Content-based image retrieval

Content-based image retrieval (CBIR), also known as query by image content (QBIC) and content-based visual information retrieval (CBVIR) is the application of computer vision techniques to the image retrieval problem, that is, the problem of searching for digital images in large databases. (see this survey^[1] for a recent scientific overview of the CBIR field). Content based image retrieval is opposed to concept based approaches (see concept based image indexing).

"Content-based" means that the search will analyze the actual contents of the image rather than the metadata such as keywords, tags, and/or descriptions associated with the image. The term 'content' in this context might refer to colors, shapes, textures, or any other information that can be derived from the image itself. CBIR is desirable because most web based image search engines rely purely on metadata and this produces a lot of garbage in the results. Also having humans manually enter keywords for images in a large database can be inefficient, expensive and may not capture every keyword that describes the image. Thus a system that can filter images based on their content would provide better indexing and return more accurate results.

History

The term Content-Based Image Retrieval (CBIR) seems to have originated in 1992, when it was used by T. Kato to describe experiments into automatic retrieval of images from a database, based on the colors and shapes present.^[2] Since then, the term has been used to describe the process of retrieving desired images from a large collection on the basis of syntactical image features. The techniques, tools and algorithms that are used originate from fields such as statistics, pattern recognition, signal processing, and computer vision.

Technical progress

There is a growing interest in CBIR because of the limitations inherent in metadata-based systems, as well as the large range of possible uses for efficient image retrieval. Textual information about images can be easily searched using existing technology, but requires humans to personally describe every image in the database. This is impractical for very large databases, or for images that are generated automatically, e.g. from surveillance cameras. It is also possible to miss images that use different synonyms in their descriptions. Systems based on categorizing images in semantic classes like "cat" as a subclass of "animal" avoid this problem but still face the same scaling issues.

Potential uses for CBIR include:

• Art collections
• Photograph archives
• Retail catalogs
• Medical diagnosis
• Crime prevention
• The military
• Intellectual property
• Architectural and engineering design
• Geographical information and remote sensing systems

CBIR software systems

• University of Washington FIDS Demo^[3]
• CIRES: Content Based Image Retrieval System^[4]
• Impezzeo Image Suite Visual Search http://www.imprezzeo.com
• LTU-Corbis Visual Search^[5]
• TinEye^[6]
• Cortina ^[7]
• Octagon^[8]
• Windsurf^[9]
• Visual recognition factory ^[10]

See CBIR engines for other examples of publicly available and accessible CBIR systems.

CBIR techniques

Many CBIR systems have been developed, but the problem of retrieving images on the basis of their pixel content remains largely unsolved.

Query techniques

            Different implementations of CBIR make use of different types of user queries.

Query by example is a query technique that involves providing the CBIR system with an example image that it will then base its search upon. The underlying search algorithms may vary depending on the application, but result images should all share common elements with the provided example.

Options for providing example images to the system include:

• A preexisting image may be supplied by the user or chosen from a random set.
• The user draws a rough approximation of the image they are looking for, for example with blobs of color or general shapes.^[11]

This query technique removes the difficulties that can arise when trying to describe images with words.

Semantic retrieval

The ideal CBIR system from a user perspective would involve what is referred to as semantic retrieval, where the user makes a request like "find pictures of dogs" or even "find pictures of Abraham Lincoln". This type of open-ended task is very difficult for computers to perform - pictures of chihuahuas and Great Danes look very different, and Lincoln may not always be facing the camera or in the same pose. Current CBIR systems therefore generally make use of lower-level features like texture, color, and shape, although some systems take advantage of very common higher-level features like faces (see facial recognition system). Not every CBIR system is generic. Some systems are designed for a specific domain, e.g. shape matching can be used for finding parts inside a CAD-CAM database.

