US20040064526A1 - Method of searching or browsing multimedia data and data structure - Google Patents

Method of searching or browsing multimedia data and data structure Download PDF

Info

Publication number
US20040064526A1
US20040064526A1 US10673281 US67328103A US2004064526A1 US 20040064526 A1 US20040064526 A1 US 20040064526A1 US 10673281 US10673281 US 10673281 US 67328103 A US67328103 A US 67328103A US 2004064526 A1 US2004064526 A1 US 2004064526A1
Authority
US
Grant status
Application
Patent type
Prior art keywords
information
multimedia data
weight
user
method
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Abandoned
Application number
US10673281
Inventor
Jin Lee
Hyeon Kim
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
LG Electronics Inc
Original Assignee
LG Electronics Inc
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F21/00Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/30Information retrieval; Database structures therefor ; File system structures therefor
    • G06F17/30244Information retrieval; Database structures therefor ; File system structures therefor in image databases
    • G06F17/30247Information retrieval; Database structures therefor ; File system structures therefor in image databases based on features automatically derived from the image data
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/30Information retrieval; Database structures therefor ; File system structures therefor
    • G06F17/30244Information retrieval; Database structures therefor ; File system structures therefor in image databases
    • G06F17/30247Information retrieval; Database structures therefor ; File system structures therefor in image databases based on features automatically derived from the image data
    • G06F17/30256Information retrieval; Database structures therefor ; File system structures therefor in image databases based on features automatically derived from the image data using a combination of image content features
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/30Information retrieval; Database structures therefor ; File system structures therefor
    • G06F17/30244Information retrieval; Database structures therefor ; File system structures therefor in image databases
    • G06F17/30274Information retrieval; Database structures therefor ; File system structures therefor in image databases by browsing
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/30Information retrieval; Database structures therefor ; File system structures therefor
    • G06F17/30244Information retrieval; Database structures therefor ; File system structures therefor in image databases
    • G06F17/3028Information retrieval; Database structures therefor ; File system structures therefor in image databases data organisation and access thereof
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y10TECHNICAL SUBJECTS COVERED BY FORMER USPC
    • Y10STECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y10S707/00Data processing: database and file management or data structures
    • Y10S707/99931Database or file accessing
    • Y10S707/99932Access augmentation or optimizing
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y10TECHNICAL SUBJECTS COVERED BY FORMER USPC
    • Y10STECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y10S707/00Data processing: database and file management or data structures
    • Y10S707/99931Database or file accessing
    • Y10S707/99933Query processing, i.e. searching
    • Y10S707/99935Query augmenting and refining, e.g. inexact access
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y10TECHNICAL SUBJECTS COVERED BY FORMER USPC
    • Y10STECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y10S707/00Data processing: database and file management or data structures
    • Y10S707/99931Database or file accessing
    • Y10S707/99933Query processing, i.e. searching
    • Y10S707/99936Pattern matching access
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y10TECHNICAL SUBJECTS COVERED BY FORMER USPC
    • Y10STECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y10S707/00Data processing: database and file management or data structures
    • Y10S707/99931Database or file accessing
    • Y10S707/99939Privileged access

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.

