Digital imaging: objects The Beazley Archive, CLAROS and The World - - PowerPoint PPT Presentation

▶
digital imaging objects
SMART_READER_LITE
LIVE PREVIEW

Digital imaging: objects The Beazley Archive, CLAROS and The World - - PowerPoint PPT Presentation

Sep 25, 2022 285 likes •928 views

Beazley Archive Classical Art Research Centre Ioannou School for Classical and Byzantine Studies Digital imaging: objects The Beazley Archive, CLAROS and The World of Ancient Art of Ancient Art Donna Kurtz Beazley Archive Donna Kurtz,

slide-1
SLIDE 1

Beazley Archive Classical Art Research Centre Ioannou School for Classical and Byzantine Studies

Digital imaging: objects

The Beazley Archive, CLAROS and The World

  • f Ancient Art
  • f Ancient Art

Donna Kurtz Beazley Archive Donna Kurtz, Beazley Archive Sebastian Rahtz, OUCS Andrew Zisserman, Engineering Science

slide-2
SLIDE 2

Sir John Beazley

1885-1970 Photograph by Cecil Beaton

slide-3
SLIDE 3

http://news.bbc.co.uk/1/hi/england/oxfordshire/8347232.stm

slide-4
SLIDE 4
slide-5
SLIDE 5
slide-6
SLIDE 6
slide-7
SLIDE 7
slide-8
SLIDE 8
slide-9
SLIDE 9

Ashmolean Museum, Cast Gallery b t basement

slide-10
SLIDE 10
slide-11
SLIDE 11
slide-12
SLIDE 12
slide-13
SLIDE 13
slide-14
SLIDE 14
slide-15
SLIDE 15
slide-16
SLIDE 16
slide-17
SLIDE 17
slide-18
SLIDE 18
slide-19
SLIDE 19
slide-20
SLIDE 20
slide-21
SLIDE 21
slide-22
SLIDE 22

CLAROS System Components

Beazley Archive DAI Arachne LGPN (Oxford) LIMC (Paris) Archive Arachne (Oxford) (Paris) Convert Convert Convert Convert CIDOC-CRM Cache data Cache Index Query

Links back to original data

CLAROS application Browser

Other potential applications

application

slide-23
SLIDE 23
slide-24
SLIDE 24
slide-25
SLIDE 25
slide-26
SLIDE 26
slide-27
SLIDE 27
slide-28
SLIDE 28

The place of images

representation of real-world objects pottery, gems, sculpture

  • bjects as holders of textual sources

images of inscriptions and coins representations of time and place chronological mapping representations of time and place chronological mapping input and interaction “what is this pottery shape I am showing ?” you?” first class objects antiquarian photographs visualization charts, plots, etc

slide-29
SLIDE 29

Behind CLAROS

  • The CLAROS infrastructure relies upon a set of technology

standards:

  • a common ontology − CIDOC CRM conceptual reference model
  • a common approach to data management − RDF
  • working practices:
  • working practices:
  • federation not aggregation − devolved responsibility
  • collaboration − more than Oxford
  • proportionality and subsidiarity − no attempt at a universal model
  • open data − we are not the only users
  • and assumptions:

p

  • open licensing − no data hoarding
  • no limits − world wide
  • f i

t d l t li it d t d i

  • a range of impact models − not limited to academia
slide-30
SLIDE 30

CLAROS initial collaborators

  • Beazley Archive:

 150,000 Pottery records and 130,000 images  50 000 Engraved gem and cameo records and 30 000 images  50,000 Engraved gem and cameo records and 30,000 images  900 cast records of classical sculpture and 2000 images  900 Antiquarian photographs

  • Lexicon of Greek Personal Names:

 400,000 recorded individuals. Over 35,000 unique personal names

from 2500 places p

  • Cologne Research Sculpture Archive

 250,000 Sculpture records, 490,000 images

  • German Archaeological Institute:

German Archaeological Institute:

 1,500,000 photographs

  • Lexicon Iconographicum Mythologiae Classicae (Paris):

100 000 d 180 000 i f th l i l d li i

 100,000 records, 180,000 images of mythological and religious

iconography from 2,000 museums and collection

slide-31
SLIDE 31

Disparate technologies

Beazley Archive

  • ‘XDB’ – XML data, SQL Server Database, ASP front end

, , Cologne Research Archive and German Archaeological Institute Institute

  • ‘Arachne’ - MySQL database, PHP front end.