Other query methods

Other query methods include browsing for example images, navigating customized/hierarchical categories, querying by image region (rather than the entire image), querying by multiple example images, querying by visual sketch, querying by direct specification of image features, and multimodal queries (e.g. combining touch, voice, etc.) [1].

CBIR systems can also make use of relevance feedback, where the user progressively refines the search results by marking images in the results as "relevant", "not relevant", or "neutral" to the search query, then repeating the search with the new information.

Content comparison using image distance measures

The most common method for comparing two images in content based image retrieval (typically an example image and an image from the database) is using an image distance measure. An image distance measure compares the similarity of two images in various dimensions such as color, texture, shape, and others. For example a distance of 0 signifies an exact match with the query, with respect to the dimensions that were considered. As one may intuitively gather, a value greater than 0 indicates various degrees of similarities between the images. Search results then can be sorted based on their distance to the queried image.^[11] A long list of distance measures can be found in ^[12].

Color

Computing distance measures based on color similarity is achieved by computing a color histogram for each image that identifies the proportion of pixels within an image holding specific values (that humans express as colors). Current research is attempting to segment color proportion by region and by spatial relationship among several color regions. Examining images based on the colors they contain is one of the most widely used techniques because it does not depend on image size or orientation. Color searches will usually involve comparing color histograms, though this is not the only technique in practice.

Texture

Texture measures look for visual patterns in images and how they are spatially defined. Textures are represented by texels which are then placed into a number of sets, depending on how many textures are detected in the image. These sets not only define the texture, but also where in the image the texture is located.

Texture is a difficult concept to represent. The identification of specific textures in an image is achieved primarily by modeling texture as a two-dimensional gray level variation. The relative brightness of pairs of pixels is computed such that degree of contrast, regularity, coarseness and directionality may be estimated (Tamura, Mori & Yamawaki, 1978). However, the problem is in identifying patterns of co-pixel variation and associating them with particular classes of textures such as silky, or rough.

Shape

Shape does not refer to the shape of an image but to the shape of a particular region that is being sought out. Shapes will often be determined first applying segmentation or edge detection to an image. Other methods like [Tushabe and Wilkinson 2008] use shape filters to identify given shapes of an image. In some case accurate shape detection will require human intervention because methods like segmentation are very difficult to completely automate.

Applications

Some software producers are trying to push CBIR based applications into the filtering and law enforcement markets for the purpose of identifying and censoring images with skin-tones and shapes that could indicate the presence of nudity, with controversial results.

See also

• Document classification
• Image retrieval
• Nearest neighbor search
• GazoPa
• Multimedia Information Retrieval

Relevant research papers

• Query by Image and Video Content: The QBIC System, (Flickner, 1995)

• Finding Naked People (Fleck et al., 1996)

• Virage Video Engine, (Hampapur, 1997)

• Library-based Coding: a Representation for Efficient Video Compression and Retrieval, (Vasconcelos & Lippman, 1997)

• System for Screening Objectionable Images (Wang et al., 1998)

• Content-based Image Retrieval (JISC Technology Applications Programme Report 39) (Eakins & Graham 1999)

• Windsurf: Region-Based Image Retrieval Using Wavelets (Ardizzoni, Bartolini, and Patella, 1999)

• A Probabilistic Architecture for Content-based Image Retrieval, (Vasconcelos & Lippman, 2000)

• A Unifying View of Image Similarity, (Vasconcelos & Lippman, 2000)

• Next Generation Web Searches for Visual Content, (Lew, 2000)

• Image Indexing with Mixture Hierarchies, (Vasconcelos, 2001)

• SIMPLIcity: Semantics-Sensitive Integrated Matching for Picture Libraries (Wang, Li, and Wiederhold, 2001)

• A Conceptual Approach to Web Image Retrieval (Popescu and Grefenstette, 2008)

• FACERET: An Interactive Face Retrieval System Based on Self-Organizing Maps (Ruiz-del-Solar et al., 2002)

• Automatic Linguistic Indexing of Pictures by a Statistical Modeling Approach (Li and Wang, 2003)

