The development of a human-centered object based image retrieval engine

Eva M. van Rikxoort; B.J.A. Kröse; Egon van den Broek; H.J. Bos; E.A. Hendriks; Theo E. Schouten; J.W.J. Heijnsdijk

The development of a human-centered object based image retrieval engine

Eva M. van Rikxoort, B.J.A. Kröse (Editor), Egon van den Broek, H.J. Bos (Editor), E.A. Hendriks (Editor), Theo E. Schouten, J.W.J. Heijnsdijk (Editor)

Research output: Contribution to conference › Paper

41 Downloads (Pure)

Abstract

The development of a new object-based image retrieval (OBIR) engine is discussed. Its goal was to yield intuitive results for users by using human-based techniques. The engine utilizes a unique and efficient set of 15 features: 11 color categories and 4 texture features, derived from the color correlogram. These features were calculated for the center object of the images, which was determined by agglomerative merging. Subsequently, OBIR was applied, using the color and texture features of the center objects on the images. The final OBIR engine, as well as all intermediate versions, were evaluated in a CBIR benchmark, consisting of the engine, the Corel image database, and an interface module. The texture features proved to be useful in combination with the 11 color categories. In general, the engine proved to be fast and yields intuitive results for users.

Original language	Undefined
Pages	401-408
Number of pages	8
Publication status	Published - 8 Jun 2005
Event	Eleventh Annual Conference of the Advanced School for Computing and Imaging, ASCI 2005: Proceedings of the 11th ASCI 2005 conference - Heijen, The Netherlands Duration: 8 Jun 2005 → 10 Jun 2005

Conference

Conference	Eleventh Annual Conference of the Advanced School for Computing and Imaging, ASCI 2005
Period	8/06/05 → 10/06/05
Other	8-10 June 2005

Keywords

object-based
color correlogram
human perception
EWI-21122
Image segmentation
IR-79155
Content-Based Image Retrieval (CBIR)
11 color categories
HMI-MR: MULTIMEDIA RETRIEVAL

Access to Document

Cite this

@conference{cdb0c6ee591146f7b51f849bd88c47a4,

title = "The development of a human-centered object based image retrieval engine",

abstract = "The development of a new object-based image retrieval (OBIR) engine is discussed. Its goal was to yield intuitive results for users by using human-based techniques. The engine utilizes a unique and efficient set of 15 features: 11 color categories and 4 texture features, derived from the color correlogram. These features were calculated for the center object of the images, which was determined by agglomerative merging. Subsequently, OBIR was applied, using the color and texture features of the center objects on the images. The final OBIR engine, as well as all intermediate versions, were evaluated in a CBIR benchmark, consisting of the engine, the Corel image database, and an interface module. The texture features proved to be useful in combination with the 11 color categories. In general, the engine proved to be fast and yields intuitive results for users.",

keywords = "object-based, color correlogram, human perception, EWI-21122, Image segmentation, IR-79155, Content-Based Image Retrieval (CBIR), 11 color categories, HMI-MR: MULTIMEDIA RETRIEVAL",

author = "{van Rikxoort}, {Eva M.} and B.J.A. Kr{\"o}se and {van den Broek}, Egon and H.J. Bos and E.A. Hendriks and Schouten, {Theo E.} and J.W.J. Heijnsdijk",

year = "2005",

month = jun,

day = "8",

language = "Undefined",

pages = "401--408",

note = "Eleventh Annual Conference of the Advanced School for Computing and Imaging, ASCI 2005 ; Conference date: 08-06-2005 Through 10-06-2005",

}

TY - CONF

T1 - The development of a human-centered object based image retrieval engine

AU - van Rikxoort, Eva M.

AU - van den Broek, Egon

AU - Schouten, Theo E.

A2 - Kröse, B.J.A.

A2 - Bos, H.J.

A2 - Hendriks, E.A.

A2 - Heijnsdijk, J.W.J.

PY - 2005/6/8

Y1 - 2005/6/8

N2 - The development of a new object-based image retrieval (OBIR) engine is discussed. Its goal was to yield intuitive results for users by using human-based techniques. The engine utilizes a unique and efficient set of 15 features: 11 color categories and 4 texture features, derived from the color correlogram. These features were calculated for the center object of the images, which was determined by agglomerative merging. Subsequently, OBIR was applied, using the color and texture features of the center objects on the images. The final OBIR engine, as well as all intermediate versions, were evaluated in a CBIR benchmark, consisting of the engine, the Corel image database, and an interface module. The texture features proved to be useful in combination with the 11 color categories. In general, the engine proved to be fast and yields intuitive results for users.

AB - The development of a new object-based image retrieval (OBIR) engine is discussed. Its goal was to yield intuitive results for users by using human-based techniques. The engine utilizes a unique and efficient set of 15 features: 11 color categories and 4 texture features, derived from the color correlogram. These features were calculated for the center object of the images, which was determined by agglomerative merging. Subsequently, OBIR was applied, using the color and texture features of the center objects on the images. The final OBIR engine, as well as all intermediate versions, were evaluated in a CBIR benchmark, consisting of the engine, the Corel image database, and an interface module. The texture features proved to be useful in combination with the 11 color categories. In general, the engine proved to be fast and yields intuitive results for users.

KW - object-based

KW - color correlogram

KW - human perception

KW - EWI-21122

KW - Image segmentation

KW - IR-79155

KW - Content-Based Image Retrieval (CBIR)

KW - 11 color categories

KW - HMI-MR: MULTIMEDIA RETRIEVAL

M3 - Paper

SP - 401

EP - 408

T2 - Eleventh Annual Conference of the Advanced School for Computing and Imaging, ASCI 2005

Y2 - 8 June 2005 through 10 June 2005

ER -