Description

    BACKGROUND OF THE INVENTION
  • 1. Field of the Invention [0001]
  • The present invention relates to a method of searching or browsing data, and more particularly to a method of searching or browsing multimedia data such as an image or video. [0002]
  • 2. Background of the Related Art [0003]
  • Recently, technology for digital image signal processing has been greatly developed and has been applied in various fields. For example, the digital image signal processing technology may be used in a search system for automatically editing only the face of a specific character in a moving picture file of a movie or drama, in a security system for permitting access to only persons registered in the system, or in a search system for searching a particular data from an image or video detected by a detection system. The performance of such systems basically depend on the accuracy and speed of detecting or searching the desired object. Accordingly, various image searching methods have been proposed in the related art. [0004]
  • An image search system which detects a degree of similarity with an image to be searched utilizing features such as color, texture or shape is disclosed in U.S. Pat. No. 5,579,471 entitled “An image query system and method.” Depending upon the image to be searched, the importance of a feature may vary and within one particular feature such as the color, the importance of a feature element such as the red or green color may also vary. However, the above searching system does not take into consideration the different importance of features or feature elements for each image to be searched. [0005]
  • In another searching method entitled “Virage image search engine” (www.virage.com), a user directly inputs the level of importance for features such as the color, texture and shape by assigning weight values. Although an image may be searched according to an importance of a feature using this method, it may be difficult for a user to determine the importance of features. [0006]
  • Therefore, Yong Rui in “Relevance feedback techniques in interactive” SPIE Vol.3312, discloses a method in which images similar to a reference image are found and the importance of features or weight for features are automatically obtained by calculating the similarities among the found images. However, the weight importance information is not maintained after a search for a specific image is finished and must be calculated for each image search, even for a same image. [0007]
  • In the image search and browsing system or the video (moving image) search and browsing system of the related art, information which describes a particular feature of an image or video data is utilized to perform a more effective search or browsing of the multimedia data. For example, in the image query system, an image may be divided into a plurality of regions and a representative color of each region may be utilized as a feature information of the image, or a whole color histogram of the image may be utilized as a feature information. Thereafter, two images are compared to calculate a similarity based upon the feature information and a determination is made whether the two images are similar. [0008]
  • Also, a user may wish to search and view a section of a video in which a specific character appears or a specific event occurs. At this time, a key frame representing a specific event may be utilized to perform a search and browsing of the video. Moreover, in recent searching and browsing methods, a key frame and a key segment have been defined utilizing an upper level feature information and a lower level feature information. This type of multimedia data search and browsing method may use weight information which indicates a degree of importance or may directly or indirectly use group information which was obtained in advance by grouping similar multimedia data. Such weight information or group information may be predefined in advance by an expert or may be a feature information variably modified by user feedback. [0009]
  • Furthermore, when browsing the multimedia data such as an image or video, the whole or a portion of the original multimedia data can be displayed depending upon a user request or upon a resource condition of the hardware. When portions of the original multimedia data are displayed, weight values are assigned to each portion such that an important portion among the whole data may be preferentially displayed. This weight value may be a varied by a user feedback or defined in advance by an expert. [0010]
  • In U.S. Pat. Nos. 5,020,019 and 5,297,042, information which describes a user preference is utilized to provide a better service for each user. For example, for a movie or video data, the information may include user preference such as action movie, drama or sports. In another example, users may have a different preference and meaning for keywords used most frequently in a keyword search. Therefore, each user can perform a more effective search if weights of keywords used often by a user is assigned differently according to the user preference. Such user preference may be obtained using search conditions and history of previous searches by the user. The information which depends on a user preference may also be varied and updated. [0011]
  • Although the variable feature information may be sufficient for some searching and browsing of multimedia data, when the feature information which includes the weight values is predefined by an expert, the reliability may vary depending upon the trustworthiness of an expert and/or a number of expert opinions used in defining the variable information. In other words, even if the feature information describing a feature of the multimedia data is defined in advance by an expert group, the reliability of the feature information defined for a same image may be inconsistent depending upon the skill of the expert. Similarly, when the feature information is trained by a user feedback, the reliability may vary depending upon the number and accuracy of feedbacks. For example, if two images are incorrectly judged to be similar by a user after a search, such information would be fed back and adversely affect the training of the feature information. [0012]
  • In addition, a user preference input by a new user may be different from the feature information recommended by a server. In such case, the system should assign appropriate weights to the user preference information depending upon the reliability of the user. Finally, as different users gives different feedback to the system, if the reliability of the existing feature information is relatively high, individual feedback of a new user would have a small effect on the update of the feature information. However, if the reliability is low, a feedback of each new user would have a large effect on the feature information value. [0013]
  • Since the searching and browsing methods of the related art do not take into consideration the factors described above, either the reliability of the searched result would be inconsistent or reliable feedback must be input at all times. [0014]
  • SUMMARY OF THE INVENTION
  • Accordingly, an object of the present invention is to solve at least the problems and disadvantages of the related art. [0015]
  • An object of the present invention is to provide an accurate and effective method of searching or browsing multimedia data. [0016]
  • Another object of the present invention is to provide a method of searching or browsing in consideration of a information reliability and an authority code to perform an update of the feature information. [0017]
  • A further object of the present invention is to provide a data structure for use in searching or browsing multimedia data. [0018]
  • Additional advantages, objects, and features of the invention will be set forth in part in the description which follows and in part will become apparent to those having ordinary skill in the art upon examination of the following or may be learned from practice of the invention. The objects and advantages of the invention may be realized and attained as particularly pointed out in the appended claims. [0019]
  • To achieve the objects and in accordance with the purposes of the invention, as embodied and broadly described herein, the method of searching or browsing multimedia data comprises selecting or inputting a reference multimedia data; searching for the reference multimedia data using weights assigned to features and/or feature elements of the multimedia data; inputting user feedback on the relevance of the searched or browsed multimedia data; measuring a similarity of the reference multimedia data to the resultant images of the search and calculating a new weight using a measured value; and updating previous weights and maintaining the updated weights. [0020]
  • In another aspect of the present invention, a method of searching or browsing multimedia data comprises searching a reference multimedia data using variable information representing importance of features of multimedia data, said variable information being included within the multimedia data structure, and using a reliability information representing a reliability of the variable information; inputting a user feedback on the relevance of the searched or browsed multimedia data; calculating a new variable information using training information fed back by a user or user pattern information stored in the system; and updating the previous variable information using the calculated variable information and/or reliability information, and maintaining the updated information. [0021]
  • In still another aspect of the present invention, a method of searching or browsing multimedia data comprises selecting of inputting a reference multimedia data; searching for the reference multimedia data using variable information representing importance of features of the multimedia data wherein the multimedia data structure includes the variable information, a reliability information of the variable information and an authority code for limiting an authority for a user; inputting a user feedback on a relevance of the searched or browsed multimedia data; measuring a similarity of the reference multimedia data to the resultant images of the search and calculating a new variable information using the measured value; and updating the previous variable information using a selective combination of the reliability information and authority code, and maintaining the updated information. [0022]
  • In still a further aspect of the present invention, a data structure for a multimedia data searching or browsing system comprises a multimedia data; feature information of the multimedia data; and weight information representing a weight of a feature of the multimedia data.[0023]
  • BRIEF DESCRIPTION OF THE DRAWINGS
  • The invention will be described in detail with reference to the following drawings in which like reference numerals refer to like elements wherein: [0024]
  • FIG. 1 is a multimedia data structure in a multimedia data searching or browsing system according to the present invention; [0025]
  • FIG. 2 is a another data structure for use in a multimedia data searching or browsing system according to the present invention; [0026]
  • FIG. 3 is a flowchart of a multimedia data searching or browsing process according to a first embodiment of the present invention; [0027]
  • FIG. 4 is a data structure of variable reliability information in a multimedia data searching or browsing system according to a third embodiment of the present invention; [0028]
  • FIG. 5 is an example of a variable weight information in multimedia data according to the data structure of FIG. 4; [0029]
  • FIG. 6 is a data structure of a fixed reliability information in a multimedia data searching or browsing system according to a third embodiment of the present invention; and [0030]
  • FIG. 7 is an example of the fixed weight information in multimedia data according to the data structure of FIG. 5.[0031]
  • DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
  • Reference will now be made in detail to the preferred embodiment of the present invention, examples of which are illustrated in the accompanying drawings. [0032]
  • FIG. 1 is a multimedia data structure which may be used in a search or browsing system according to the present invention, including an image description for relevance feedback [0033] 101. The image description for relevance feedback 101 is information which indicates an importance of features or feature elements (hereinafter generally referred to as “features”) trained by user feedback and includes an image description 102, an authority code 104 and a reliability code 107.
  • Particularly, the image description [0034] 102 includes image features 103 a for use in the actual search and weights 103 b indicating the importance of image features. The reliability code 107 indicates the reliability of the weights. In the preferred embodiment, the reliability code is represented using the number of weight updates by a user of level i 108. The authority code 104 indicates an authority level 106 and the number of the authority levels 105.
  • The present invention utilizes the authority code [0035] 104 to determine whether the weight should be updated and if so, the degree of the update. Moreover, the reliability code 107 and the authority code 104 may be selectively or both included in the data structure depending upon the needs of the system. For example, the data structure may include only the reliability code 107 and the image description 102. In such case, the system may provide the authority code 104. Also, if only one authority level is required in the system, the authority code (104) may be omitted.
  • The weight [0036] 103 b of the image description. 102 may be updated upon a user feedback and is the weight values assigned to features of the image. Furthermore, an authority level i 106 of the authority code 104 determines whether to update a weight assigned to an image feature and/or the degree of the update. The number of different levels may be determined based upon the needs of the system and is indicated in the number of authority levels 105. For example, assuming there are five levels, a weight may be updated upon feedback by users of the first and second authority levels, and the degree of update for the first level user may be 0.95 while the weight for the second level user may be 0.85.
  • FIG. 2 is a view illustrating a data structure for use in a multimedia data searching or browsing system according to the present invention. Referring to FIG. 2, the data structure includes a multimedia data [0037] 201, a feature information 202 of the multimedia data, a weight information (or variable information) 203 representing the importance of features of the multimedia data, a reliability information 206 and 208 representing the reliability of the weight information, and an authority code representing an authority level for a user.
  • As described with reference to FIG. 1, the authority levels are used to determine whether to update a weight information and the degree of such update. Thus, in the data structure, the authority code includes the number of authority levels [0038] 204 and authority level passwords 205 and 207 for the authority levels. Different passwords may be given to users based upon the authority level to limit or permit appropriate image access, i.e. access to modify the data, based on the authority code. Accordingly, an image access would not be permitted to the users having an authority levels lower than a specified level.
  • In the preferred embodiment, an image producer (or creator) divides the user authority into n levels and gives appropriate passwords to users based upon the authority level. Thereafter, a user can search or browse images and vary the image description of an image according to a given authority level. [0039]
  • Moreover, because the image description is updated by users of different authority levels, the number of feedbacks by users of each authority level is recorded to calculate the reliability information. Specifically, the number (Nk) of weight updates for an image description by user feedbacks of the kth level is multiplied with a weight coefficient (ak) assigned to the kth level. The product values (ak*Nk) for each respective authority level (1-n) are added and the sum is multiplied by a predetermined reliability coefficient (a) to obtain the reliability of the image description. If two input data have the same multimedia data, but different image description trained by different histories, the user can determine which image to use based upon the reliability information in the respective image description. Here, if there is only one authority level, the image would have a reliability value without the authority information. [0040]
  • In the first embodiment of the present invention, the multimedia data searching or browsing method is explained when variable information describing features of an image and/or an authority code is included in the input multimedia data. FIG. 3 is a flowchart of a searching or browsing method according to a first embodiment of the present invention. For purposes of explanation, the multimedia data will be assumed to be an image. [0041]
  • Referring to FIG. 3, a reference image is selected or input to the searching or browsing system by a user (step S[0042] 301). The system then searches for similar images using image features and weights assigned to image features (step S302). The system determines an initial values of the weight if the reference image is selected or input for the first time. The weight values may be assigned for image features such as color, texture or shape and/or may be assigned for image feature elements such as the Ith color element.
  • Upon viewing the search or browsing result, the user may give feedback by inputting relevance information, i.e. whether the search or browsing result is relevant. Particularly, the user may give positive feedback if the result is good or give negative feedback if the result poor. For example, images determined by a user to be similar to the reference image would be fed back as positive feedbacks and images determined by a user to be different from the reference image would be fed back as negative feedbacks. [0043]
