Image indexing and retrieval in the compressed domain

  • Andrew Armstrong

    Student thesis: Doctoral Thesis

    Abstract

    This thesis is focused on low computational cost algorithms to facilitate the automatic indexing and retrieval of digital images. Several techniques are proposed, which can be classified into three distinct stages of application; In the first stage, a novel approach is proposed to provide a foundation for using genetic algorithms in imaging applications. The approach allows itself to be applied readily to any block based quantisation problem, including that of JPEG DCT domain information.

    The second stage tackles the main problem investigated, that of how to automatically index large numbers of images reliably and provide a mechanism to retrieve those images. Several methods are proposed, which apply various indexing techniques to JPEG images by the extraction of keys directly from the DCT domain. Thus avoiding the computationally costly de-compression stage required when applying pixel based techniques and serves the creation of index keys from partially-decoded data through manipulation of DCT coefficients - to increase speed and improve processing costs. The use of neural and genetic techniques to extract and organise DCT coefficients renders de-compression unnecessary.

    The third stage focuses on image security. Proposed techniques are developed and analysed to allow for the inclusion of watermarking and other data. Using these techniques, a substantial proportion of non-image data can be stored within the image invisibly at little or no extra cost. These allow additional security to be imposed, coupling these with the indexing methods; image tracking and change control can be implemented with very little overhead.

    All the work presented lends itself easily to a number of domains including web databases, general storage, diagnosis and secure image tracking. More importantly, extensive experimentation and analysis prove that the proposed techniques are faster than their counterparts with no loss in the quality of results generated.
    Date of AwardSept 2003
    Original languageEnglish
    SupervisorAndrew Ware (Supervisor), Mike Reddy (Supervisor) & J. Jiang (Supervisor)

    Cite this

    '