Object and Concept Recognition for Content-Based Image Retrieval (CBIR)
University of Washington

groundtruth (1365 files)
annotation.txt 64.44kB
arborgreens/descriptions 1.69kB
arborgreens/Image01.jpg 409.93kB
arborgreens/Image02.jpg 383.66kB
arborgreens/Image03.jpg 516.77kB
arborgreens/Image04.jpg 418.55kB
arborgreens/Image05.jpg 456.97kB
arborgreens/Image06.jpg 495.21kB
arborgreens/Image07.jpg 464.83kB
arborgreens/Image08.jpg 426.51kB
arborgreens/Image09.jpg 506.24kB
arborgreens/Image10.jpg 372.52kB
arborgreens/Image11.jpg 395.51kB
arborgreens/Image12.jpg 408.51kB
arborgreens/Image13.jpg 359.94kB
arborgreens/Image14.jpg 361.26kB
arborgreens/Image15.jpg 368.86kB
arborgreens/Image16.jpg 255.37kB
arborgreens/Image17.jpg 273.34kB
arborgreens/Image18.jpg 361.12kB
arborgreens/Image19.jpg 371.73kB
arborgreens/Image20.jpg 310.63kB
arborgreens/Image21.jpg 357.31kB
arborgreens/Image22.jpg 356.08kB
arborgreens/Image23.jpg 470.93kB
arborgreens/Image24.jpg 297.90kB
arborgreens/Image25.jpg 139.78kB
arborgreens/Image26.jpg 324.92kB
arborgreens/Image27.jpg 376.82kB
arborgreens/Image28.jpg 390.73kB
arborgreens/Image29.jpg 369.48kB
arborgreens/Image30.jpg 418.81kB
arborgreens/Image31.jpg 415.19kB
arborgreens/Image32.jpg 460.62kB
arborgreens/Image33.jpg 391.83kB
arborgreens/Image34.jpg 401.60kB
arborgreens/Image35.jpg 342.25kB
arborgreens/Image36.jpg 442.64kB
arborgreens/Image37.jpg 383.88kB
arborgreens/Image38.jpg 404.09kB
arborgreens/Image39.jpg 415.83kB
arborgreens/Image40.jpg 401.27kB
arborgreens/Image41.jpg 383.54kB
arborgreens/Image42.jpg 272.12kB
arborgreens/Image43.jpg 333.40kB
arborgreens/Image44.jpg 310.21kB
arborgreens/Image45.jpg 402.79kB
arborgreens/Image46.jpg 335.23kB
arborgreens/Image47.jpg 296.83kB
arborgreens/Thumbs.db 7.68kB
australia/description.txt 1.12kB
australia/Image01.jpg 72.70kB
australia/Image02.jpg 103.91kB
australia/Image03.jpg 45.75kB
australia/Image04.jpg 54.36kB
australia/Image05.jpg 120.00kB
australia/Image06.jpg 97.02kB
australia/Image07.jpg 57.87kB
australia/Image08.jpg 138.61kB
australia/Image09.jpg 59.32kB
australia/Image10.jpg 92.39kB
australia/Image11.jpg 97.09kB
australia/Image12.jpg 89.11kB
australia/Image13.jpg 64.70kB
australia/Image14.jpg 89.78kB
australia/Image15.jpg 116.86kB
australia/Image16.jpg 89.53kB
australia/Image17.jpg 202.28kB
australia/Image18.jpg 73.45kB
australia/Image19.jpg 93.86kB
australia/Image20.jpg 52.38kB
australia/Image21.jpg 94.85kB
australia/Image22.jpg 81.19kB
australia/Image23.jpg 64.01kB
australia/Image24.jpg 42.67kB
australia/Image25.jpg 44.96kB
australia/Image26.jpg 54.13kB
australia/Image27.jpg 88.96kB
australia/Image28.jpg 56.61kB
australia/Image29.jpg 100.66kB
australia/Image30.jpg 62.40kB
barcelona/Image01.jpg 275.19kB
barcelona/Image02.jpg 239.42kB
barcelona/Image03.jpg 374.12kB
barcelona/Image04.jpg 313.86kB
barcelona/Image05.jpg 286.26kB
barcelona/Image06.jpg 367.03kB
barcelona/Image07.jpg 330.47kB
barcelona/Image08.jpg 396.89kB
barcelona/Image09.jpg 366.37kB
barcelona/Image10.jpg 357.58kB
barcelona/Image11.jpg 287.52kB
barcelona/Image12.jpg 413.10kB
barcelona/Image13.jpg 376.00kB
barcelona/Image14.jpg 288.80kB
barcelona/Image15.jpg 302.53kB
barcelona/Image16.jpg 339.33kB
barcelona/Image17.jpg 359.21kB
barcelona/Image18.jpg 335.59kB
barcelona/Image19.jpg 255.35kB
barcelona/Image20.jpg 327.53kB
barcelona/Image21.jpg 303.80kB
barcelona/Image22.jpg 280.39kB
barcelona/Image23.jpg 316.16kB
barcelona/Image24.jpg 260.75kB
barcelona/Image25.jpg 320.97kB