  • Thus, the system judges whether the user has input relevance information (step S[0044] 303) and if there is no user feedback, the system returns to step S301. However, if there is user feedback, the system determines whether the user has sufficient authority level to update the weight of features (step S304). Here, the system may determine whether the authority level of the user by requiring a user to enter a password. A detailed explanation of the authority levels will be explained below with reference to the third embodiment. Generally, step S304 limits the update of the weight including the degree of the update depending upon the authority level. However, such step may be omitted, in which case, the weight value would be updated for each and every user feedback.
  • Referring back to FIG. 3, if the authority level of the user allows an update, the system calculates the new weights by measuring the similarity of the reference image and the fed back images (steps S[0045] 305 and S306) among the searched images. Namely, the system increases the weights of features which would increase the similarity between the reference image and the fed back images if the relevance information is positive information. On the contrary, if the relevance information is negative information, the system increases the weights of features which would increase the dissimilarity between the reference image and the fed back images.
  • Thereafter, the system updates the previous weight information in the image description using the new weights and maintains the updated weights for the next search or browsing (step S[0046] 307) Particularly, a weight value is updated by taking into consideration the weight of the kth feature prior to the update, the new weight value of the kth feature obtained in the current image search and an average of new weight values of all features. Here, the degree of effect on the updated weight value due to the previous weight, i.e. weight of the kth feature prior to the update, is inversely proportional to the reliability of the previous weight.
  • In the preferred embodiment, the weight value can be updated using Equation 1, where Wk(t) is the updated weight of the kth feature, Wk(t−1) is the weight of the kth feature prior to an update, Wnew_k is the calculated weight of the kth feature obtained by a current image search, M(Wnew) is the average of the calculated weights for all features obtained by the current image search, and a is a weight coefficient which determines the degree of update according to the user authority level. [0047]
  • Wk(t)=Wk(t−1)+ΔWk, (ΔWk=a(Wnew k−M(Wnew))  [1]
  • Alternatively, the weight may be updated using a similar image list or a dissimilar image list obtained during the search process. For example, the system would measure the similarity among the images in the similar list and increase the weight of features contributing to the judgement of the similarity. On the contrary, the system measures the dissimilarity among the images in the dissimilar image list, and increase the weight of features contributing to the judgement of the dissimilarity. [0048]
  • According to the first embodiment of the present invention, the weight information of features used in a search is included within the multimedia data structure input to the system. Thus, the system develops a proper weight by self-training during each searching or browsing of an image. As a result, the system can perform a more effective search or browsing using the weight information of features irrespective of a place or application program, image searching engine. Also, the present embodiment may be adapted and used for searching or browsing an image that the user desires by performing an effective response to subjective and objective queries by the user whenever weights are used for a search or browsing. Accordingly, the first embodiment of the present invention can be suitably adopted to be used as an image format that can use the “relevance feedback” concept for controlling the weight according to the user feedback. [0049]
  • In a second embodiment of the present invention, the reference data selected or input for searching or browsing includes variable information representing the importance of features of the multimedia data and reliability information representing the reliability of the variable information. In the second embodiment, the multimedia data structure which includes the variable information and the reliability information is input to the system, and the system searches for the reference data. For purposes of explanation, the multimedia data will be assumed to be an image. [0050]
  • As in the first embodiment, the user may give feedback on the relevance of the resultant images of the search or browsing. The system then calculates a new variable information using either the relevance information input by the user or the user pattern information stored in the system. For example, the user pattern information may be a history of a user or the history of uses. Thereafter, the system updates the variable information using the new variable information and/or the reliability information, and maintains the updated variable information. Here, the variable information is updated in an analogous manner as the update of weights explained with reference to FIG. 3. [0051]
  • The variable information may be a weight assigned to features used for searching such as the color, texture, or keyword of the multimedia data; a weight assigned to a frame or segment used in searching or browsing a specific video; a weight assigned to user-dependent information representing a user preference or habit, and representing a portion of data used for searching or browsing a main region or main object of the multimedia data; a information for a multimedia grouping of either a similarity list or a cluster model; or a combination of two or more weights as described above. [0052]
  • Generally, the reliability information directly or indirectly represents the reliability of the variable information and is proportional to the amount of user training of the variable information according to the input relevance information. Also, the reliability information can be determined by the performance of the system. A detailed explanation of the reliability information will be explained below with reference to the third embodiment. [0053]
  • Accordingly, if two data has identical multimedia data but different variable information values, the system may select the variable information with the higher reliability or combine the variable information in proportion to the reliability of the variable information when calculating a new variable information. The calculation of the variable information may be used independently irrespective of the second embodiment of the present invention. [0054]
  • For example, assume that an image is created and is copied into a plurality of images by other users, and further assume that the image description of each copied image is developed differently while passing through different application programs. Particularly, the image description developed by different application programs will have different variable information and reliability information of the variable information. If the system then requires a use of the image in a search, a determination as to which copy of the image to use must be made. Because the images with different image description have the reliability information of the variable information, i.e. weight, the system will be able to easily select and use the image having the highest reliability for the search. Also, the system may obtain a new weight by combining the weights of the different image descriptions corresponding to the plurality of image copies in proportion to their reliabilities. [0055]
  • According to the second embodiment of the present invention as described above, since the reliability information of the variable information as well as the variable information is included in the image input to the system, the weights may be updated whenever the image is searched. Thus, the variable information is trained, allowing a more accurate search element. As a result, the system may intellectually develop to an optimal state. [0056]
  • In a third embodiment of the present invention, the multimedia data structure input to the searching or browsing system includes the variable information representing the importance of features, the reliability information representing the reliability of the variable information, and the authority code for limiting an authority for a user. Here, the authority code may be included in the multimedia data or may be provided from the system when justification of the multimedia data search or browsing is fed back. [0057]
  • In the third embodiment of the present invention, the multimedia data search and browsing system selects or inputs a reference multimedia data according to a control signal from the user. Thereafter, the system searches the multimedia data using the variable information, the reliability information of the variable information, and the authority code. The authority code is used to limit an improper training of the variable information by updates in response to all user feedbacks regardless of the reliability of such feedbacks. [0058]
  • For example, an inexperienced user may consider two different images as similar causing the weight assigned to features of the image used in the search to be updated in an improper direction. Thus, the training result of the corresponding image would be lower in reliability. However, in an alternative method, the input image may not include the authority code, instead the system may limit or discriminate the authority of weight updates or the degree of the weight update by providing the authority code. For example, user Log-In IDs may be utilized to determine the authority level. [0059]
  • Moreover, as in the first and second embodiments, the user gives feedback on the relevance of the searched or browsed multimedia data. Thereafter, the system measures the similarity of the reference image to the fed back images among resultant images of the search, and calculates new variable information using the measured value. The system then updates the previous variable information included in the reference image using the calculated variable information, reliability information and/or authority code, and maintains the updated variable information. Thus, if there are two images having different variable information values, the system selects one which has a higher reliability with respect to the variable information value. [0060]
  • Particularly, the new weights may be calculated and updated as in the first embodiment by Equation 1, or by a similarity list or dissimilarity list obtained during the search process. Furthermore, the weight may be updated based upon the reliability of the weight. The weight can be updated by Equation 2 where (Rc) is a built-up reliability of the currently trained image, (Wc) is a weight predetermined for the reliability, (Rt) is the degree of updating the weight corresponding to the currently fed back user authority level, and (Wt) is the weight for the user authority level. [0061]
  • Updated weight=(RcWc+RtWt)/(Rc+Rt)  [2]
  • Here, the value of Rc is the number of previous weight updates by a user of respective authority levels. [0062]
  • FIG. 4 shows a data structure of a variable reliability information in the multimedia data searching or browsing system according to the third embodiment of the present invention. Referring to FIG. 4, the variable reliability descriptor [0063] 401 is organized by the number of levels 402, the degree of effect of level I 403, and the number of updates by a user of level I. In contrast, FIG. 6 shows a data structure of a fixed reliability information in the multimedia data searching or browsing system according to the third embodiment of the present invention. Referring to FIG. 6, the fixed reliability descriptor 601 includes the number of updates 602 performed by the user of level I. The reliability information can be obtained as follows.
  • First, a higher reliability is given to an image with variable information trained frequently by users having high authority level. In other words, the reliability is given in proportion to the number of the users who give feedback and the authority level. Accordingly, the system gives a relatively high reliability to images which has a relatively large amount of training by relevance information fed back by users having high authority level. [0064]
  • Second, the system gives a higher reliability to an image trained mostly by users having authority level in the range from a predetermined level to the upper level. In other words, the system gives a relatively high reliability to images having a relatively large amount of training by relevance information fed back by the user having an authority level over a predetermined level. [0065]
  • Third, the reliability can be determined according to the performance of the system. [0066]
  • Fourth, the system may use the reliability information as shown in FIG. 4 by variably setting and using a number of user levels with corresponding degree of update, or may use a fixed reliability information as shown in FIG. 6. In any case, a relatively higher reliability would be given as the number of updates by user feedbacks and the authority level of the user giving feedback becomes higher. [0067]
  • FIG. 5 shows an example of a variable reliability information of FIG. 4. In the example, users are classified into five authority levels. The first level has an update degree of 1.0 and has a record of eight updates by users of the first level. The second level has an update degree of 0.7 and has a record of fourteen updates by users of the second level. The third level has an update degree of 0.5 and has a record of thirty updates by users of the third level. The fourth level has an update degree of 0.3 and has a record of twenty-three updates by users of the fourth level. The fifth level has an update degree of 0.1 and has a record of four updates by users of the fifth level. Thus, the number of authority levels and the degree of update influenced by users of the respective authority level are variably determined. [0068]
  • In contrast, FIG. 7 is an example of a fixed reliability information of FIG. 6. Referring to FIG. 7, the number of user authority level is fixed to 10 levels and a corresponding weight-updating degree for each level is allocated in advance from the range of 0.1 to 1. Particularly, the first level has an update degree of 1.0 and has a record of eight updates, the fourth level has an update degree of 0.7 and has a record of fourteen updates, the sixth level has an update degree of 0.5 and has a record of thirty updates, the eighth level has an update degree of 0.3 and has a record of twenty-three updates, and the tenth level has an update degree of 0.1 and has a record of four updates. [0069]
  • The system checks the user authority level as determined above, and effectively controls the access of the image, i.e. permission and/or prohibition of weight update or degree of update. Also, in the system shown in FIG. 7, all or a portion of the 10 levels may be used as necessary. For example, the system may use five levels as in FIG. 5 by not assigning the remaining five levels to users. In such case, the first level of FIG. 7 corresponding to the first level of FIG. 5 would be the first level, the fourth level of FIG. 7 corresponding to the second level of FIG. 5 would be the second level, the sixth level of FIG. 7 corresponding to the third level of FIG. 5 would be the third level, the eight level of FIG. 7 corresponding to the fourth level of FIG. 5 would be the fourth level, and the tenth level of FIG. 7 corresponding to the fifth level of FIG. 5 would be the fifth level. Accordingly, 5 authority levels among 10 fixed authority levels are used and the system can determine whether to permit an update based upon the respective authority levels. [0070]
  • According to the embodiments of the present invention as described above, the following effects can be provided. [0071]
  • First, since the weights (or variable information) of image features are included in the input image and the corresponding image is trained to provide a better search result when the image search is repeated, an effective and accurate search or browsing can be achieved when performing the search with respect to equal images. [0072]
  • Second, when the equal images are updated after being trained in different environments, the reliability information representing the reliability of the weight or variable information of the image is included in the respective image so as to identify which image has been more effectively trained. Thus, the user can search or browse the current image effectively and accurately. [0073]
  • Third, the permission of update and the degree of update are limited according to user authority levels by including an authority code in the input image or by providing the authority code by the system. Accordingly, the corresponding image is prevented from being improperly trained due to thoughtless or abnormal updates by a user. [0074]
  • Fourth, since the reliability information and the authority code is combined with the weight (or variable information) of the image features selectively or together according to the characteristic of the system, the multimedia data search or browsing can be properly performed in a direction where the intelligent training and self-development are effected. [0075]
  • The foregoing embodiments are merely exemplary and are not to be construed as limiting the present invention. The present teachings can be readily applied to other types of apparatuses. The description of the present invention is intended to be illustrative, and not to limit the scope of the claims. Many alternatives, modifications, and variations will be apparent to those skilled in the art. [0076]

