![]() | Only 14 pages are availabe for public view |
Abstract The main objective of the present thesis is two fold: the development of an automatic system that processes, segments, and classifies the human chromosome images, and the automatic identification of the DNA sequences. The main focus is to investigate how more information can be extracted from the available database using a detailed study of their signal structure in order to utilize them in further stages. In conclusion, it is argued that suggested image and signal processing methodology adopted for automatic feature extraction and classification of the available data provides quantitative information to assist in automatic classification and pairing of human chromosome images, as well as the identification of DNA sequences. It offers opportunity, justification and directions for further development, by other workers seeking the possible automation of the analysis and classification of the genomic data. The work has shown that it is possible to automatically classify the chromosome images as well as the DNA sequences. Although, the number of data sample is not too large, the results obtained suggest that the adopted methodologies of signal analysis and classification has the potential of becoming an effective classification system. |