USO0RE42185E

(19) United States (12) Reissued Patent

(10) Patent Number: US RE42,185 E (45) Date of Reissued Patent: Mar. 1, 2011

Sekiguchi et a]. (54)

5,819,286 A

IMAGE RETRIEVAL SYSTEM AND IMAGE RETRIEVAL METHOD

7,006,714 B2 *

(75) Inventors: Shunichi Sekiguchi, Tokyo (JP); Yoshimi Isu, Tokyo (JP); Hirofumi NishikaWa, Tokyo (JP); Yoshihisa Yamada, Tokyo (JP); Kohtaro Asai,

2002/0105541 A1 *

2/2006 Kasutani 8/2002

EP GB JP

Mitsubishi Denki Kabushiki Kaisha,

(Continued) Sung et al., “Iconic pictorial retrieval using multiple attributes, ” Systems, Man, and Cybernetics, 1998, 1998 IEEE International Conference, San Diego, CA, USA,, Oct.

Related US. Patent Documents

11, 14, 1998, New York, NY, USA, IEEE, US, vol. 5, pp. 458941594, Oct. 11, 1998, XP010311152.

Reissue of:

Patent No.:

6,665,442

Issued:

Dec. 16, 2003

Appl. No.:

09/773,570

Filed:

Feb. 2, 2001

(Continued) Primary ExamineriSamir A Ahmed Assistant ExamineriAli Bayat (74) Attorney, Agent, or FirmiBirch, Stewart, Kolasch & Birch, LLP.

US. Applications:

(30)

Continuation of application No. PCT/JP00/08547, ?led on Dec. 1, 2000.

(51)

(57)

Foreign Application Priority Data

Dec. 2, 1999

(JP)

11/1998 10/1998 8/1990

OTHER PUBLICATIONS

(21) Appl. No.: 11/300,693 Dec. 15, 2005 (22) Filed:

(63)

382/305

Endou et al. .............. .. 345/738

0878767 A 0872803 A1 2-219391 A

Tokyo (JP)

(64)

Yan et a1. ............... .. 707/104.1 Takahashiet a1. .... .. 375/24001

FOREIGN PATENT DOCUMENTS

Tokyo (JP) (73) Assignee:

10/1998 Yang et al.

6,502,105 B1 * 12/2002 6,792,043 B1 * 9/2004

ABSTRACT

When a retrieval condition of an attribute list is input from a user interface unit to a retrieval processing unit, the attribute list stored in an attribute list storing unit is retrieved in the

......................................... .. 11-343256

Int. Cl.

(2006.01)

retrieval processing unit. Thereafter, attribute information

(52)

US. Cl. ...................... .. 382/224; 382/190; 382/195;

played on a displaying unit. Thereafter, When a retrieval con

(58)

Field of Classi?cation Search ................ .. 382/232,

G06K 9/62

conforming to the retrieval condition is output to and dis

dition of the similarity retrieval is input from the user inter face unit to the retrieval processing unit, image data stored in the image information storing unit is retrieved in the retrieval processing unit, and speci?c image data relating to a charac teristic descriptor set conforming to the retrieval condition is selected in the retrieval processing unit. Thereafter, the spe ci?c image data is output to and displayed on the displaying

382/232; 382/305

382/224, 217, 305, 236, 190; 348/231.99; 707/104.1, 3, 6, 2, 100, 102 See application ?le for complete search history.

(56)

References Cited

unit. U.S. PATENT DOCUMENTS

5,465,353 A

11/1995 Hull et al.

28 Claims, 17 Drawing Sheets

, --------------- --

-

I

1

g

5

:

_-

____ __ _

SERVER

IMAGE DATA BASE PRODUCING UNIT

7

k

1 I

ATTRIBUTE DATA

|

ATTRIBUTE LIST

|

PRODUCING UNIT

5

l

6 CHARACI'ERISTIC

m. E

CHARACTERIS'I'IC

__

- DESCRIPI'OR sEI'

:

EXTRACIZNG uurr

PRODUCI‘NG UNIT

I

3

4 ____

{

--- ................. --.,

I I

\__

8

l

IMAGE RETR'EWNG UNIT

:

I 2 | 5 ll

"

STORING UN"

RErRIEvAI.