Claims (28)

    What is claimed is:
  1. 1. A method of searching or browsing multimedia data comprising:
    (a) receiving a reference multimedia data with data structure including features of said reference multimedia data and weight information of said features;
    (b) searching for said reference multimedia data using the features and the weight information;
    (c) receiving user feedback on a relevance of resultant multimedia data found in (b);
    (d) measuring a similarity of the reference multimedia data to the resultant multimedia data and calculating a new weight information of said features using the measured value; and
    (e) updating the weight information of said features in said data structure of the reference multimedia data using the new weight information.
  2. 2. A method of claim 1, wherein in (c), increasing weights of features which would increase a similarity between the reference multimedia data and the resultant multimedia data if the user feedback is a positive relevance information
  3. 3. A method of claim 2, wherein in (c), increasing weights of features which would increase a dissimilarity between the reference multimedia data and the resultant multimedia data if the user feedback is a negative relevance information.
  4. 4. A method of claim 1, wherein the data structure of the reference multimedia data further comprises reliability information indicating a reliability of the weight information.
  5. 5. A method of claim 4, wherein a reliability of a weight assigned to a feature is proportional to the amount of training by user feedback.
  6. 6. A method of claim 4, wherein the data structure of the reference multimedia data further comprises authority information which limits an update of the weight information by a user feedback.
  7. 7. A method of claim 6, wherein the authority information includes a plurality of authority levels, wherein each authority level has degree values affecting the degree of weight information update in (e).
  8. 8. A method of claim 7, wherein a higher reliability is given to user feedback by a user with a high authority level.
  9. 9. A method of claim 6, wherein in (e), updating the weight information of said features in said data structure of the reference multimedia data depending upon the reliability information and the authority information.
  10. 10. A method of claim 1, wherein the data structure of the reference multimedia data further comprises authority information which limits an update of the weight information by a user feedback.
  11. 11. A method of claim 10, wherein the authority information includes a plurality of authority levels, wherein each authority level has degree values affecting the degree of weight information update in (e).
  12. 12. A method of claim 11, wherein receiving a password from a user to determine an authority level of the user.
  13. 13. A method of searching or browsing multimedia data comprising:
    searching for a reference multimedia data using variable information representing an importance of a feature of the reference multimedia data;
    receiving user feedback on relevance of the searched multimedia data;
    calculating a new variable information using the relevance information as training information or using user pattern information stored in the system; and
    updating the variable information using the calculated new variable information and/or reliability information, and maintaining the updated variable information.
  14. 14. A method of claim 13, wherein the variable information is one or a combination of:
    a weight of features used for searching for the reference multimedia data;
    a weight of a frame or segment used for searching or browsing a specific video;
    a weight of user-dependent information representing a user preference or user habit and a portion of data used for searching or browsing a main region or main object of the multimedia data; and
    information for multimedia grouping of a similarity list and a cluster model.
  15. 15. A method of claim 13, wherein if at least two identical multimedia data having different variable information for a search or browsing are provided, selecting a multimedia data which has a relatively high reliability with respect to the variable information to calculate the new variable information.
  16. 16. A method of claim 13, wherein if at least two identical multimedia data having different variable information for a search or browsing are provided, combining the provided multimedia data in proportion to the reliability of the variable information value to calculate the new variable information.
  17. 17. A method of searching or browsing multimedia data comprising:
    searching for a reference multimedia data using variable information representing an importance of a feature of the reference multimedia data;
    receiving user feedback on relevance of the searched multimedia data; and
    updating the variable information using the relevance information as training information or using a prestored user pattern information, and/or reliability information, and maintaining the updated variable information.
  18. 18. A data structure for a multimedia data searching or browsing system comprising:
    a multimedia data; and
    a variable information representing features of the multimedia data.
  19. 19. A data structure of claim 18, further comprising a reliability information representing a reliability of the variable information.
  20. 20. A data structure of claim 19, wherein the reliability information includes information on the number of variable information updates by a user.
  21. 21. A data structure of claim 19, further comprising an authority code.
  22. 22. A data structure of claim 21, wherein the reliability information is variable and includes a number of authority levels, a degree of variable information update for each authority level, and a number of variable information updates by a user of each authority level.
  23. 23. A data structure of claim 21, wherein the reliability information is fixed and includes a number of variable information updates by a user of fixed authority levels.
  24. 24. A data structure of claim 18, further comprising an authority code.
  25. 25. A method of searching or browsing a multimedia data having a data structure as in claim 18.
  26. 26. A method of searching or browsing a multimedia data having a data structure as in claim 19.
  27. 27. A method of searching or browsing a multimedia data having a data structure as in claim 21.
  28. 28. A method of searching or browsing a multimedia data having a data structure as in claim 24.
US10673281 1999-01-29 2003-09-30 Method of searching or browsing multimedia data and data structure Abandoned US20040064526A1 (en)

