Abstract: The present invention relates to a method for quantization of a color histogram bin value of an image or video, and more particularly, to a method for non-uniform quantization of a color histogram bin value of an image (or video) according to the frequency of color occurrence. The present invention has effects of effectively representing the characteristics of the color histogram of the image better as compared to the conventional art, and improving the performance of the image retrieval when the image (video) retrieval search is conducted.

Abstract: A method for designating a representative color which is expressed based on a reliability that a representative color of an image region expresses an image region is disclosed. This method includes a step for expressing a reliability of the representative color value as a color information of the image region together with a representative color value which represents the image region in a method using a color value as an information with respect to an image region, for thereby expressing a color information of an image region using a reliability and a color segmentation method of an image region.

Abstract: The present invention relates to a color space quantization descriptor structure for performing quantization of a color space in order to search a multimedia based on contents when multimedia feature information is color information, particularly when the multimedia feature information is the color information and the search is about a moving image or a still image, the color space quantization descriptor structure according to the present invention has a tree structure divided into a plurality steps of superior color spaces and subordinate color spaces, and the tree structure recursively comprises a plurality of subordinate color spaces. Accordingly, the present invention can improve performance of a still image and a moving image search apparatus, perform the quantization of a n dimensional color space such as a H, S, V, RGB, HMMD color space etc., and perform the different step quantization corresponding to each feature.

Abstract: A method of searching for images in a database system determines weights of desired image features by taking into consideration both recent user relevance feedback information and whole feedback information. The method is performed in accordance with a multimedia data structure which reflects user feedback change. According to one embodiment, the data structure includes information describing the features of a specific image, recent user feedback information when the weights of the features of the specific image are learned and determined by the user relevance feedback information, and whole feedback information when th weight of the features of the specific image are learned and determined by the user relevance feedback information. The weights of the image features are determined considering both the recent user feedback information and the whole feedback information, and the image features according to the determined weights are used for the image search.

Abstract: The present invention relates to an effect color extracting method of an image and an image original color recovering method which are capable of automatically extracting an effect color of an image pictured in accordance with an environment of a certain illumination and a color lens (or filter) and a feature of a camera, adjusting the extracted effect color and recovering an original image color of the image for thereby enhancing a performance of an image search.

Abstract: The present invention relates to an effect color extracting method of an image and an image original color recovering method which are capable of automatically extracting an effect color of an image pictured in accordance with an environment of a certain illumination and a color lens (or filter) and a feature of a camera, adjusting the extracted effect color and recovering an original image color of the image for thereby enhancing a performance of an image search.

Abstract: A method of quantization a color space is disclosed.

Abstract: Disclosed is a content-based multimedia data retrieval method. The method according to the present invention comprises the steps of extracting color distortion information from multimedia data, setting weight of color-based descriptors on the basis of the extracted color distortion information, and extracting a distortion sensitivity by differently applying the weight according to the color distortion information. The method according to the present invention can improve a multimedia data retrieval performance and solve a problem of color distortion due to a different illumination or characteristics of a device.

Abstract: A multimedia data keyword management method and a keyword data structure which can be applied to a search system is disclosed. According to the present invention, the search system includes a data table having a plurality of multimedia objects mapped with one or more keywords and can additionally register a new keyword to a data table through a feedback of a user according to a search result when a particular multimedia object is to be searched with a specific keyword. Each newly registered keyword can be weighted based on the keyword feedback authorization level of the user providing the feedback.

Abstract: A method for designating a representative color which is expressed based on a reliability that a representative color of an image region expresses an image region is disclosed. This method includes a step for expressing a reliability of the representative color value as a color information of the image region together with a representative color value which represents the image region in a method using a color value as an information with respect to an image region, for thereby expressing a color information of an image region using a reliability and a color segmentation method of an image region.

Abstract: A method for designating a representative color which is expressed based on a reliability that a representative color of an image region expresses an image region is disclosed. This method includes a step for expressing a reliability of the representative color value as a color information of the image region together with a representative color value which represents the image region in a method using a color value as an information with respect to an image region, for thereby expressing a color information of an image region using a reliability and a color segmentation method of an image region.