-

INs'rRucI'IoN

:

___________ __

RErRIEvAI.

-

l

: 10

s

l

RETRIEVAL PROCBSING

l

l I I

INSTRUCTION

: I

5 __

:

__ ___

_ _ _ __

____I - _ '7

i 9 IMAGE DATA

CLIENT

_ '\

11

l

S

:

|

s

|

USER INTERFACE

DISPLAYING

|

UNIT

UNIT

l

I I

I

I

\ ________________ _ _ _¢

US RE42,185 E Page 2

FOREIGN PATENT DOCUMENTS JP JP JP JP JP JP JP JP TW TW TW WO

3-270388 6168277 9-270006 09282324 10091634 10124655 10-320400 11224266 84112558 85104458 85112595 WO-98/21688

A A

A

12/1991 6/1994 10/1997 10/1997 4/1998 5/1998 12/1998 8/1999 11/1995 4/1996 10/1996 5/1998

Shibata, Masahiro, Temporal Video Segmentation for Scene Description, Transactions of the Institute of Electronics,

Information and Communication Engineers, Apr. 25, 1999, vol. J82*D*11,No. 4, pp. 7324742. Yoshimi Isu et al., “XML Kijutsu wo mochiiru Contents

Kensaku Jikken System no Kouchiku”, Proceedings of

Information System Society Meeting in 1999, the Institute of Electronics, Information and Communication Engineers (Sep. 7, 1999), p. 132, Fig. 1.

JauiYuen Chen et al., “ViBE: a new paradigm for Video database browsing and search, ” ContentiBased Access of

“Synthesis and Evalution of the Image Database with Fully Automated Keyword Extraction by State Transition Model and Scene Description Language”, Institute of Electronic Information and Communication Engineers ofJapan, Dill vol. J79iDill No. 4, pp. 4764483, Apr. 1996.

Image and Video Libraries, 1998, Proceedings, IEEE Work shop on Santa Barbara, CA, USA, Jun. 21, 1998, Los Alami tos, CA, USA, IEEE Comput. Soc., US, 1998, pp. 964100,

“A critical evaluation of mage and Video indexing techniques in the compressed domain”, M.K. Mandal et al., Image

XP010293858.

ViSiOI’l Computing, 17, 5134529, 1999.

A

OTHER PUBLICATIONS

Hatano, Kenji, New Generation Database Technology, Authoring and Retrieval of Video Scenes by Multiilevel Sel fmrganizing Maps, Transactions of the Institute of Informa

Ono et al., IEICE, DAII vol. J79, No. 4, pp. 476483 (1996)

w/partial English Translation.

tion Processing Society of Japan, Apr. 15, 1998, VOl. 39, No. 4, pp. 933942.

* cited by examiner

US. Patent

Mar. 1, 2011

Sheet 1 0f 17

US RE42,185 E

FIG.1 (PRIOR ART) 101

102

S

S

PREPARATION UNIT

103

RETRIEVAL TOOL

104

A

IMAGE

S

CONCEPTION —»

KEYWORD

EXTRACTING UNIT

9 ,

I;

108

Eo

AREA

7

[4,] E

DIVIDING

E3 5;