Priority Applications (6)

Application Number Priority Date Filing Date Title
KR2979/1999 1999-01-29
KR19990002979A KR100319153B1 (en) 1999-01-29 1999-01-29 Image query system using authority relevance feedback
KR19990035798A KR100350785B1 (en) 1999-08-27 1999-08-27 Method for generating of multimedia feature description scheme
KR35798/1999 1999-08-27
US09493038 US6643643B1 (en) 1999-01-29 2000-01-28 Method of searching or browsing multimedia data and data structure
US10673281 US20040064526A1 (en) 1999-01-29 2003-09-30 Method of searching or browsing multimedia data and data structure

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
US10673281 US20040064526A1 (en) 1999-01-29 2003-09-30 Method of searching or browsing multimedia data and data structure

Related Parent Applications (1)

Application Number Title Priority Date Filing Date
US09493038 Continuation US6643643B1 (en) 1999-01-29 2000-01-28 Method of searching or browsing multimedia data and data structure

Publications (1)

Publication Number Publication Date
US20040064526A1 true true US20040064526A1 (en) 2004-04-01

Family

ID=26634655

Family Applications (2)

Application Number Title Priority Date Filing Date
US09493038 Active US6643643B1 (en) 1999-01-29 2000-01-28 Method of searching or browsing multimedia data and data structure
US10673281 Abandoned US20040064526A1 (en) 1999-01-29 2003-09-30 Method of searching or browsing multimedia data and data structure

Family Applications Before (1)

Application Number Title Priority Date Filing Date
US09493038 Active US6643643B1 (en) 1999-01-29 2000-01-28 Method of searching or browsing multimedia data and data structure

Country Status (7)

Country Link
US (2) US6643643B1 (en)
EP (2) EP1066595B1 (en)
JP (1) JP3585844B2 (en)
CN (1) CN1293793B (en)
CA (1) CA2326813A1 (en)
DE (1) DE60044924D1 (en)
WO (1) WO2000045341A1 (en)

Cited By (22)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7117207B1 (en) * 2002-09-11 2006-10-03 George Mason Intellectual Properties, Inc. Personalizable semantic taxonomy-based search agent
US20080306807A1 (en) * 2007-06-05 2008-12-11 At&T Knowledge Ventures, Lp Interest profiles for audio and/or video streams
US20090103887A1 (en) * 2007-10-22 2009-04-23 Samsung Electronics Co., Ltd. Video tagging method and video apparatus using the same
US20090287655A1 (en) * 2008-05-13 2009-11-19 Bennett James D Image search engine employing user suitability feedback
US20090328122A1 (en) * 2008-06-25 2009-12-31 At&T Corp. Method and apparatus for presenting media programs
US7734622B1 (en) * 2005-03-25 2010-06-08 Hewlett-Packard Development Company, L.P. Media-driven browsing
US20100226288A1 (en) * 2009-03-04 2010-09-09 At&T Intellectual Property I, Lp. Method and apparatus for group media consumption
US20110093909A1 (en) * 2009-10-15 2011-04-21 At&T Intellectual Property I, L.P. Apparatus and method for transmitting media content
US20110106718A1 (en) * 2009-11-05 2011-05-05 At&T Intellectual Property I, L.P. Apparatus and method for managing a social network
US20110106612A1 (en) * 2009-10-30 2011-05-05 At&T Intellectual Property L.L.P. Apparatus and method for product marketing
US20110109648A1 (en) * 2009-11-06 2011-05-12 At&T Intellectual Property I, L.P. Apparatus and method for managing marketing
US20110113440A1 (en) * 2009-11-10 2011-05-12 At&T Intellectual Property I.L.P. Apparatus and method for transmitting media content
US20110112665A1 (en) * 2009-11-10 2011-05-12 At&T Intellectual Property I, L.P. Method and apparatus for presenting media programs
US20110119725A1 (en) * 2009-11-13 2011-05-19 At&T Intellectual Property I, L.P. Method and apparatus for presenting media programs
US20110126252A1 (en) * 2009-11-20 2011-05-26 At&T Intellectual Property I, L.P. Method and apparatus for presenting media programs
US20110126253A1 (en) * 2009-11-20 2011-05-26 At&T Intellectual Property I, L.P. Apparatus and method for managing a social network
US20110122220A1 (en) * 2009-11-20 2011-05-26 At&T Intellectual Property I, L.P. Apparatus and method for collaborative network in an enterprise setting
US20110138326A1 (en) * 2009-12-04 2011-06-09 At&T Intellectual Property I, L.P. Apparatus and Method for Tagging Media Content and Managing Marketing
US20110255614A1 (en) * 2010-04-15 2011-10-20 Samsung Electronics Co., Ltd. Apparatus for providing digital content and method thereof
US20120134648A1 (en) * 2010-06-16 2012-05-31 Kouji Miura Video search device, video search method, recording medium, program, and integrated circuit
US8275623B2 (en) 2009-03-06 2012-09-25 At&T Intellectual Property I, L.P. Method and apparatus for analyzing discussion regarding media programs
US9015778B2 (en) 2008-06-25 2015-04-21 AT&T Intellectual Property I. LP Apparatus and method for media on demand commentaries

