Babu M. Mehtre

Shape measures for content based image retrieval: a comparison

Abstract A great deal of work has been done on the evaluation of information retrieval systems for alphanumeric data. The same thing can not be said about the newly emerging multimedia and image database systems. One of the central concerns in these systems is the automatic characterization of image content and retrieval of images based on similarity of image content. In this paper, we discuss effectiveness of several shape measures for content based similarity retrieval of images. The different shape measures we have implemented include outline based features (chain code based string features, Fourier descriptors, UNL Fourier features), region based features (invariant moments, Zernike moments, pseudo-Zernike moments), and combined features (invariant moments & Fourier descriptors, invariant moments & UNL Fourier features). Given an image, all these shape feature measures (vectors) are computed automatically, and the feature vector can either be used for the retrieval purpose or can be stored in the database for future queries. We have tested all of the above shape features for image retrieval on a database of 500 trademark images. The average retrieval efficiency values computed over a set of fifteen representative queries for all the methods is presented. The output of a sample shape similarity query using all the features is also shown.

Color matching for image retrieval

Abstract Color is an important attribute for image matching and retrieval. We present two new color matching methods, the “Reference Color Table Method” and a “Distance Method”, for image retrieval. Both these methods and an existing method “Histogram Intersection” were implemented and tested for a database size of 170 color images. To compare the efficacy of each method, a figure of merit, called “Efficiency of Retrieval”, is defined. The results show that both the new methods perform better than the existing method, and that the Reference Color Table Method gives the best results.

CORE: a content-based retrieval engine for multimedia information systems

Rapid advances in multimedia technology necessitate the development of a generic multimedia information system with a powerful retrieval engine for prototyping multimedia applications. We develop a content-based retrieval engine (CORE) that makes use of novel indexing techniques for multimedia object retrieval. We formalize the concepts related to multimedia information systems such as multimedia objects and content-based retrieval. We bring out the requirements and challenges of a multimedia information system. The architecture of CORE is described in detail along with the associated retrieval mechanisms and indexing techniques. Various modules developed for efficient retrieval are presented with some APIs. The efficacy of CORE is demonstrated in the development of two multimedia systems, a computer-aided facial image inference and retrieval (CAFIIR) system and a system for trademark archival and retrieval (STAR), which have been developed at the Institute of Systems Science (ISS). We expect that CORE will be useful for effective prototyping of other such multimedia applications.

Cluster-based color matching for image retrieval

Abstract Color is an important attribute for image matching and retrieval. We present a new method fo color matching based on a clustering algorithm in 3-D color space. We define a new color feature to characterize the color information and a distance measure to compute the color similarity of images. We have implemented this technique and tested it for a database of approximately 170 images. The test results shoe that the ‘Efficiency of Retrieval’ of this new method is very high.

Content-based image retrieval using a composite color-shape approach

We have proposed a composite feature measure which combines the shape and color features of an image based on a clustering technique. We have also developed a similarity measure to compute the degree of match between a given pair of images. This technique can be used for content-based image retrieval of images using shape and/or color, We have tested our technique on two image databases: one consisting of 100 synthetic images, and another database consisting of 500 actual trademarks images. Test results of the proposed scheme for retrieval of images using only shape, only color, and a weighted combination of the two are presented. The efficiency of retrieval is found to be very high and the experimental results are promising for practical applications

Color and spatial feature for content-based image retrieval

Abstract Most of the currently available image database systems provide a text-based retrieval function called keyword retrieval, where users specify `keywords such as titles, attributes, and categories of themes. But many times it is not easy for users to specify suitable keywords for a particular retrieval. Besides, building a large image database with complete description of contents is a very difficult task. In this paper, we present a content-based retrieval method which obviates the need to describe certain contents of an image to be archived and retrieved. The proposed method computes image features automatically from a given image and they can be used to archive and/or retrieve images. These features are based on color and its spatial distribution information in an image. We have also developed a similarity measure to compare the color and spatial feature similarity of two images. This technique has been developed and tested for content-based similarity retrieval of images on two databases consisting of: (i) 100 test images and (ii) 800 actual trademarks images. The experimental results show a high efficiency of retrieval.

Color indexing for efficient image retrieval

Content based image retrieval is an active area of research. Many approaches have been proposed to retrieve images based on matching of some features derived from the image content. Color is an important feature of image content. The problem with many traditional matching-based retrieval methods is that the search time for retrieving similar images for a given query image increases linearly with the size of the image database. We present an efficient color indexing scheme for similarity-based retrieval which has a search time that increases logarithmically with the database size.In our approach, the color features are extracted automatically using a color clustering algorithm. Then the cluster centroids are used as representatives of the images in 3-dimensional color space and are indexed using a spatial indexing method that usesR-tree. The worst case search time complexity of this approach isOnq log(N* navg)), whereN is the number of images in the database, andnq andnavg are the number of colors in the query image and the average number of colors per image in the database respectively. We present the experimental results for the proposed approach on two databases consisting of 337 Trademark images and 200 Flag images.

Content-Based Retrieval for Trademark Registration

With ever increasing number of registered trademarks, the task of trademark office is becoming increasingly difficult to ensure the uniqueness of all trademarks registered. Trademarks are complex patterns consisting of various image and text patterns, called device-mark and word-in-mark respectively. Due to the diversity and complexity of image patterns occurring in trademarks, due to multi-lingual word-in-mark, there is no very successful computerized operating trademark registration system. We have tackled key technical issues: multiple feature extraction methods to capture the shape, similarity of multi-lingual word-in-mark, matching device mark interpretation using fuzzy thesaurus, and fusion of multiple feature measures for conflict trademark retrieval. A prototype System for Trademark Archival and Registration (STAR) has been developed. The initial test run has been conducted using 3000 trademarks, and the results have shown satisfaction to trademark officers and specialists.

STAR — A multimedia database system for trademark registration

To ensure the uniqueness of all trademarks registered is very important. With ever increasing number of registered trademarks, this is becoming increasingly difficult. A system for search and registration of trademarks is presented in this paper. Trademarks are complex patterns consisting of various image and text patterns, called devicemark and word-in-mark respectively. Traditionally, only text part has been used for search and retrieval of such patterns. This was largely due to the diversity and complexity of image patterns occurring in trademarks. The System for Trademark Archival and Registration (STAR) presented here, uses features based on image as well as text components of trademarks and brings out the conflicting trademarks for the consideration of trademark officer. Thus, it simplifies the task of trademark office to a great extent. A structural representation consisting of image, graphics, text, and phonetics has been proposed to handle the diversity and complexity of trademarks. Based on this structural representation, an object-orieted database schema, a sophisticated segmentation technique, a composite similarity measure for searching conflicting trademarks, and an indexing scheme have been developed. Initial results are very promising. More testing is in progress.