UNIT

-

SCENE DESCRIPTION V

KEYWORD

DESCRIBING UNIT

i E I: 5

~

109

I

105

U9D

1; 0 106 ~ DESCRIPTION

107 ~

g; m 2

USER

PARAMETER INPUT N112

111~

US. Patent

Mar. 1, 2011

US RE42,185 E

Sheet 3 0f 17

FIG?» START

1 I

3T1.~

5T2

~

I

?’??g?gg" 0F IMAGE

EXTRACTION OF IMAGE

(TEXT INFORMATION) I

CHARACI‘ERJSTIC VALUE

~ 8T4

r PRODUCTION OF

PRODUCTION OF

A'I'I‘RIB UTE LIST

ggggagrrg?'ggc

I

1

REGISTRATION OF

CHARACTERISTIC

A'I'I‘RIBUTE LIST

DESCRIWOR SET

~

5T5

REGISTRATION OF ST3 ~

END

I CALCULATION OF AVERAGE ~ ST15_1

MAGNITUDE OF MOTION I

THRESHOLD PROCESSING

~ST15-2

II

PRODUCI‘ ION OF ACTIVITY OF MOTION DISTRIBUTION

l

r» STlS-3

~ ST6

US. Patent

Mar. 1, 2011

Sheet 5 or 17

US RE42,185 E

WA21C.

_

_

_

+4:41!

QUE

MOA U I

/uoqmdlz

Am8muzw2niM25

US. Patent

Mar. 1, 2011

Sheet 7 or 17

US RE42,185 E

FIG.8 SHORT RUN

MIDDLE RUN

O 0 LONG RUN

DCUInI 0R

DCVIn'I

L

avg std (DISPERSION FROM AVERAGE) > TIME

US. Patent

Mar. 1, 2011

Sheet 8 or 17

US RE42,185 E



MPEG-1 CD



A: alWideoMail ¥Shun 5&5 meeting. mpeg



10.5





47.5

50.2

55

CHARACI‘ERISTIC

_

VALUE SET EXTRACI‘ED



FROM VIDEO BIT

fPDG'

STREAM

dUDC>



CHARACTERISTIC DESCRIP'TOR SET

(XML DOCUMENT)

DEFINITION FILE FOR DESCRIBING CHARACTERISTIC VALUES

(CHARACTERISTIC VALUE DESCRIPTION DATA CLASS) (DTD)

US. Patent

Mar. 1, 2011

US RE42,185 E

Sheet 10 0f17

I INPUT OF RETRIEVAL CONDITION

~ST18

FIG. 12

I ST19 CONFORMITY JUDGMENT OF ATTRIBUTE

INCONFORMITY

CONFORMITY TRANSFER OF CONFORMITY RESULT TO DISPLAYING UNIT

DISPLAY OF RETRIEVAL RESULT

sT23

~ ST2O

ST22 REPRODUCTION INSTRUCTION

INSTRUCTION OF REPRODUCTION/SIMILARTT Y RETRIEVAL

ST24

RETRIEVAL INSTRUCTION

S

SELECTION OF DISPLAYED IMAGE

SELECTION OF SIMILAR

RETRIEVED IMAGE 5

ST26

V

REPRODUCTION AND DISPLAY OF SELECTED IMAGE

ST27 CONFORMITY JUDGMENT OF CHARACTERISTIC DESCRIPTOR INCONFORMITY CONFORMITY TRANSFER OF CONFORMITY RESULT TO DISPLAYING UNIT

néM?

ST29

(M:LENGTH OF LIST OF CHARACTERISTIC DESCRIPTOR

SETS) YES

5

ST25

~ ST28

US. Patent

Mar. 1, 2011

Sheet 11 0f 17

Ta, min, Ta, maxzTHRESHOLD VALUES

OF CHARACTER DESCRIPTOR "a" (Ta, min
US RE42,185 E

13 L

3127.]

TCNpminécNpgTCNpmax?

3: YES N0

‘__€

5

ST27-2

S

5

TNsr.min--Nsr——TNsr.max?

l YES NO

s

S

3"

ST27-3 9

NO

kc

=

5



TNlnminéNlrsTNlr.max'-7

2"

T n=l

l NO

h:

5

TavgY.min--S—avgYlnlgTavgYmax?

I YES NO

H‘:

*"t

1*

TstdYmingstdYmjsTstdYmax?

Ts‘duminéstdUlnlgTmum?