Families Citing this family (61)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2000276469A (en) * 1999-03-23 2000-10-06 Canon Inc Method and device for information retrieval and storage medium
US6411724B1 (en) * 1999-07-02 2002-06-25 Koninklijke Philips Electronics N.V. Using meta-descriptors to represent multimedia information
KR100346262B1 (en) * 1999-08-27 2002-07-26 엘지전자주식회사 Method of multimedia data keyword self formation
US7099860B1 (en) 2000-10-30 2006-08-29 Microsoft Corporation Image retrieval systems and methods with semantic and feature based relevance feedback
US6970860B1 (en) * 2000-10-30 2005-11-29 Microsoft Corporation Semi-automatic annotation of multimedia objects
KR100788643B1 (en) * 2001-01-09 2007-12-26 삼성전자주식회사 Searching method of image based on combination of color and texture
US6870956B2 (en) 2001-06-14 2005-03-22 Microsoft Corporation Method and apparatus for shot detection
JP2003132090A (en) * 2001-10-26 2003-05-09 Olympus Optical Co Ltd Similar data retrieval device and method therefor
JP4014390B2 (en) * 2001-10-29 2007-11-28 オリンパス株式会社 Multimedia object retrieval system
US7098117B2 (en) * 2002-10-18 2006-08-29 The Regents Of The University Of Michigan Method of fabricating a package with substantially vertical feedthroughs for micromachined or MEMS devices
US7116716B2 (en) 2002-11-01 2006-10-03 Microsoft Corporation Systems and methods for generating a motion attention model
US20040088723A1 (en) * 2002-11-01 2004-05-06 Yu-Fei Ma Systems and methods for generating a video summary
US7274741B2 (en) 2002-11-01 2007-09-25 Microsoft Corporation Systems and methods for generating a comprehensive user attention model
US7164798B2 (en) * 2003-02-18 2007-01-16 Microsoft Corporation Learning-based automatic commercial content detection
US7260261B2 (en) * 2003-02-20 2007-08-21 Microsoft Corporation Systems and methods for enhanced image adaptation
US7400761B2 (en) * 2003-09-30 2008-07-15 Microsoft Corporation Contrast-based image attention analysis framework
US7471827B2 (en) 2003-10-16 2008-12-30 Microsoft Corporation Automatic browsing path generation to present image areas with high attention value as a function of space and time
US7805024B2 (en) * 2004-05-05 2010-09-28 Nokia Corporation Method and apparatus to provide efficient multimedia content storage
US7860874B2 (en) 2004-06-08 2010-12-28 Siemens Industry, Inc. Method for searching across a PLC network
US9053754B2 (en) 2004-07-28 2015-06-09 Microsoft Technology Licensing, Llc Thumbnail generation and presentation for recorded TV programs
US7986372B2 (en) 2004-08-02 2011-07-26 Microsoft Corporation Systems and methods for smart media content thumbnail extraction
US7383260B2 (en) * 2004-08-03 2008-06-03 International Business Machines Corporation Method and apparatus for ontology-based classification of media content
JP2006048320A (en) * 2004-08-04 2006-02-16 Sony Corp Device, method, recording medium, and program for information processing
GB0521690D0 (en) * 2005-10-25 2005-11-30 Donnelly Thomas Imagerank
US8312031B2 (en) 2005-10-26 2012-11-13 Cortica Ltd. System and method for generation of complex signatures for multimedia data content
US9558449B2 (en) 2005-10-26 2017-01-31 Cortica, Ltd. System and method for identifying a target area in a multimedia content element
US9235557B2 (en) 2005-10-26 2016-01-12 Cortica, Ltd. System and method thereof for dynamically associating a link to an information resource with a multimedia content displayed in a web-page
US9466068B2 (en) 2005-10-26 2016-10-11 Cortica, Ltd. System and method for determining a pupillary response to a multimedia data element
US9396435B2 (en) 2005-10-26 2016-07-19 Cortica, Ltd. System and method for identification of deviations from periodic behavior patterns in multimedia content
US9767143B2 (en) 2005-10-26 2017-09-19 Cortica, Ltd. System and method for caching of concept structures
US8112376B2 (en) 2005-10-26 2012-02-07 Cortica Ltd. Signature based system and methods for generation of personalized multimedia channels
US8326775B2 (en) 2005-10-26 2012-12-04 Cortica Ltd. Signature generation for multimedia deep-content-classification by a large-scale matching system and method thereof
US9191626B2 (en) 2005-10-26 2015-11-17 Cortica, Ltd. System and methods thereof for visual analysis of an image on a web-page and matching an advertisement thereto
US9639532B2 (en) 2005-10-26 2017-05-02 Cortica, Ltd. Context-based analysis of multimedia content items using signatures of multimedia elements and matching concepts
US9384196B2 (en) 2005-10-26 2016-07-05 Cortica, Ltd. Signature generation for multimedia deep-content-classification by a large-scale matching system and method thereof
US9218606B2 (en) 2005-10-26 2015-12-22 Cortica, Ltd. System and method for brand monitoring and trend analysis based on deep-content-classification
US8266185B2 (en) 2005-10-26 2012-09-11 Cortica Ltd. System and methods thereof for generation of searchable structures respective of multimedia data content
US9529984B2 (en) 2005-10-26 2016-12-27 Cortica, Ltd. System and method for verification of user identification based on multimedia content elements
US9646005B2 (en) 2005-10-26 2017-05-09 Cortica, Ltd. System and method for creating a database of multimedia content elements assigned to users
US9953032B2 (en) 2005-10-26 2018-04-24 Cortica, Ltd. System and method for characterization of multimedia content signals using cores of a natural liquid architecture system
US9031999B2 (en) 2005-10-26 2015-05-12 Cortica, Ltd. System and methods for generation of a concept based database
US8655801B2 (en) 2005-10-26 2014-02-18 Cortica, Ltd. Computing device, a system and a method for parallel processing of data streams
US9489431B2 (en) 2005-10-26 2016-11-08 Cortica, Ltd. System and method for distributed search-by-content
US9330189B2 (en) 2005-10-26 2016-05-03 Cortica, Ltd. System and method for capturing a multimedia content item by a mobile device and matching sequentially relevant content to the multimedia content item
US20140082211A1 (en) * 2005-10-26 2014-03-20 Cortica Ltd. System and method for generation of concept structures based on sub-concepts
US9372940B2 (en) 2005-10-26 2016-06-21 Cortica, Ltd. Apparatus and method for determining user attention using a deep-content-classification (DCC) system
US9286623B2 (en) 2005-10-26 2016-03-15 Cortica, Ltd. Method for determining an area within a multimedia content element over which an advertisement can be displayed
US9477658B2 (en) 2005-10-26 2016-10-25 Cortica, Ltd. Systems and method for speech to speech translation using cores of a natural liquid architecture system
US9256668B2 (en) 2005-10-26 2016-02-09 Cortica, Ltd. System and method of detecting common patterns within unstructured data elements retrieved from big data sources
US7773813B2 (en) 2005-10-31 2010-08-10 Microsoft Corporation Capture-intention detection for video content analysis
US8180826B2 (en) * 2005-10-31 2012-05-15 Microsoft Corporation Media sharing and authoring on the web
US8196032B2 (en) 2005-11-01 2012-06-05 Microsoft Corporation Template-based multimedia authoring and sharing
CN100463515C (en) 2005-11-23 2009-02-18 中国移动通信集团公司 Data protection method of multimedia broadcast multicast service
US7599918B2 (en) * 2005-12-29 2009-10-06 Microsoft Corporation Dynamic search with implicit user intention mining
CN100485680C (en) 2006-03-03 2009-05-06 摩达网股份有限公司 System and method for searching multi-medium content in Internet
CN102265274B (en) * 2008-12-22 2017-05-31 皇家飞利浦电子股份有限公司 Relevance feedback on the data object segment
US8831358B1 (en) * 2011-11-21 2014-09-09 Google Inc. Evaluating image similarity
US9846696B2 (en) 2012-02-29 2017-12-19 Telefonaktiebolaget Lm Ericsson (Publ) Apparatus and methods for indexing multimedia content
US9292552B2 (en) * 2012-07-26 2016-03-22 Telefonaktiebolaget L M Ericsson (Publ) Apparatus, methods, and computer program products for adaptive multimedia content indexing
US9633015B2 (en) 2012-07-26 2017-04-25 Telefonaktiebolaget Lm Ericsson (Publ) Apparatus and methods for user generated content indexing
US9070046B2 (en) 2012-10-17 2015-06-30 Microsoft Technology Licensing, Llc Learning-based image webpage index selection

Citations (18)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5020019A (en) * 1989-05-29 1991-05-28 Ricoh Company, Ltd. Document retrieval system
US5297042A (en) * 1989-10-05 1994-03-22 Ricoh Company, Ltd. Keyword associative document retrieval system
US5321833A (en) * 1990-08-29 1994-06-14 Gte Laboratories Incorporated Adaptive ranking system for information retrieval
US5566291A (en) * 1993-12-23 1996-10-15 Diacom Technologies, Inc. Method and apparatus for implementing user feedback
US5579471A (en) * 1992-11-09 1996-11-26 International Business Machines Corporation Image query system and method
US5724567A (en) * 1994-04-25 1998-03-03 Apple Computer, Inc. System for directing relevance-ranked data objects to computer users
US5731991A (en) * 1996-05-03 1998-03-24 Electronic Data Systems Corporation Software product evaluation
US5774121A (en) * 1995-09-18 1998-06-30 Avantos Performance Systems, Inc. User interface method and system for graphical decision making with categorization across multiple criteria
US5793888A (en) * 1994-11-14 1998-08-11 Massachusetts Institute Of Technology Machine learning apparatus and method for image searching
US5802361A (en) * 1994-09-30 1998-09-01 Apple Computer, Inc. Method and system for searching graphic images and videos
US5826260A (en) * 1995-12-11 1998-10-20 International Business Machines Corporation Information retrieval system and method for displaying and ordering information based on query element contribution
US6067539A (en) * 1998-03-02 2000-05-23 Vigil, Inc. Intelligent information retrieval system
US6081276A (en) * 1996-11-14 2000-06-27 International Business Machines Corporation Method and apparatus for creating a color name dictionary and for querying an image by color name
US6163622A (en) * 1997-12-18 2000-12-19 U.S. Philips Corporation Image retrieval system
US6285995B1 (en) * 1998-06-22 2001-09-04 U.S. Philips Corporation Image retrieval system using a query image
US6430566B1 (en) * 1997-04-14 2002-08-06 Canon Kabushiki Kaisha Image processing apparatus and control method therefor
US6457052B1 (en) * 1998-06-23 2002-09-24 At&T Corp Method and apparatus for providing multimedia buffering capabilities based on assignment weights
US6460036B1 (en) * 1994-11-29 2002-10-01 Pinpoint Incorporated System and method for providing customized electronic newspapers and target advertisements