LIMC LIMC

  • MySQL database, PHP front end.

LGPN LGPN

  • Ingres relational database, also available as an eXist XML

database serving TEI-XML data. XQuery front end.

slide-32
SLIDE 32

The CLAROS data web approach

  • No changes to the databases of the individual sources
  • Semantic differences between data sources are resolved by

mapping selected metadata from each source to CIDOC-CRM

  • Syntactic differences between data sources are resolved by

converting the selected metadata to RDF, accessed from a single triple store using SPARQL single triple store using SPARQL

  • CLAROS is a resource discovery service − all results link

b k t h t d t b back to host databases The job of CLAROS is provide cacheing, indexing and querying services

slide-33
SLIDE 33

CIDOC Conceptual Reference Model (CRM)

slide-34
SLIDE 34

CIDOC CRM in CLAROS

  • CIDOC CRM Core can describe the complex provenance of

artefacts and their relationships with key events, people, places and times places and times

  • The CIDOC CRM "E55.Type" system is particularly useful to

i f d/d ill d i i i l b h permit faceted/drill-down queries, e.g. restricting results by the shape of a pot

  • We focused initially on the CIDOC CRM Core terms, and

employed additional terms as necessary. Some additional RDF vocabulary for time metadata relating to imprecise periods and y g p p eras i.e. <claros:not_before> and <claros:not_after>, applied to a <crm:E61.Time_Primitive object>

slide-35
SLIDE 35
slide-36
SLIDE 36

The CIDOC route to 2nd century BC Ath i h Athenian amphorae

E22.Man-Made_Object P2.has type P2.has_type E55.Type P127.has_broader_term "Amphora" P108I.was produced by P108I.was_produced_by E12.Production P4.has_time-span E52.Time-Span P82.at some time within P82.at_some_time_within E61.Time_Primitive ; not_before "-0300" not_after "-0200" P16I.was used for 6 as_used_ o E7.Activity P2.has_type "Object" P7.took_place_at E53.Place P87.is_identified_by E48.Place_Name "Athens"

slide-37
SLIDE 37
slide-38
SLIDE 38

Each data partner may create their own i t f interface, e.g.:

slide-39
SLIDE 39
slide-40
SLIDE 40

Some ongoing partner projects

  • MILARQ (Oxford)

 investigate performance issues with complex queries in RDF

  • Metamorphoses (Oxford)

 establish a working co-reference system for name, place and date

information

 develop and document import for into the CLAROS RDF database  provide web-based tools for geo-temporal cross-searching and

visualization of the database visualization of the database

  • STAR/Stellar (Glamorgan)

 extraction of semantic data from unstructured text (archaeological

report) report)

  • Zoology (Oxford)

 flyweb, semantic web, and text mining projects

O f d R E j t

  • Oxford Roman Economy project

 adding new types of economic data

slide-41
SLIDE 41

Lessons

  • We are in a very different state from 10 years ago, with

 mapping and satellite services from Google and others

mapping and satellite services from Google and others

 semantic web technologies which deliver on their promise  Web 2.0 approaches which let us write exciting interfaces

i i ti f f t d t

 an increasing assumption of free access to data  an expectation of data for computers, not just humans

  • CLAROS is an exemplar virtuous virtual collaboration with no

centre and no boundaries, a club anyone can join

  • We demonstrate that the RDF approach based on a wide-

ranging ontology is not exotic, constraining or hard to use

slide-42
SLIDE 42

Challenges

  • Deliver a system in which searching for “Athens” does not take

5 minutes to respond (there are a lot of references to Athens…)

