NICI, Nijmegen Institute for Cognition and Information
Lambert Schomaker
Edward de Leau
Louis Vuurpijl
University of Nijmegen, P.O.Box 9104
6500 HE Nijmegen, The Netherlands
Tel: +31 24 3616029 / Fax: +31 24 3616066
schomaker@nici.kun.nl
hwr.nici.kun.nl
Schomaker, de Leau & Vuurpijl
Schomaker, de Leau & Vuurpijl
projects in the Cognitive Engineering
group at NICI :
Content-Based Image Retrieval
overview
usability problems in image-based retrieval
Question | Yes | No | NA |
"Did you need an image ..." | |||
"...with a particular object on it?" | 122 | 41 | 7 |
"...with a particular color on it?" | 25 | 137 | 8 |
"...with a particular texture on it?" | 23 | 137 | 10 |
(results of a WWW questionnaire, N=170 responses)
Schomaker, de Leau & Vuurpijl
Schomaker, de Leau & Vuurpijl
usability problems in image-based retrieval
what do users want?
often: the 'basic categories' (Rosch, 1972)
cf. Hoenkamp, Schomaker & Stegeman, SIGIR'99
or 'layout structures'
queries and matching methods
in image-based search
Query Matched with: Matching algorithm
A keywords manually provided textual free text and information-
image annotations retrieval (IR) methods
B keywords textual and contextual information free text and
in the image neighbourhood IR methods
C exemplar image image bitmap template matching or
feature-based
D layout structure image bitmap texture and color segmentation
E object outline image bitmap, contours feature-based
F object sketch image bitmap feature-based
Schomaker, de Leau & Vuurpijl
Schomaker, de Leau & Vuurpijl
Schomaker, de Leau & Vuurpijl
usability problems in image-based retrieval
questions:
design considerations
animal collection outlines
typical bodyworks shape of motor bicycle
(note the distribution of points of high curvature along the outline)
Schomaker, de Leau & Vuurpijl
A query to find an engine
bodyworks shapes of motor bicycle
Schomaker, de Leau & Vuurpijl
motor-bicycle collection
driver shapes
Schomaker, de Leau & Vuurpijl
motor-bicycle collection
engine shapes
Schomaker, de Leau & Vuurpijl
motor-bicycle collection
frame shapes
Schomaker, de Leau & Vuurpijl
Simple 1-NN matching will be used for all feature categories.
Schomaker, de Leau & Vuurpijl
algorithm
matching possibilities
algorithm
outline features
Schomaker, de Leau & Vuurpijl
The following 68 features were derived from the pixels within the
closed object outline:
Schomaker, de Leau & Vuurpijl
Data set: 200 mixed JPEG and GIF photographs of
motor bicycles. Within this set, 750 outlines were drawn around image parts
in the following classes: exhaust, wheels, engine, frame, pedal, fuel tank,
saddle, driver, mirror, license plate, bodyworks, head light, fuel tank lid,
light, rear light, totalling 15 object classes with 50 different
outline samples of each object
Schomaker, de Leau & Vuurpijl
Results are represented
as the average percentage of correct hits in the top-10 hit list (P10),
averaged over n = 50 outline instances per class, of which each was used as
a probe in nearest-neighbour matching. The query itself was excluded from
the matching process.
algorithm
image features
results
data set
results
outline matching & within-outline image matching
Query I. P10 (%)
II. P10 (%)
III. P10 (%)
IV. P10 (%)
([^x],[^y])
(cosf,sinf)
p(f)
image-based
wheels 77.6 81.8 36.0 58.2
exhaust 75.4 79.4 34.0 34.6
engine 57.0 51.4 31.6 49.6
frame 52.0 33.8 38.8 69.4
pedal 47.4 47.2 22.8 33.0
driver 43.6 43.4 20.2 50.2
saddle 41.4 39.2 15.0 20.2
fuel tank 41.4 43.2 23.2 22.8
mirror 40.6 39.8 11.2 22.4
license plate 36.0 47.8 30.2 21.8
bodywork 31.0 26.6 14.4 22.4
head light 30.6 38.2 13.2 30.4
fuel tank lid 29.6 35.8 25.8 23.4
light 21.6 19.4 11.0 27.4
rear light 14.8 14.8 9.0 33.0
Schomaker, de Leau & Vuurpijl
Whereas in general, the outlines outperform pixel-based features
in this experiment, a class-dependent feature selection may yield
reversed results.
Ultimately, one will want to use the set of outlines to perform
object classification in unseen images, for which only the
'bottom-up' edge representation can be computed. Assuming that
scale and translation are already approximately correct, how well can
we match the human-generated outlines with the edges?
algorithm
outline vs edge matching
For each point i on a raw outline
(Xi,Yi), a convolution is calculated as follows. Let DI(x,y) be
an estimate of the absolute and smoothed derivative of the luminance gradient
of an image I(x,y), averaged over a number of suitable directions.
Then the local match between an outline point (X,Y) and the edge
representation of the image can be calculated as:
| (1) |
Schomaker, de Leau & Vuurpijl
results
outline vs edge matching
Schomaker, de Leau & Vuurpijl
Improved outline vs edge matching
The matching results based on outline vs edge matching presented
above can be improved. Assuming that an
class is often presented in a stereotypical background (cow on a
meadow, engine part in shaded metallic textures), it may be
useful to perform class-dependent edge matching. This can
be done using the human-produced outlines as the target for an
MLP edge detector:
generic edge detector (spurious edge pixels!)
class-dependent edge detector (MLP 49x25x9x1)
Note that these results are only preliminary because scale and
translation invariance has not been achieved at all here.
Conclusion
Schomaker, de Leau & Vuurpijl
Schomaker, Vuurpijl & de Leau
(training set: heterogenous set of 100+ motor bicycles, outline$
parts determine the edge target output per 7x7 field)