Family Cites Families (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP3143532B2 (en) 1992-11-30 2001-03-07 キヤノン株式会社 Image retrieval apparatus and method
JPH0721198A (en) 1993-06-17 1995-01-24 Nippon Telegr & Teleph Corp <Ntt> Image retrieving method
JP3026712B2 (en) 1993-12-09 2000-03-27 キヤノン株式会社 Image retrieval method and apparatus
JPH07239856A (en) 1994-02-25 1995-09-12 Canon Inc Method and device for retrieving image
JP3284528B2 (en) 1995-03-15 2002-05-20 オムロン株式会社 Image retrieval method and apparatus
JPH08249353A (en) 1995-03-15 1996-09-27 Omron Corp Method and device for image retrieval
JPH09101970A (en) 1995-10-06 1997-04-15 Omron Corp Method and device for retrieving image
JP3609225B2 (en) 1996-11-25 2005-01-12 日本電信電話株式会社 Similar object retrieval apparatus
JP3446797B2 (en) 1996-12-11 2003-09-16 日本電信電話株式会社 Similar object retrieval method and apparatus
JP3754791B2 (en) 1997-03-19 2006-03-15 キヤノン株式会社 Image retrieval apparatus and method
JPH10289241A (en) 1997-04-14 1998-10-27 Canon Inc Image processor and its control method
JPH10326286A (en) 1997-05-27 1998-12-08 Mitsubishi Electric Corp Similarity retrieval device and recording medium where similarity retrival program is recorded
JP3673615B2 (en) 1997-06-19 2005-07-20 キヤノン株式会社 Image processing apparatus and control method thereof

Patent Citations (19)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5020019A (en) * 1989-05-29 1991-05-28 Ricoh Company, Ltd. Document retrieval system
US5297042A (en) * 1989-10-05 1994-03-22 Ricoh Company, Ltd. Keyword associative document retrieval system
US5321833A (en) * 1990-08-29 1994-06-14 Gte Laboratories Incorporated Adaptive ranking system for information retrieval
US5579471A (en) * 1992-11-09 1996-11-26 International Business Machines Corporation Image query system and method
US5751286A (en) * 1992-11-09 1998-05-12 International Business Machines Corporation Image query system and method
US5566291A (en) * 1993-12-23 1996-10-15 Diacom Technologies, Inc. Method and apparatus for implementing user feedback
US5724567A (en) * 1994-04-25 1998-03-03 Apple Computer, Inc. System for directing relevance-ranked data objects to computer users
US5802361A (en) * 1994-09-30 1998-09-01 Apple Computer, Inc. Method and system for searching graphic images and videos
US5793888A (en) * 1994-11-14 1998-08-11 Massachusetts Institute Of Technology Machine learning apparatus and method for image searching
US6460036B1 (en) * 1994-11-29 2002-10-01 Pinpoint Incorporated System and method for providing customized electronic newspapers and target advertisements
US5774121A (en) * 1995-09-18 1998-06-30 Avantos Performance Systems, Inc. User interface method and system for graphical decision making with categorization across multiple criteria
US5826260A (en) * 1995-12-11 1998-10-20 International Business Machines Corporation Information retrieval system and method for displaying and ordering information based on query element contribution
US5731991A (en) * 1996-05-03 1998-03-24 Electronic Data Systems Corporation Software product evaluation
US6081276A (en) * 1996-11-14 2000-06-27 International Business Machines Corporation Method and apparatus for creating a color name dictionary and for querying an image by color name
US6430566B1 (en) * 1997-04-14 2002-08-06 Canon Kabushiki Kaisha Image processing apparatus and control method therefor
US6163622A (en) * 1997-12-18 2000-12-19 U.S. Philips Corporation Image retrieval system
US6067539A (en) * 1998-03-02 2000-05-23 Vigil, Inc. Intelligent information retrieval system
US6285995B1 (en) * 1998-06-22 2001-09-04 U.S. Philips Corporation Image retrieval system using a query image
US6457052B1 (en) * 1998-06-23 2002-09-24 At&T Corp Method and apparatus for providing multimedia buffering capabilities based on assignment weights

