tool for pictorial contents retrieval ist ka3: semantic web technologies workshop zdenek mikovec,...

7
Tool for pictorial contents retrieval IST KA3: Semantic Web Technologies Workshop Zdenek Mikovec, Pavel Slavik Czech Technical University Prague Department of Computer Science and Engineering November 2000 department of computer science and engineering

Upload: madlyn-phelps

Post on 23-Dec-2015

214 views

Category:

Documents


0 download

TRANSCRIPT

Page 1: Tool for pictorial contents retrieval IST KA3: Semantic Web Technologies Workshop Zdenek Mikovec, Pavel Slavik Czech Technical University Prague Department

Tool for pictorial contents retrieval

IST KA3: Semantic Web Technologies Workshop

Zdenek Mikovec, Pavel SlavikCzech Technical University Prague

Department of Computer Science and Engineering

November 2000

department of computer scienceand engineering

Page 2: Tool for pictorial contents retrieval IST KA3: Semantic Web Technologies Workshop Zdenek Mikovec, Pavel Slavik Czech Technical University Prague Department

department of computer scienceand engineering

Content

• motivation, problems & solutions• implementation• results and future work

Page 3: Tool for pictorial contents retrieval IST KA3: Semantic Web Technologies Workshop Zdenek Mikovec, Pavel Slavik Czech Technical University Prague Department

department of computer scienceand engineering

Motivation, problems &

solutions• traditional approach to picture information

retrieval: histograms, keywords, ...• problems & solutions

– P: pure description of picture structure&semantic– S: introduction of relations among picture objects

• relations could be of two principal classes:– structural (they reflect visual structure)– functional (they reflect semantic relations among

object)

– P: efficient information retrieval from pictures– S: information filtering and pictorial information

inference– P: query result presentation in a suitable picture

format– S: suitable formal description of transformation

process

Page 4: Tool for pictorial contents retrieval IST KA3: Semantic Web Technologies Workshop Zdenek Mikovec, Pavel Slavik Czech Technical University Prague Department

department of computer scienceand engineering

Implementation

• all mentioned requirements could be satisfied by the use of XML and XSL transformation sheets

DBS (XML)

DBS (XML)

new relation

specification (XSL)

spatial specification

(XSL)

DBS (XML)

vis

ualiza

tio

n (

XS

L)

VRML

Web

C

GM

requests

feedback

metric definitio

n

filtering informatio

n(XQL)

DBS (XML)

MPEG-7WebCG

M(XML)

imp

ort

(XS

L)

MP

EG

-7

1.

2a. 2b. 3.

4.

BROWSING USER d

escri

pti

on

b

row

sers

5.

XSL pipeline

Page 5: Tool for pictorial contents retrieval IST KA3: Semantic Web Technologies Workshop Zdenek Mikovec, Pavel Slavik Czech Technical University Prague Department

department of computer scienceand engineering

Results and future work

• described system– semantic views and filters– simpler querying– corresponds with current trends (MPEG-7)

• system has been implemented and tested– picture databases on WAP– picture information retrieval for blind people

Pre-defined dynamically adapting XSL pipeline

DBS new rel. generatio

n

DBS

Web

C

GM

requests

feedback

metric definition

DBS spatial specificatio

n

vis

ualiza-

tion

DBS filtering inform

MP

EG

-7

MPEG-7WebCG

M

imp

ort

BROWSING USER

choose import sheet

choose visualization

sheet

VR

ML

Page 6: Tool for pictorial contents retrieval IST KA3: Semantic Web Technologies Workshop Zdenek Mikovec, Pavel Slavik Czech Technical University Prague Department

department of computer scienceand engineering

Page 7: Tool for pictorial contents retrieval IST KA3: Semantic Web Technologies Workshop Zdenek Mikovec, Pavel Slavik Czech Technical University Prague Department

department of computer scienceand engineering

Information inference

<?XML version="1.0"?><movie name="M.A.S.H."><popularity>7</popularity><type>comedy</type>

</movie><movie name="Indiana Jones"<popularity>9</popularity><type>action</type>

</movie>

<?XML version="1.0"?><movie name="M.A.S.H."><popularity>7</popularity><type>comedy</type><funny>7</funny>

</movie><movie name="Indiana Jones"<popularity>8</popularity><type>action</type><funny>4</funny>

</movie>

trans-formatio

n

type.comedy=1type.action=0.5funny=type*popularity

New information - transformation rules (XSL)

Original DBS (XML)

DBS with new relations (XML)