• Video google: A text retrieval approach to object matching in videos (Sivic & Zisserman, 2003)

• Minimum Probability of Error Image Retrieval (Vasconcelos, 2004)

• On the Efficient Evaluation of Probabilistic Similarity Functions for Image Retrieval (Vasconcelos, 2004)

• Extending image retrieval systems with a thesaurus for shapes (Hove, 2004)

• Names and Faces in the News (Berg et al., 2004)

• Cortina: a system for large-scale, content-based web image retrieval (Quack et al., 2004)

• A new perspective on Visual Information Retrieval (Eidenberger 2004)

• Language-based Querying of Image Collections on the basis of an Extensible Ontology (Town and Sinclair, 2004)

• Costume: A New Feature for Automatic Video Content Indexing (Jaffre 2005)

• Automatic Face Recognition for Film Character Retrieval in Feature-Length Films (Arandjelovic & Zisserman, 2005)

• Content-based Multimedia Information Retrieval: State of the Art and Challenges (Lew et al. 2006)

• Algorithm on which Retrievr (Flickr search) and imgSeek is based on (Jacobs, Finkelstein, Salesin)

• Evaluating Use of Interfaces for Visual Query Specification. (Hove, 2007)

• From Pixels to Semantic Spaces: Advances in Content-Based Image Retrieval (Vasconcelos, 2007)

• Content-based Image Retrieval by Indexing Random Subwindows with Randomized Trees (Maree et al., 2007)

• Image Retrieval: Ideas, Influences, and Trends of the New Age (Datta et al., 2008)

• Real-Time Computerized Annotation of Pictures (Li and Wang, 2008)

• Query Processing Issues in Region-based Image Databases (Bartolini, Ciaccia, and Patella, 2010)

• The Windsurf Library for the Efficient Retrieval of Multimedia Hierarchical Data (Bartolini, Patella, and Stromei, 2011)

References

1. ^ Content-based Multimedia Information Retrieval: State of the Art and Challenges, Michael Lew, et al., ACM Transactions on Multimedia Computing, Communications, and Applications, pp. 1-19, 2006.
2. ^ Content-based Image Retrieval, John Eakins and Margaret Graham, University of Northumbria at Newcastle
3. ^ University of Washington FIDS Demo
4. ^ CIRES: Content Based Image Retrieval System
5. ^ LTU Technologies Corbis Visual Search
6. ^ Idée Inc. TinEye Reverse Image Search Engine.
7. ^ Vision Research Lab, UCSB
8. ^ Octagon by Viitala
9. ^ Windsurf (University of Bologna, Italy)
10. ^ Visual recognition factory
11. ^ ^{a b} Shapiro, Linda; George Stockman (2001). Computer Vision. Upper Saddle River, NJ: Prentice Hall. ISBN 0-13-030796-3. 
12. ^ Eidenberger, Horst (2011). “Fundamental Media Understanding”, atpress. ISBN 978-3842379176.

Bibliography

• Bird, C.L.; P.J. Elliott, Griffiths (1996). User interfaces for content-based image retrieval. 
• Rui, Yong; Thomas S. Huang, Shih-Fu Chang (1999). Image Retrieval: Current Techniques, Promising Directions, and Open Issues. 
• Datta, Ritendra; Dhiraj Joshi, Jia Li, James Z. Wang (2008). "Image Retrieval: Ideas, Influences, and Trends of the New Age". ACM Computing Surveys 40 (2): 1–60. doi:10.1145/1348246.1348248. http://infolab.stanford.edu/~wangz/project/imsearch/review/JOUR/. 
• Tushabe, F.; M.H.F. Wilkinson (2008). "Content-based Image Retrieval Using Combined 2D Attribute Pattern Spectra". Springer Lecture Notes in Computer Science. 

External links

• cbir.info CBIR-related articles
• Search by Drawing