I YES N0

‘—"c

TstdvmingstdvlnjgTstdvmax?

T n=n+l

INCONFORMITY JUDGMENT

3"

S'I‘27-7

Tavgvminsavgv[n]--TavgV.max?

1 YES NO

8127-6 ‘

I YES NO

3"

TavgUJuingavgUln]§TavgU.max?

I YES "i

STZ7-5

NO CONFORMITY JUDGMENT

—_

ST27-8 ‘

3'

ST27-9 ‘

23"

ST27-l0 5

2:

US. Patent

QNUE

Mar. 1, 2011

Sheet 17 0f 17

US RE42,185 E

2mZMO0FC5DU4E.PQ2 OZ78OE0/‘:5S8 O"21:25

O2.95 82

02nE035o2

5muczib? 532m 2ZEO0C5U.ME2Q vmui.h6é 5Ezm8p2mv%

PMZO
US RE42,185 E 1

2

IMAGE RETRIEVAL SYSTEM AND IMAGE RETRIEVAL METHOD

segment of the image, and an image retrieval processing is

performed for the image. However, in the above-described image retrieval process ing system, an identity of characteristic values is checked by using keywords such as conception keywords and scene description keywords selected by the user 112 and keywords attached to each image, and an image retrieval processing is performed according to the characteristic values of each image. Therefore, all images are searched according to only

Matter enclosed in heavy brackets [ ] appears in the original patent but forms no part of this reissue speci?ca tion; matter printed in italics indicates the additions made by reissue. Notice: More then one reissue application has been ?led

the characteristic values of the images, so that it takes a lot of time to retrieve a desired image.

for the reissue of US. Pat. No. 6,665,442. The reissue appli cations are application Ser. No. 11/300,693, and Divisional

Also, in the above-described image retrieval processing

Reissue application Ser Nos. 11/932,022, 11/933,358, and 12/603,268 all ofwhich are divisional reissues of US. Pat. No. 6,665,442.

system, a description method or a storing method of each

keyword is not considered. Therefore, it is required that a plurality of image servers relate to a plurality of retrieval tools denoting clients in one-to-one correspondence. As a result, a system, in which many users respectively perform

CROSS-REFERENCE TO The RELATED APPLICATION

This application is a continuation of International Appli cation No. PCT/JP00/08547, whose International ?ling date is Dec. 1, 2000, the disclosures of which Application are

the image retrieval through a network while using various retrieval tools, cannot be provided for the users. 20

Also, because only static images are processed in the image retrieval, it is dif?cult to retrieve a desired moving

incorporated by reference herein.

image.

BACKGROUND OF THE INVENTION

SUMMARY OF THE INVENTION

1. Field of the Invention The present invention relates to an image retrieval system and an image retrieval method in which characteristic values and/or pieces of attribute information are extracted from

The present invention is provided to solve the above problems, and a main object of the present invention is to provide an image retrieval system and an image retrieval method in which an image retrieval processing can be e?i

25

ciently performed.

pieces of image data such as moving images or static images recorded in analog or digital and in which the retrieval of

desired image data is performed by using the extracted char acteristic values and/or the pieces of extracted attribute information. 2. Description of Related Art FIG. 1 shows the con?guration of a system as an example

30

35

of a conventional image retrieval processing system. This system is disclosed in a letter “Synthesis and Evaluation of

the Image Database with Fully Automated Keyword Extrac tion by State Transition Model and Scene Description Lan guage” edited by Institute of Electronic Information and Communication Engineers of Japan, D-II Vol. J79-D-II No.4, pp.476*483, April of 1996. In this system, static

be easily performed by extracting a characteristic value for 40

An image retrieval system according to the present invention, comprises a characteristic descriptor producing 45

plurality of keywords are attached to each divided segment. As the keywords, a conception keyword and a scene descrip tion keyword are prepared. In a conception keyword extract ing unit 104, a conception keyword 108 of each segment is obtained according to a color and a characteristic value of