Cited By (69)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7117207B1 (en) * 2002-09-11 2006-10-03 George Mason Intellectual Properties, Inc. Personalizable semantic taxonomy-based search agent
US7734622B1 (en) * 2005-03-25 2010-06-08 Hewlett-Packard Development Company, L.P. Media-driven browsing
US20080306807A1 (en) * 2007-06-05 2008-12-11 At&T Knowledge Ventures, Lp Interest profiles for audio and/or video streams
US8099315B2 (en) 2007-06-05 2012-01-17 At&T Intellectual Property I, L.P. Interest profiles for audio and/or video streams
US8392238B2 (en) 2007-06-05 2013-03-05 At&T Intellectual Property I, L.P. Interest profiles for audio and/or video streams
US20090103887A1 (en) * 2007-10-22 2009-04-23 Samsung Electronics Co., Ltd. Video tagging method and video apparatus using the same
US20090287655A1 (en) * 2008-05-13 2009-11-19 Bennett James D Image search engine employing user suitability feedback
US20110111854A1 (en) * 2008-06-25 2011-05-12 At&T Intellectual Property I, L.P. Apparatus and method for gaming
US9015778B2 (en) 2008-06-25 2015-04-21 AT&T Intellectual Property I. LP Apparatus and method for media on demand commentaries
US9369781B2 (en) 2008-06-25 2016-06-14 At&T Intellectual Property Ii, Lp Method and apparatus for presenting media programs
US20090328122A1 (en) * 2008-06-25 2009-12-31 At&T Corp. Method and apparatus for presenting media programs
US9415303B2 (en) 2008-06-25 2016-08-16 At&T Intellectual Property I, L.P. Apparatus and method for gaming
US9769532B2 (en) 2008-06-25 2017-09-19 At&T Intellectual Property Ii, L.P. Method and apparatus for presenting media programs
US10080056B2 (en) 2008-06-25 2018-09-18 At&T Intellectual Property Ii, L.P. Method and apparatus for presenting media programs
US8839327B2 (en) 2008-06-25 2014-09-16 At&T Intellectual Property Ii, Lp Method and apparatus for presenting media programs
US9584864B2 (en) 2008-06-25 2017-02-28 At&T Intellectual Property I, L.P. Apparatus and method for media on demand commentaries
US9501758B2 (en) 2008-06-25 2016-11-22 At&T Intellectual Property I, L.P. Apparatus and method for monitoring and control on a network
US20100226288A1 (en) * 2009-03-04 2010-09-09 At&T Intellectual Property I, Lp. Method and apparatus for group media consumption
US9276761B2 (en) 2009-03-04 2016-03-01 At&T Intellectual Property I, L.P. Method and apparatus for group media consumption
US8457971B2 (en) 2009-03-06 2013-06-04 At&T Intellectual Property I, L.P. Method and apparatus for analyzing discussion regarding media programs
US8275623B2 (en) 2009-03-06 2012-09-25 At&T Intellectual Property I, L.P. Method and apparatus for analyzing discussion regarding media programs
US8589168B2 (en) 2009-03-06 2013-11-19 At&T Intellectual Property I, L.P. Method and apparatus for analyzing discussion regarding media programs
US8266652B2 (en) 2009-10-15 2012-09-11 At&T Intellectual Property I, L.P. Apparatus and method for transmitting media content
US9124908B2 (en) 2009-10-15 2015-09-01 At&T Intellectual Property I, Lp Apparatus and method for transmitting media content
US9432706B2 (en) 2009-10-15 2016-08-30 At&T Intellectual Property I, L.P. Apparatus and method for transmitting media content
US8935724B2 (en) 2009-10-15 2015-01-13 At&T Intellectual Property I, Lp Apparatus and method for transmitting media content
US9661391B2 (en) 2009-10-15 2017-05-23 At&T Intellectual Property I, L.P. Apparatus and method for transmitting media content
US20110093909A1 (en) * 2009-10-15 2011-04-21 At&T Intellectual Property I, L.P. Apparatus and method for transmitting media content
US8645997B2 (en) 2009-10-15 2014-02-04 At&T Intellectual Property I, L.P. Apparatus and method for transmitting media content
US9830605B2 (en) 2009-10-30 2017-11-28 At&T Intellectual Property I, L.P. Apparatus and method for product marketing
US20110106612A1 (en) * 2009-10-30 2011-05-05 At&T Intellectual Property L.L.P. Apparatus and method for product marketing
US8224756B2 (en) 2009-11-05 2012-07-17 At&T Intellectual Property I, L.P. Apparatus and method for managing a social network
US8504484B2 (en) 2009-11-05 2013-08-06 At&T Intellectual Property I, Lp Apparatus and method for managing a social network
US20110106718A1 (en) * 2009-11-05 2011-05-05 At&T Intellectual Property I, L.P. Apparatus and method for managing a social network
US9942621B2 (en) 2009-11-06 2018-04-10 At&T Intellectual Property I, L.P. Apparatus and method for managing marketing
US8760469B2 (en) 2009-11-06 2014-06-24 At&T Intellectual Property I, L.P. Apparatus and method for managing marketing
US9565484B2 (en) 2009-11-06 2017-02-07 At&T Intellectual Property I, L.P. Apparatus and method for managing marketing
US9098867B2 (en) 2009-11-06 2015-08-04 At&T Intellectual Property I, Lp Apparatus and method for managing marketing
US20110109648A1 (en) * 2009-11-06 2011-05-12 At&T Intellectual Property I, L.P. Apparatus and method for managing marketing
US9313547B2 (en) 2009-11-10 2016-04-12 At&T Intellectual Property I, Lp Method and apparatus for presenting media programs
US8316303B2 (en) 2009-11-10 2012-11-20 At&T Intellectual Property I, L.P. Method and apparatus for presenting media programs
US9031379B2 (en) 2009-11-10 2015-05-12 At&T Intellectual Property I, L.P. Apparatus and method for transmitting media content
US8996998B2 (en) 2009-11-10 2015-03-31 At&T Intellectual Property I, Lp Method and apparatus for presenting media programs
US9681190B2 (en) 2009-11-10 2017-06-13 At&T Intellectual Property I, L.P. Method and apparatus for presenting media programs
US20110112665A1 (en) * 2009-11-10 2011-05-12 At&T Intellectual Property I, L.P. Method and apparatus for presenting media programs
US20110113440A1 (en) * 2009-11-10 2011-05-12 At&T Intellectual Property I.L.P. Apparatus and method for transmitting media content
US8387088B2 (en) 2009-11-13 2013-02-26 At&T Intellectual Property I, Lp Method and apparatus for presenting media programs
US9830041B2 (en) 2009-11-13 2017-11-28 At&T Intellectual Property I, Lp Method and apparatus for presenting media programs
US20110119725A1 (en) * 2009-11-13 2011-05-19 At&T Intellectual Property I, L.P. Method and apparatus for presenting media programs
US9351047B2 (en) 2009-11-20 2016-05-24 At&T Intellectual Property I, Lp Apparatus and method for managing a social network
US9898785B2 (en) 2009-11-20 2018-02-20 At&T Intellectual Property I, L.P. Apparatus and method for managing a social network
US9100550B2 (en) 2009-11-20 2015-08-04 At&T Intellectual Property I, L.P. Apparatus and method for managing a social network
US9986292B2 (en) 2009-11-20 2018-05-29 At&T Intellectual Property I, L.P. Method and apparatus for presenting media programs
US20110122220A1 (en) * 2009-11-20 2011-05-26 At&T Intellectual Property I, L.P. Apparatus and method for collaborative network in an enterprise setting
US8839306B2 (en) 2009-11-20 2014-09-16 At&T Intellectual Property I, Lp Method and apparatus for presenting media programs
US20110126253A1 (en) * 2009-11-20 2011-05-26 At&T Intellectual Property I, L.P. Apparatus and method for managing a social network
US8373741B2 (en) 2009-11-20 2013-02-12 At&T Intellectual Property I, Lp Apparatus and method for collaborative network in an enterprise setting
US20110126252A1 (en) * 2009-11-20 2011-05-26 At&T Intellectual Property I, L.P. Method and apparatus for presenting media programs
US9639561B2 (en) 2009-11-20 2017-05-02 At&T Intellectual Property I, L.P. Apparatus and method for managing a social network
US9380349B2 (en) 2009-11-20 2016-06-28 At&T Intellectual Property I, Lp Method and apparatus for presenting media programs
US9479844B2 (en) 2009-12-04 2016-10-25 At&T Intellectual Property I, L.P. Apparatus and method for tagging media content and managing marketing
US20110138326A1 (en) * 2009-12-04 2011-06-09 At&T Intellectual Property I, L.P. Apparatus and Method for Tagging Media Content and Managing Marketing
US9094726B2 (en) 2009-12-04 2015-07-28 At&T Intellectual Property I, Lp Apparatus and method for tagging media content and managing marketing
US10038944B2 (en) 2009-12-04 2018-07-31 At&T Intellectual Property I, L.P. Apparatus and method for tagging media content and managing marketing
US9367545B2 (en) * 2010-04-15 2016-06-14 Samsung Electronics Co., Ltd. Apparatus for providing digital content and method thereof
US20110255614A1 (en) * 2010-04-15 2011-10-20 Samsung Electronics Co., Ltd. Apparatus for providing digital content and method thereof
CN102859522A (en) * 2010-04-15 2013-01-02 三星电子株式会社 Apparatus for providing digital content and method thereof
US20120134648A1 (en) * 2010-06-16 2012-05-31 Kouji Miura Video search device, video search method, recording medium, program, and integrated circuit
US8718444B2 (en) * 2010-06-16 2014-05-06 Panasonic Corporation Video search device, video search method, recording medium, program, and integrated circuit

Also Published As

Publication number Publication date Type
JP3585844B2 (en) 2004-11-04 grant
CN1293793A (en) 2001-05-02 application
US6643643B1 (en) 2003-11-04 grant
WO2000045341A1 (en) 2000-08-03 application
EP1635243A3 (en) 2010-02-17 application
CN1293793B (en) 2010-05-12 grant
DE60044924D1 (en) 2010-10-21 grant
CA2326813A1 (en) 2000-08-03 application
EP1066595B1 (en) 2010-09-08 grant
EP1635243A2 (en) 2006-03-15 application
JP2002536730A (en) 2002-10-29 application
EP1066595A1 (en) 2001-01-10 application
EP1635243B1 (en) 2011-05-18 grant

Similar Documents

Publication Publication Date Title
Gupta et al. Semantic queries with pictures: The VIMSYS model
Yeh et al. Leveraging context to resolve identity in photo albums
Harmandas et al. Image retrieval by hypertext links
US5960422A (en) System and method for optimized source selection in an information retrieval system
Chua et al. Content-based retrieval of segmented images
US7231399B1 (en) Ranking documents based on large data sets
US6519360B1 (en) Image processing apparatus for comparing images based on color feature information and computer program product in a memory
US6314420B1 (en) Collaborative/adaptive search engine
Singhal et al. Learning routing queries in a query zone
Liu et al. Partially supervised classification of text documents
US6757691B1 (en) Predicting content choices by searching a profile database
US6560600B1 (en) Method and apparatus for ranking Web page search results
Xue et al. Scalable collaborative filtering using cluster-based smoothing
US5721902A (en) Restricted expansion of query terms using part of speech tagging
Lee Collaborative learning for recommender systems
US7509344B1 (en) Method for detecting link spam in hyperlinked databases
US6456999B1 (en) Aggregations size estimation in database services
US7627613B1 (en) Duplicate document detection in a web crawler system
US7111002B2 (en) Relevance maximizing, iteration minimizing, relevance-feedback, content-based image retrieval (CBIR)
US6775674B1 (en) Auto completion of relationships between objects in a data model
Teevan et al. To personalize or not to personalize: modeling queries with variation in user intent
US20040128301A1 (en) Method and apparatus for automatic updating of user profiles
US20030226100A1 (en) Systems and methods for authoritativeness grading, estimation and sorting of documents in large heterogeneous document collections
US6542878B1 (en) Determining whether a variable is numeric or non-numeric
US6256633B1 (en) Context-based and user-profile driven information retrieval