output signal corresponding to the color input signal.

Abstract: An image processing method includes the following steps. First, noise of a first image is filtered, and the first image is converted to obtain a luminance signal. Second, the first image is stored and outputted. Third, a color space converting process is performed upon the first image according to the luminance signal to obtain a second image. Fourth, a linear computing is performed upon the second image to obtain a third image. Fifth, the color space converting process is performed according to a third image and the luminance signal to obtain and output a fourth image. Sixth, an error compensation is performed upon the first image and the fourth image, and the fourth image is outputted. Accordingly, a linear operating process and error compensation processing is performed upon the single image to filter the noise of the image, and thus a load of the system is reduced.

Abstract: A nursing system of the present invention can position where a person to be nursed through a sensor network widely deployed in an environment, instantaneously detect if the person to be nursed has an accident, and forward a message to inform a relative or medical staff. An autonomous robot will actively move beside the person to be nursed and transmit real-time images to a remote computer or PDA so that the relative or medical staff can swiftly ascertain the situation of the person to be nursed and the person to be nursed in case of emergency can be rescued as soon as possible.

Abstract: The invention relates to a method and a module for regulating luminance. In this method, a gray-level input signal is received and a power operation is performed on the gray-level input signal by a gamma parameter to obtain a first regulation scale. Then, the gray-level input signal is regulated according to the first regulation scale to obtain a gray-level output signal.

Abstract: An image processing method and an image processing system adapted to processing image information with multiple process pixels are disclosed. The image processing method includes steps of: setting a group of parameters; establishing a luminance lookup table; establishing a chrominance-luminance lookup table; retrieving the image information; determining a format of the image information; and if the format of the image is a first format, utilizing the chrominance-luminance lookup table to generate an adjusted chrominance and a first adjusted luminance corresponding to one of the process pixels; if the format of the image is a second format, utilizing the chrominance-luminance lookup table and the luminance lookup table to generate an adjusted chrominance, a first adjusted luminance, and a second adjusted luminance corresponding to one of the process pixels.

Abstract: An image processing method includes the following steps. First, noise of a first image is filtered, and the first image is converted to obtain a luminance signal. Second, the first image is stored and outputted. Third, a color space converting process is performed upon the first image according to the luminance signal to obtain a second image. Fourth, a linear computing is performed upon the second image to obtain a third image. Fifth, the color space converting process is performed according to a third image and the luminance signal to obtain and output a fourth image. Sixth, an error compensation is performed upon the first image and the fourth image, and the fourth image is outputted. Accordingly, a linear operating process and error compensation processing is performed upon the single image to filter the noise of the image, and thus a load of the system is reduced.

Abstract: An image processing method includes the following steps. First, noise of a first image is filtered, and the first image is converted to obtain a first luminance signal. Second, a color space converting process is performed upon the first image to obtain a second image. Third, the second image is stored and outputted. Fourth, noise of the second image is filtered, and the second image is converted to obtain a second luminance signal. Fifth, a linear computing is performed to obtain a third image. Sixth, an error compensation is performed upon the third image and the second image, and the third image is outputted. Seventh, the color space converting process is performed to obtain and output a fourth image. The linear computing and the error compensation are performed upon a single image to filter the noise of the images, and thus a load of a system may be decreased.

Abstract: The invention relates to a method and module for regulating color distribution. In this method, a reference point in a first gamut and a second reference point in a second gamut are found, and then the first gamut is converted to the second gamut based on the first and second reference point.

Abstract: The invention relates to a method and module for regulating saturation degree. In this method, a curvature of a specific function in all position is regulated by a saturation parameter to obtain a regulated function. A color input signal is substituted to the regulated function to calculate a color output signal corresponds to the color input signal.

Abstract: The invention relates to a method and a module for regulating luminance. In this method, a gray-level input signal is received and a power operation is performed on the gray-level input signal by a gamma parameter to obtain a first regulation scale. Then, the gray-level input signal is regulated according to the first regulation scale to obtain a gray-level output signal.

Abstract: A computer having a CPU, a chipset and a graphic card is provided. The CPU is coupled to the graphic card through the chipset. The graphic card receives an output video from the chipset. The output video has a plurality of images, and each of the images has a plurality of pixels. The graphic card calculates the pixels of the image to obtain brightness values of the each pixels, and the brightness values are calculated to obtain brightness mapping values according to a non-linear function. Consequently, the graphic card is able to adjust a brightness contrast of each of the images so as to obtain a renewed output video.