50

cated to color information in advance. In a scene description

55

60

condition, receiving a second retrieval condition relating to a

storing unit for one piece of image data conforming to the second retrieval condition and outputting the piece of image

words. In a characteristic identifying unit 110, an identity of

108 or the scene description keyword 109 attached to each

input image data, and an image retrieving unit for receiving a ?rst retrieval condition relating to attribute information, searching the attribute list produced in the attribute list pro ducing unit for one piece of attribute information conform ing to the ?rst retrieval condition, outputting the piece of attribute information conforming to the ?rst retrieval

characteristic descriptor, searching the image information

keyword as each of keywords 112 from the prepared key 112 selected by the user 111 with the conception keyword

tic descriptor for each piece of input image data, an image information storing unit for storing the characteristic descriptors produced in the characteristic descriptor produc ing unit while holding the correspondence of each character to a piece of attribute information attached to each piece of

keyword describing unit 105, a predicate relating to “position”, “color”, “shape”, “size”, “direction” or the like is

characteristic values is checked by comparing each keyword

unit for extracting a plurality of image characteristic values from pieces of input image data and producing a characteris

istic descriptor to one piece of input image data, an attribute list producing unit for producing an attribute list according

the segment by using conception keywords respectively allo

obtained from a plurality of image characteristic values of segments. In the unit 105, an operation 106, in which a user 107 selects one predicate from predicates de?ned in advance and describes the selected predicate, is required, and the selected predicate is output as a scene description keyword 109. In a retrieval tool 102, conception keywords and scene description keywords are prepared in advance. A user 111 selects one conception keyword and one scene description

each video segment, which is composed of a plurality of frames, in place of the extraction of a characteristic value for each frame when a plurality of keywords are extracted from

moving images.

images are processed in the image retrieval. That is, an area of each of images is divided into a plurality of segments in an area dividing unit 103 of a preparation unit 101, and a

A subordinate object of the present invention is to provide an image retrieval system and an image retrieval method which does not depend on a plurality of image servers dis tributed in a network by describing and producing a plurality of retrieval keywords according to a common syntax. Another subordinate object of the present invention is to provide an image retrieval system and an image retrieval method in which the retrieval of a desired moving image can

65

data conforming to the second retrieval condition. Therefore, the retrieval can be ef?ciently performed. In an image retrieval system according to the present invention, the attribute list is produced according to a syntax,

Image retrieval system and image retrieval method

Dec 15, 2005 - face unit to the retrieval processing unit, image data stored in the image information storing unit is retrieved in the retrieval processing unit, and ...

3MB Sizes 1 Downloads 401 Views

Recommend Documents

Image Retrieval: Color and Texture Combining Based on Query-Image*
into account a particular query-image without interaction between system and .... groups are: City, Clouds, Coastal landscapes, Contemporary buildings, Fields,.

A Robust Content-Based Image Retrieval System ...
GCH and 2-D Haar wavelet transform using the cosine distance gives good ..... January 1999. http://www.unn.ac.uk/iidr/report.html. [2] Christopher C. Yang, ...

SemRetriev – an Ontology Driven Image Retrieval System
Jul 9, 2007 - prototype system for image retrieval which combines the use of an ontology which structures an ... SemRetriev is meant to show that the use of semantic .... After the elimination of invalid links and invalid files, there are around ...

Robust Content Based Image Retrieval system using ... - Dipan Pal
robust classification shows that the image database can be expanded while ... algorithm which tries to capture the data modeling and processing ... input during learning of the spatial pooler is compared with .... big advantage in scalability.

Robust Content Based Image Retrieval system using ... - Dipan Pal
machine learning, pattern recognition and computer vision to search large image databases. Some CBIR systems employ processing over text annotations and ...

Evaluating Content Based Image Retrieval Techniques ... - CiteSeerX
(“Mountain” class); right: a transformed image (negative transformation) in the testbed ... Some images from classes of the kernel of CLIC ... computer science.