barcelona/Image26.jpg 323.23kB
barcelona/Image27.jpg 350.76kB
barcelona/Image28.jpg 379.77kB
barcelona/Image29.jpg 279.84kB
barcelona/Image30.jpg 285.40kB
barcelona/Image31.jpg 243.18kB
barcelona/Image32.jpg 283.76kB
barcelona/Image33.jpg 279.47kB
barcelona/Image34.jpg 255.64kB
barcelona/Image35.jpg 351.88kB
barcelona/Image36.jpg 223.09kB
barcelona/Image37.jpg 220.95kB
barcelona/Image38.jpg 216.68kB
barcelona/Image39.jpg 314.42kB
barcelona/Image40.jpg 223.19kB
barcelona/Image41.jpg 198.45kB
barcelona/Image42.jpg 199.25kB
barcelona/Image43.jpg 210.03kB
barcelona/Image44.jpg 198.89kB
barcelona/Image45.jpg 203.66kB
barcelona/Image46.jpg 215.41kB
barcelona/Image47.jpg 195.70kB
barcelona/Image48.jpg 228.12kB
barcelona/Thumbs.db 161.79kB
barcelona2/barcelona2_001.gif 599.95kB
barcelona2/barcelona2_002.gif 599.93kB
barcelona2/barcelona2_003.gif 464.98kB
barcelona2/barcelona2_004.gif 423.97kB
barcelona2/barcelona2_005.gif 599.93kB
barcelona2/barcelona2_006.gif 599.93kB
barcelona2/barcelona2_007.gif 392.92kB
barcelona2/barcelona2_008.gif 599.93kB
barcelona2/barcelona2_009.gif 599.93kB
barcelona2/barcelona2_010.gif 599.93kB
barcelona2/barcelona2_011.gif 599.93kB
barcelona2/barcelona2_012.gif 599.93kB
barcelona2/barcelona2_013.gif 449.08kB
barcelona2/barcelona2_014.gif 599.93kB
barcelona2/barcelona2_015.gif 430.99kB
barcelona2/barcelona2_016.gif 599.93kB
barcelona2/barcelona2_017.gif 599.93kB
barcelona2/barcelona2_018.gif 599.93kB
barcelona2/barcelona2_019.gif 340.62kB
barcelona2/barcelona2_020.gif 476.04kB
barcelona2/barcelona2_021.gif 599.93kB
barcelona2/barcelona2_022.gif 432.64kB
barcelona2/barcelona2_023.gif 430.59kB
barcelona2/barcelona2_024.gif 599.93kB
barcelona2/barcelona2_025.gif 599.93kB
barcelona2/barcelona2_026.gif 599.93kB
barcelona2/barcelona2_027.gif 421.43kB
barcelona2/barcelona2_028.gif 599.93kB
barcelona2/barcelona2_029.gif 599.93kB
barcelona2/barcelona2_030.gif 599.93kB
barcelona2/barcelona2_031.gif 595.89kB
barcelona2/barcelona2_032.gif 595.89kB
barcelona2/barcelona2_033.gif 595.89kB
barcelona2/barcelona2_034.gif 376.46kB
barcelona2/barcelona2_035.gif 595.89kB
barcelona2/barcelona2_036.gif 371.95kB
barcelona2/barcelona2_037.gif 371.58kB
barcelona2/barcelona2_038.gif 374.97kB
barcelona2/barcelona2_039.gif 387.83kB
barcelona2/barcelona2_040.gif 359.90kB
barcelona2/barcelona2_041.gif 418.41kB
barcelona2/barcelona2_042.gif 595.89kB
barcelona2/barcelona2_043.gif 595.89kB
barcelona2/barcelona2_044.gif 595.89kB
barcelona2/barcelona2_045.gif 595.89kB
barcelona2/barcelona2_046.gif 595.89kB
barcelona2/barcelona2_047.gif 352.10kB
barcelona2/barcelona2_048.gif 595.89kB
barcelona2/barcelona2_049.gif 595.89kB
barcelona2/barcelona2_050.gif 595.89kB
barcelona2/barcelona2_051.gif 595.89kB
barcelona2/barcelona2_052.gif 259.75kB
barcelona2/barcelona2_053.gif 595.89kB
barcelona2/barcelona2_054.gif 595.89kB
barcelona2/barcelona2_055.gif 595.89kB
barcelona2/barcelona2_056.gif 595.89kB
barcelona2/barcelona2_057.gif 595.89kB
barcelona2/barcelona2_058.gif 595.89kB
barcelona2/barcelona2_059.gif 595.89kB
barcelona2/barcelona2_060.gif 595.89kB
barcelona2/barcelona2_061.gif 595.89kB
barcelona2/barcelona2_062.gif 595.89kB
barcelona2/barcelona2_063.gif 595.89kB
barcelona2/barcelona2_064.gif 595.89kB
barcelona2/barcelona2_065.gif 595.89kB
barcelona2/barcelona2_066.gif 595.89kB
barcelona2/barcelona2_067.gif 451.21kB
barcelona2/barcelona2_068.gif 595.89kB
barcelona2/barcelona2_069.gif 489.61kB
Too many files! Click here to view them all.
Type: Dataset
Tags:

