Paper Presentation & Seminar Topics: Visual Similarity Based Image Retrieval

Visual Similarity Based Image Retrieval

Image database management and retrieval has been an active research area since the 1970s. With the rapid increase in computer speed and decrease in memory cost, image databases containing thousands or even millions of images are used in many application areas such as medicine, satellite imaging, and biometric databases, where it is important to maintain a high degree of precision. With the growth in the number of images, manual annotation becomes infeasible both time and cost-wise.
Content-based image retrieval (CBIR) is a powerful tool since it searches the image database by utilizing visual cues alone. CBIR systems extract features from the raw images themselves and calculate an association measure (similarity or dissimilarity) between a query image and database images based on these features. CBIR is becoming very popular because of the high demand for searching image databases of ever-growing size. Since speed and precision are important, we need to develop a system for retrieving images that is both efficient and effective.
Recent approaches to represent images require the image to be segmented into a number of regions (a group of connected pixels which share some common properties). This is done with the aim of extracting the objects in the image. However, there is no unsupervised segmentation algorithm that is always capable of partitioning an image into its constituent objects, especially when considering a database containing a collection of heterogeneous images. Therefore, an inaccurate segmentation may result in an inaccurate representation and hence in poor retrieval performance.
Contour-based CBIR technique uses a new approach to describe the shape of a region, inspired by an idea related to the color descriptor in. This new shape descriptor, called Directional Fragment Histogram (DFH), is computed using the outline of the region. One way of improving its efficiency would be to reduce the number of image comparisons done at query time. This can be achieved by using a metric access structure or a filtering technique.
IBM’s QBIC system is the first commercial CBIR system and probably the best known of all CBIR systems. QBIC supports users to retrieval images by color, shape and texture. QBIC provides several query methods: Simple, Multi-feature and Multi-pass. In the simple method, a query is processed using only one feature. A Multi-feature query involves more than one feature and all features have equal weights during the search. A Multi-pass query uses the output of a previous query as the basis for further refinements. Users can draw and specify color and texture color and texture patterns in desired images. In QBIC, the color similarity is computed by quadratic metric using k-element color histograms and the average colors are used as filters to improve query efficiency. Its shape function retrieves images by shape area, circularity, eccentricity and major axis orientation. Its texture function retrieves images by global coarseness, contrast and directionality features.
A wide range of possible applications for CBIR technology are
1. Crime prevention: Law enforcement agencies typically maintain large archives of visual evidence including past suspects facial photographs, fingerprints and shoe prints. Whenever a serious crime is committed, they can compare evidence from the scene of the crime for its similarity to records in their archives.
2. Military: Recognition of enemy aircraft from radar screens, identification of targets from satellite photographs, and provision of guidance systems for cruise missiles are some of the examples in military field.
3. Intellectual property: Trademark image registration, where a new mark is compared with existing marks to ensure that there is no risk of confusion, has long been recognized as a prime application area for CBIR. Copyright protection is also a potentially important application area.
4. Architecture and engineering design: Architectural and engineering design share a number of common features- the use of stylized 2-D and 3-D models to represent design objects, the need to visualize designs for the benefit of non-technical clients and the need to work within externally-imposed constraints, often financial. Such constraints mean that the designer needs to be aware of previous designer needs to aware of previous designs, particularly if these can be adapted to the problem at hand.

5. Fashion and interior design: Similarities can be observed in the design process in other fields, including fashion and interior design. Here again the designer has to work within externally imposed constraints, such as choice of materials. The ability to search a collection of fabrics to find a particular combination of color or texture is increasingly being recognized as a useful aid to the design process.
6. Journalism and advertising: Both newspapers and stock shot agencies maintain archives of still photographs to illustrate articles or advertising copy. These archives can often be extremely large (running into millions of images), and dauntingly expensive to maintain if detailed keyword indexing is provided. Hence CBIR techniques are very useful here.
7. Medical diagnosis: The increasing reliance of modern medicine on diagnostic techniques such as radiology, histopathology, and computerized tomography has resulted in am explosion in the number and importance of medical images now stored by most hospitals. While the prime requirement for medical imaging systems is to be able to display images relating to a named patient, there is increasing interest in the use of CBIR techniques to aid diagnosis by identifying similar past cases.
8. Geographical information and remote sensing systems: Agriculturalists and physical geographers use images (searching by spatial attribute) extensively, both in research and for more practical purposes, such as identifying areas where crops are diseased or lacking in nutrients- or alerting governments to farmers growing crops on land they have paid to leave lying fallow.
9. Education and training: The availability of searchable collections of video clips providing examples of avalanches for a lecture on mountain safety, or traffic congestion for a course on urban planning, could reduce preparation time and lead to improve teaching quality. In some cases such videos might even replace a human tutor.
10. Home entertainment: Much home entertainment is image or video-based, including holiday snapshots, home videos and scenes from favorite TV programmers or films. Possible applications could include management of family photo albums.
Operating Environment
• This model is intended to be used in a software organization or a research environment
• The software will be running on an average personal desktop computer that has a Win95/98/00/NT OS

Hardware Interfaces:
The software will be built using the java application. Hence, the back-end interfacing with the OS (Win family) will not be a concern for the software