CONTENT-FREE IMAGE RETRIEVAL USING ...
signed value of one is denoted by XE = {Xj1 , ..., XjE } and is called the ... XE is in practice much smaller than. XH. .... Fourteen trademark examiners in the Intel-.

Semantic Image Retrieval and Auto-Annotation by ...
Conventional information retrieval ...... Once we have constructed a thesaurus specific to the dataset, we ... the generated thesaurus can be seen at Table 5. 4.3.

Method and system for image processing
Jul 13, 2006 - images,” Brochure by Avelem: Mastery of Images, Gargilesse,. France. Porter et al. ..... known image processing techniques is that the image editing effects are applied ..... 6iA schematic illustration of the FITS reduction. FIG.

Image Retrieval: Color and Texture Combining Based ...
tion has one common theme (for example, facial collection, collection of finger prints, medical ... It is possible to borrow some methods from that area and apply.

Image Retrieval Based on Wavelet Transform and Neural Network ...
The best efficiency of 88% was obtained with the third method. Key Words: .... Daubechies wavelets are widely used in signal processing. For an ..... Several procedures to train a neural network have been proposed in the literature. Among ...

Method and system for image processing
Jul 13, 2006 - US RE43,747 E. 0 .File Edi! Monan Palette Llybul. 09 Fib Edit Malian PM L. II I ... image editing packages (e.g. MacIntosh or Windows types), manipulates a copy of ...... ¢iY):ai(X>Y)¢ii1(X>Y)+[1_ai(X>Y)l'C. As there is no ...

Shape Indexing and Semantic Image Retrieval Based on Ontological ...
Retrieval Engine by NEC USA Inc.) provides image retrieval in Web by ...... The design and implementation of the Redland RDF application framework, Proc.

Shape Indexing and Semantic Image Retrieval Based on Ontological ...
Center retrieves images, graphics and video data from online collections using color, .... ular class of image collection, and w(i,j) is semantic weight associated with a class of images to which .... Mn is defined by means of two coordinates (x;y).

Enhancing Image and Video Retrieval: Learning via ...
School of Computer Science and Engineering and the Center for Neural Computation. The Hebrew ... on the clustering and retrieval of surveillance data. Our.

Interactive and progressive image retrieval on the ...
INTERNET, we present the principle of an interactive and progressive search ... make difficult to find a precise piece of information with the use of traditional text .... images, extracted from sites of the architect and providers of building produc

An active feedback framework for image retrieval - Semantic Scholar
Dec 15, 2007 - coupled and can be jointly optimized. ..... space when user searches for cars images. ..... Optimizing search engines using click through data.

Shape-Based Image Retrieval in Logo Databases
In recent several years, contents-based image re- trieval has been studied with more attention as huge amounts of image data accumulate in various fields,.

Content-Based Medical Image Retrieval Using Low-Level Visual ...
the retrieval task of the ImageCLEFmed 2007 edition [3], using only visual in- ..... models that mix up textual and visual data to improve the performance of our.

Content-Based Histopathology Image Retrieval Using ...
visualization, annotation[9] and retrieval[10], among others, are being exploited for ... [8] create a correlation matrix of mean centered data set, then this matrix is ...

An active feedback framework for image retrieval
may lead to faster convergence of relevance feedback. Experiments in (Jing et al., ...... SPIE Conf. on Storage and Retrieval for Image and Video Database, vol.

Web Image Retrieval Re-Ranking with Relevance Model
ates the relevance of the HTML document linking to the im- age, and assigns a ..... Database is often used for evaluating image retrieval [5] and classification ..... design plan group veget improv garden passion plant grow tree loom crop organ.

Content-Based Image Retrieval Systems: A Survey
Oct 28, 2002 - (This is one of the so-called Socratic dialogues, where two persons ... Below we describe a number of content-based image retrieval systems, in alphabetical ...... Applications The database consists of 400 advertisements and 800 color