  • Join data relating to places in a more formal way

 linking via a common gazetteer  modelling changes of name and location across time  understanding degrees of accuracy in provenance claims

  • Establish appropriate interfaces across the spectrum

 SPARQL endpoint for deep access  RESTful URIs for common data queries  Explorer style data exploration  Explorer-style data exploration  Dynamic data-driven visualizations for teaching  Intelligent Companions to formulate queries  Rich mobile-delivered resources for museum visitors  Linked community-led collections

slide-43
SLIDE 43

Visual Access to Classical Art Visual Access to Classical Art Archives within CLAROS Archives within CLAROS

Relja Arandjelović and Andrew Zisserman

Department of Engineering Science Department of Engineering Science University of Oxford

slide-44
SLIDE 44

The Objective …

To enable an image archive to be searched on its visual content with the same ease and success as a Google search of the web (text documents).

The Beazley Vase Archive

?

Visually defined query

Currently: 111 thousand images

slide-45
SLIDE 45

Example

Search results query q y

?

Results are:

  • immediate
  • unaffected by scale and image rotation (affine transformations)
  • unaffected by scale and image rotation (affine transformations)
  • for exact matches only
slide-46
SLIDE 46

Upload query image from a file or web page or a mobile phone Matches in the Beazley vase archive

Query from URL Q y

?

http://arthur.robots.ox.ac.uk:8084/

slide-47
SLIDE 47

Meta-information for matches

slide-48
SLIDE 48

How it works

Representation: bag of (visual) words

  • Visual words are ‘iconic’ image patches or fragments

Image Collection of visual words

slide-49
SLIDE 49

Visual vocabulary unaffected by scale and viewpoint y y p

The same visual word The same visual word

slide-50
SLIDE 50

Image representation using visual words

Use efficient Google like search on visual words

slide-51
SLIDE 51

The Arachne Classical Sculptures Archive

Retrieve images from the collection using only visual information

?

Visually defined query

Currently: 89 thousand images 21 thousand objects

slide-52
SLIDE 52

Example

Search results

query

?

slide-53
SLIDE 53

Upload query image from file or URL

Search results

Query from URL Query from URL

?

slide-54
SLIDE 54

Visual search for the archivist

  • Check visually if an item is already in the archive, or check

f d li t t i for duplicate entries

  • For example, in the Beazley vase archive …

Method:

  • use each image in turn as a query for retrieval
  • determine if all the matching vases have the same id
slide-55
SLIDE 55

Example:

2 copies with different IDs, and different fabric

slide-56
SLIDE 56

Image Classification

  • previously: search for exact matching vase

now: classify vase by its shape

Visually defined query

  • now: classify vase by its shape

“It is an amphora Data

… and here are similar

  • bjects in the archive”

What is this?

slide-57
SLIDE 57

Shape Representation

  • riginal image

foreground separation silhouette representation t vector

X1

1

X2 . .

x1 x2

. Xn

x

  • No representation of patterns or surface markings
  • 100-dimensional “vase shape space”

100 dimensional vase shape space

slide-58
SLIDE 58

Vase shape space

slide-59
SLIDE 59

Compute three nearest neighbours for each vase

query

classify shape all three are neck amphorae neck-amphorae

“judge me by the company I keep” “vase shape space”

slide-60
SLIDE 60

Step by step demonstration:

Step 1: upload image

slide-61
SLIDE 61

Step by step demonstration:

Step 2: classify shape

slide-62
SLIDE 62

Step by step demonstration:

Step 3: matches in CLAROS

slide-63
SLIDE 63

Future Developments

Short term (this year): 3D retrieval

p

Medium term: classification of decorations

“Herakles and the lion” Herakles and the lion

Longer term: predict artist/age

slide-64
SLIDE 64