Bibtex:
@article{,
title = {Object and Concept Recognition for Content-Based Image Retrieval (CBIR)},
journal = {},
author = {University of Washington },
year = {},
url = {http://www.cs.washington.edu/research/imagedatabase/},
abstract = {Our groundtruth database consists of 21 datasets of outdoor scene images, many including a text file containing a list of visible objects for each image.

Project Summary

With the advent of powerful but inexpensive computers and storage devices and with the availability of the World Wide Web, image databases have moved from research to reality. Search engines for finding images are available from commercial concerns and from research institutes. These search engines can retrieve images by keywords or by image content such as color, texture, and simple shape properties. Content-based image retrieval is not yet a commercial success, because most real users searching for images want to specify the semantic class of the scene or the object(s) it should contain. The large commercial image providers are still using human indexers to select keywords for their images, even though their databases contain thousands or, in some cases, millions of images. Automatic object recognition is needed, but most successful computer vision object recognition systems can only handle particular objects, such as industrial parts, that can be represented by precise geometric models. Content-based retrieval requires the recognition of generic classes of objects and concepts. A limited amount of work has been done in this respect, but no general methodology has yet emerged.
The goal of this research is to develop the necessary methodology for automated recognition of generic object and concept classes in digital images. The work will build on existing object-recognition techniques in computer vision for low-level feature extraction and will design higher-level relationship and cluster features and a new unified recognition methodology to handle the difficult problem of recognizing classes of objects, instead of particular instances. Local feature representations and global summaries that can be used by general-purpose classifiers will be developed. A powerful new hierarchical multiple classifier methodology will provide the learning mechanism for automating the development of recognizers for additional objects and concepts. The resulting techniques will be evaluated on several different large image databases, including commercial databases whose images are grouped into broad classes and a ground-truth database that provides a list of the objects in each image. The results of this work will be a new generic object recognition paradigm that can immediately be applied to automated or semi-automated indexing of large image databases and will be a step forward in object recognition.

Project Impact

The results of this project will have an impact on both image retrieval from large databases and object recognition in general. It will target the recognition of classes of common objects that can appear in image databases of outdoor scenes. It will develop object class recognizers and a new learning formalism for automating the production of new classifiers for new classes of objects. It will also develop new representations for the image features that can be used to recognize these objects. It will allow content-based retrieval to become an important method for accessing real, commercial image databases, which today use only human index terms for retrieval.
Goals, Objectives and Targeted Activities

In the first year of the grant, we developed the feature extraction routines to extract features capable of recognizing an initial set of common objects representing a variety of the types of objects that appear in outdoor scenes, including city scenes and noncity scenes. We designed generic object recognition algorithms for the initial object set. We have developed such algorithms for vehicles, boats, and buildings, and have designed new high-level image features including symmetry features and cluster features. In the second year, We designed a unified representation for the image features called abstract regions. These are regions of the image that can come about from many different processes: color clustering, texture clustering, line-segment clustering, symmetry detection, and so on. All abstract regions will have a common set of features, while each different category will have its own special features. Our current emphasis is on using abstract features along with learning methodologies to recognize comon objects.
Area Background

The area of content-based image retrieval is a hybrid research area that requires knowledge of both computer vision and of database systems. Large image databases are being collected, and images from these collections made available to users in advertising, marketing, entertainment, and other areas where images can be used to enhance the product. These images are generally organized loosely by category, such as animals, natural scenes, people, and so on. All image indexing is done by human indexers who list the important objects in an image and other terms by which users may wish to access it. This method is not suitable for today's very large image databases.
Content-based retrieval systems utilize measures that are based on low-level attributes of the image itself, including color histograms, color composition, and texture. State-of-the-art research focuses on more powerful measures that can find regions of an image corresponding to known objects that users wish to retrieve. There has been some success in finding human faces of different selected sizes, human bodies, horses, zebras and other texture animals with known patterns, and such backgrounds as jungles, water, and sky. Our research will focus on a unified methodology for feature representation and object class recognition. This work will lead to automatic indexing capabilities in the future.}
}


Support
Academic Torrents!

Disable your
ad-blocker!

Report