Abstract: A method of searching or browsing multimedia data which can effectively search or browse an image is disclosed. In the present method, the searching or browsing is performed in consideration of at least one of a reliability information on a weight of a feature of an input multimedia data and an authority code. According to the method, the system selects reference multimedia data, and searches the multimedia data using a weight of a feature and/or a feature element of the input multimedia data. A user gives feedback on the relevance of the searched or browsed multimedia data, and the system calculates a new weight using the relevance information. Thus, the system updates and maintains new weights of features and/or feature elements.

Abstract: A method for designating a local representative color value and automatically determining image searching algorithm for a color based image searching system is disclosed. A method for designating a local representative color values generally includes the steps of dividing a color image area; and obtaining a color histogram for each block, obtaining a color group from hue histograms of each block, or obtaining a maximum color group value to designate the representative color value. Also, a method determining a search algorithm generally includes the steps of detecting the number of color blocks CB having color information from the blocked information of a reference image; comparing the number of the color blocks with a determined reference value and assigning different weights to at least two search algorithm according to the comparison results; and performing a comparison search of an image by the search algorithm based on the determined weight.

Abstract: The present invention relates to a multimedia search method for searching multimedia objects using color histogram. The present invention provide a multimedia retrieval method and a multimedia feature structure capable of accelerating accurate and efficient multimedia object search by adopting various meaning reflection level according to each bin value of the color histogram. In the present invention, the color groups are classified into the solid, neutral, and gray levels, and the binarization standard point is determined at each color group such that the color distribution can be effectively represented in the binary histogram, resulting in improving the retrieval performance of binary color histogram which is a shortcoming in the conventional binary histograms in addition to remaining the high efficiency of the binary color histogram.

Abstract: A method of detecting a specific object in an image signal both efficiently and accurately is disclosed. According to the present invention, an object is first detected from an image or frame using a general feature of the object and in the following image or frame, the object is detected using an object-dependant feature. Also, when detecting a plurality of objects or portions of the object, a full color range of the specific object is determined, and color range sections of the full color range is used to detect the object.

Abstract: An efficient method for retrieving an image using multiple features for an image subregion is disclosed. The present invention obtains a regional representative color for the subregions and uses the regional representative color during a retrieval of a similar image if the regional representative color is reliable. Otherwise, a feature information other than the regional representative color is used.

Abstract: A method of searching or browsing multimedia data which can effectively search or browse an image is disclosed. In the present method, the searching or browsing is performed in consideration of at least one of a reliability information on a weight of a feature of an input multimedia data and an authority code. According to the method, the system selects reference multimedia data, and searches the multimedia data using a weight of a feature and/or a feature element of the input multimedia data. A user gives feedback on the relevance of the searched or browsed multimedia data, and the system calculates a new weight using the relevance information. Thus, the system updates and maintains new weights of features and/or feature elements.

Abstract: A new color model HMMD is disclosed based upon hue, the shade, the tone, the tint and the brightness of a color, and a color quantizing method using the HMMD color space. The present invention regards the colors adjacent to a given color in the color space as the neighboring colors to consider indices of the neighboring colors as the partial values according to the distance. Accordingly, the present invention can accomplish a color quantization close to the change of the color sensed by the human eye, thereby capable of enhancing a performance of the image searching system based on content.

Abstract: An automatic control device and method for an adaptive display speed of a motion video is disclosed. The present invention is capable of adaptively controlling acceleration and speed change of a motion video according to the variation rate of the motion video within the interval of fast forward or slow motion modes.

Abstract: A system for searching a particular character in a motion picture is disclosed comprising a recording medium on which the motion picture is recorded, the recorded motion picture being reproduced and displayed by a reproducing mechanism. The recording medium contains video information of a character table and location information indicative of scenes or sections in which a particular character appears. Thus, the system automatically searches and displays scenes and sections in which a character appears in the motion picture based upon the character table and the location information.