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.

Abstract: A method of detecting a specific object in an image signal is disclosed. In the present invention, the final object region can be determined by selecting one of two object regions detected by different methods or by combining the two object regions with assigned weights.

Abstract: A content-based video story browsing system is disclosed including setting and representing relations between objects and places of the story. A content-based video story browsing system includes the steps of selecting objects and places as factors organizing contents of a video story and setting a relational graph relating the objects to corresponding places; setting a video story section and a representative scene as an events of contents development corresponding to the relations of the objects and the places; and displaying the video story section and the representative scene and its contents as browsing information corresponding to the relation selected from the relational graph.

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: An image search method comprising the step of searching for a desired image to be found, on the basis of an image created by a user as a query image, the step of allowing the user to select one or more images similar to the desired image from among search results for the desired image, and the step of designating the selected similar images as query images and re-searching for the desired image on the basis of the designated query images.

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 discloses a method for setting a dominant color using a spatial coherency in order to improve performance of an image search function, describing an image region based on several dominant colors, a frequency of each dominant color, and a spatial coherency (SC) of the dominant color. In the method according to the present invention, the spatial coherency is non-uniformly quantized based on a predetermined threshold. According to one embodiment of the present invention, the spatial coherency (SC) is ranged from 0 to 1 and the threshold is set to 0.70.

Abstract: Disclosed is a multimedia searching method, which can achieve a high performance and provide a interoperability by defining a standard histogram that can be mutually searched, and optimizing the histogram for each application.

Abstract: A color space structure and quantizing method is disclosed. Upon conversion from the RGB color space into HSV color space, a difference value S′ (S′=max−min) is obtained by varying the maximum value of the saturation S in accordance with the value V resulting in a HS′V color space where the difference value S′ forms one axis of the color coordinate, such that all of color areas are evenly distributed and the variation of color is uniformly displayed.

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: The present invention relates to a multimedia retrieval system and a method thereof which is capable of performing a multimedia data retrieval among different systems using color histograms constructed with different color spaces and color quantization methods, in particular to a content-based multimedia retrieval system and a method thereof which is capable of retrieving multimedia data among different systems, by extracting or converting a color histogram of a query image or a color histogram of an image to be retrieved into a color histogram of the same color space and color quantization method each other, and using the extracted or converted color histogram.

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 recurrently comprises a plurality of subordinate color spaces. Accordingly, the present invention can improve performace 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.