Data processing: database and file management or data structures – Database design – Data structure types
Reexamination Certificate
1999-09-30
2003-02-25
Coby, Frantz (Department: 2171)
Data processing: database and file management or data structures
Database design
Data structure types
C707S793000, C707S793000, C707S793000, C707S793000, C707S793000
Reexamination Certificate
active
06526400
ABSTRACT:
BACKGROUND OF THE INVENTION
The present invention relates to an information search apparatus and method for searching information on the basis of an input query word. More specifically, the present invention relates to an information search apparatus and method for managing a plurality of kinds of multimedia information, and searching the managed multimedia information for desired multimedia information, and a computer readable memory.
A conventional information search apparatus, which searches multimedia information, e.g., image information, makes a search using data (keywords) derived from subjective evaluation results of one or a plurality of persons for test images, physical image features extracted from images, and the like.
When an image is searched for using a keyword, a required image is obtained by matching a given keyword with that corresponding to the image. Also, a scheme for obtaining an image, that cannot be obtained by full-word matching with an input keyword, by matching not only the input keyword but also an associated keyword associated with the input keyword with a keyword corresponding to an image, is proposed. Furthermore, a search scheme which obtains an image with similar color information by detecting a correspondence between the input keyword and color information using, e.g., color information of images is proposed.
In the image search using keywords, an impression that a person receives upon watching an image, or key information linked with the impression is appended to image information and is used in search. As the key information, words that express impressions evoked by images such as “warm”, “cold”, and the like, and words that represent objects in drawn images such as “kitty”, “sea”, “mountain”, and the like are appended as keywords. Also, local image feature components on drawn images are subjectively evaluated and are often appended as key information. For example, information that pertains to a color such as “red”, “blue”, and the like, information that pertains to a shape such as “round”, “triangular”, “sharp”, and the like, and information that pertains to a texture such as “sandy”, “smooth”, and the like are expressed using words and icons, are appended to images as key information, and are used in search.
In a system in which physical image feature amounts are extracted from images, and are used in image search, image features include local colors painted on images, overall color tones, and shapes, compositions, textures, and the like of objects on drawn images. An image feature amount is extracted from segmented regions or blocks obtained by segmenting the overall image into regions based on color information, or segmenting the image into blocks each having a given area, or is extracted from the entire image. Physical image features include, e.g., color information, density distribution, texture, edge, region, area, position, frequency distribution, and the like of an image.
However, in the above search scheme, when an image including a keyword that matches the input query word is searched for, images which do not match the search request of the searcher are often obtained. Especially, when an image search is made using an abstract query word such as a “refreshing” image, images found by the search are limited. To solve this problem, a search may be made by unfolding the query word “refreshing” to keywords which are associated with that query word. However, when such scheme is used, images which are not “refreshing” may be mixed in search results.
In this manner, the operator cannot designate query conditions for obtaining a desired search result with respect to a search request indicated by the input keyword, and cannot obtain an intended search result. For example, even when the operator wants to find only images having “refreshing” feature patterns with respect to a search request “refreshing”, images having content words associated from the search request “refreshing” such as a music score of a “refreshing” music, a “refreshing” athlete”, and the like, are presented, i.e., images which do not match the search request are presented.
In place of a query word, a query image may be input, and a search may be made using its feature amount. However, in this case, a query image which reflects the searcher's will must be prepared, and it is difficult to select a query image, resulting in poor operability.
SUMMARY OF THE INVENTION
The present invention has been made in consideration of the above-mentioned problems, and has as its object to provide an image search method and apparatus which can extract the information wanted with high precision with respect to an input query word.
In order to achieve the above object, according to one aspect of the present invention, there is provided an information search apparatus for searching information based on an input query word, comprising first search means for determining a query keyword on the basis of the query word, and searching information on the basis of the query keyword, second search means for determining a feature amount corresponding to the query word, and searching information on the basis of the feature amount, setting means for setting a search weight to be assigned to search results of the first and second search means, and integration means for integrating search results obtained by the first and second search means in accordance with the search weight set by the setting means.
In order to achieve the above object, according to another aspect of the present invention, there is provided an information search method for searching information based on an input query word, comprising the first search step of determining a query keyword on the basis of the query word, and searching information on the basis of the query keyword, the second search step of determining a feature amount corresponding to the query word, and searching information on the basis of the feature amount, the setting step of setting a search weight to be assigned to search results in the first and second search steps, and the integration step of integrating search results obtained in the first and second search steps in accordance with the search weight set in the setting step.
Other features and advantages of the present invention will be apparent from the following description taken in conjunction with the accompanying drawings, in which like reference characters designate the same or similar parts throughout the figures thereof.
REFERENCES:
patent: 5778368 (1998-07-01), Hogan et al.
patent: 5842206 (1998-11-01), Sotomayor
patent: 5884309 (1999-03-01), Vanechanos, Jr.
patent: 5893092 (1999-04-01), Driscoll
patent: 5893095 (1999-04-01), Jain et al.
patent: 5983237 (1999-11-01), Jain et al.
patent: 6078916 (2000-06-01), Culliss
patent: 6085186 (2000-07-01), Christianson et al.
patent: 6088692 (2000-07-01), Driscoll
patent: 6102969 (2000-08-01), Christianson et al.
patent: 6122628 (2000-09-01), Castelli et al.
patent: 6122647 (2000-09-01), Horowitz et al.
patent: 6175829 (2001-01-01), Li et al.
patent: 6182068 (2001-01-01), Culliss
patent: 6226636 (2001-05-01), Adel-Mottaleb et al.
patent: 6249784 (2001-06-01), Macke et al.
patent: 6347313 (2002-02-01), Ma et al.
Mukherjea, Sougata et al., “Visualizing World-Wide Web Search Engine Results”, Proceedings of the 1999 IEEE International Conference on Information Visualization, Jul. 14-16, 1999, pp. 400-405.
Yanai, Keiji, “An Automatic Image-Gathering System for the World-Wide Web by Integration of Keywords and Image Features”, Proceedings, Fourth International Conference on Computational Intelligence and Multimedia Applications, Oct. 2001, pp. 303-307.
Chung-Sheng Li, Mohan, R., Smith, J.R., Multimedia Content description in the InfoPyramid,. Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing Volume; 6, May 12-15, 1998, pp.: 3789-3792.
Hjelsvold, R., Midtsraum, R., Sandsta, O., Searching and browsing a Shared Video Database, Proceedings., International Workshop on Multi-Media Database Management Systems, 1995., Aug. 28-
Kobayashi Yuji
Takata Tomomi
Canon Kabushiki Kaisha
Coby Frantz
Fitzpatrick ,Cella, Harper & Scinto
LandOfFree
Information search apparatus and method does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Information search apparatus and method, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Information search apparatus and method will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3178701