IEE Colloquium on Intelligent Image Databases

We describe recent and on going research into the use of neural associative memories in a molecular database system. The aim of the work is to allow rapid access to a large database of 3D images of molecules using possibly incomplete information provided by the user. Two approaches are being pursued. Both are based upon the use of a class of neural networks known as correlation matrix memories (CM... View full abstract»

Ongoing research into intelligent image databases continues to produce new and innovative techniques for the browsing and retrieval of digital images, but these techniques are generally not applicable to moving image (video) databases. Video sequences, by their very nature, contain a temporal element. This, coupled with the high volume of data needed to represent even small segments of video, make... View full abstract»

Advances in digital storage technology and processing speed have made feasible the creation of large databases with rapid access to individual items stored therein. While many databases still comprise textual and numeric information, an increasing number are genuinely multi-media. A desirable - and attainable - goal of such diverse databases is to retrieve information from them in a manner that is... View full abstract»

In this paper, a temporal object-oriented approach has been explored for data modeling and management in sequential image databases. “The wood panel deformation measurement and analysis database” is taken as a case study for understanding this sort of complex database application. A generalized temporal object-oriented data model has been presented in which the object-oriented modeling... View full abstract»

This paper addresses the difficulties involved in the automatic generation of image content descriptors. These descriptors can be used for the indexing, matching and searching of data in an image database. The current stage of the work has concentrated on the development/collation of a set of feature detectors covering points (corners), lines (edges, ridges) and regions which will operate on a var... View full abstract»

This paper demonstrates a prototype application of content-based database searching, specifically customised for designers in the textile industry. It takes account of their particular needs, enabling them to operate in a visually stimulating manner that does not inhibit their creativity View full abstract»

It is often assumed that colours in an image correlate with intrinsic surface properties (e.g. reflectance). Unfortunately the assumption is unfounded since the image of a scene viewed under two different coloured lights contains two different sets of colours; that is, image colour is a measure of the intrinsic properties of light and surface combined. In our research we aim to provide alternative... View full abstract»

Colour histograms have been shown to be very effective in representing images for content-based retrieval systems. They are compact, robust and amenable to computer analysis. However, such histograms convey only global image properties and do not embody local colour information which is so important when comparing and contrasting images. We present a novel image coding scheme which captures some o... View full abstract»

The paper is based around the research and development of a novel image acquisition and data acquisition database called Visilog which provides a combination of time lapse video photography, high speed photography, and datalogging to allow post evaluation of high speed and low speed processes and events. The system has been designed to take advantage of the availability of large storage media, vid... View full abstract»

In this paper a semi-automatic approach towards efficient and flexible image database population is described. An interactive process aided by computer vision and image processing techniques is employed. Computer aided object selection, using region growing based on colour and texture, allows new labels to be added quickly and efficiently. Extracted features are used to propagate the label through... View full abstract»

Many different approaches have been taken, some focusing on highly specific topics such as improved pattern-matching algorithms, others taking a much broader view, and attempting to study the issues involved by developing and evaluating prototype systems. Work on image retrieval at Northumbria University falls mainly into this second category. Our long-term aim is to investigate the principles on ... View full abstract»

We introduce a very fast and reliable algorithm for shape similarity retrieval in large image databases which is robust with respect to noise, scale and orientation changes of the objects. The curvature scale space image is used to represent the shapes of object boundary contours. Since the algorithm uses the global information of boundaries of objects, it is sensitive to major occlusion, but some... View full abstract»

This paper describes the first stages of work aimed at developing a hierarchical framework for shape indexing in line images. The envisaged hierarchy is two-level. At the top-level of representation we construct a histogram of pairwise geometric attributes for line-structures extracted from the image. The lower level of the hierarchy is a constrained Delaunay graph which conveys detailed relationa... View full abstract»

A new method of applying n-tuple recognition techniques to searching document images is reported. The method involves scanning an n-tuple classifier over a chain-code of the image. In scanning n-tuple systems, the traditional advantages of n-tuple recognition, i.e. training and recognition speed are retained, while offering superior recognition accuracy. In this paper the application of the system... View full abstract»

Electronic images are rapidly replacing conventional paper documents due to their handling advantages. As a result, there is a need for retrieval techniques where the level of man-machine interaction is closer to that enjoyed amongst the humans. This paper describes the work carried out to date in design and development of a descriptive retrieval engine. In such a system users may retrieve documen... View full abstract»