Document Image Segmentation and Compression using Artificial Neural Networks and Evolutionary Methods

The work is intended to study the following important aspects of document image processing and develop new methods. (1) Segmentation ofdocument images using adaptive interval valued neuro-fuzzy method. (2) Improving the segmentation procedure using Simulated Annealing technique. (3) Development of optimized compression algorithms using Genetic Algorithm and parallel Genetic Algorithm (4) Feature extraction of document images (5) Development of IV fuzzy rules. This work also helps for feature extraction and foreground and background identification. The proposed work incorporates Evolutionary and hybrid methods for segmentation and compression of document images. A study of different neural networks used in image processing, the study of developments in the area of fuzzy logic etc is carried out in this work

“Improved Feature Extraction and Classification Techniques for Multispectral Brain Magnetic Resonance Images”

Magnetic Resonance Imaging (MRI) is a multi sequence medical imaging technique in which stacks of images are acquired with different tissue contrasts. Simultaneous observation and quantitative analysis of normal brain tissues and small abnormalities from these large numbers of different sequences is a great challenge in clinical applications. Multispectral MRI analysis can simplify the job considerably by combining unlimited number of available co-registered sequences in a single suite. However, poor performance of the multispectral system with conventional image classification and segmentation methods makes it inappropriate for clinical analysis. Recent works in multispectral brain MRI analysis attempted to resolve this issue by improved feature extraction approaches, such as transform based methods, fuzzy approaches, algebraic techniques and so forth. Transform based feature extraction methods like Independent Component Analysis (ICA) and its extensions have been effectively used in recent studies to improve the performance of multispectral brain MRI analysis. However, these global transforms were found to be inefficient and inconsistent in identifying less frequently occurred features like small lesions, from large amount of MR data. The present thesis focuses on the improvement in ICA based feature extraction techniques to enhance the performance of multispectral brain MRI analysis. Methods using spectral clustering and wavelet transforms are proposed to resolve the inefficiency of ICA in identifying small abnormalities, and problems due to ICA over-completeness. Effectiveness of the new methods in brain tissue classification and segmentation is confirmed by a detailed quantitative and qualitative analysis with synthetic and clinical, normal and abnormal, data. In comparison to conventional classification techniques, proposed algorithms provide better performance in classification of normal brain tissues and significant small abnormalities.

Crystal Structures and Spectral Aspects of Mixed Ligand Transition Metal Chelates Derived from Aldehyde based ONS Donor Thiosemicarbazones

Thiosemicarbazones have emerged as an important class of ligands over a period of time, for a variety of reasons, such as variable donor properties, structural diversity and biological applications. Interesting as the coordination chemistry may be, the driving force for the study of these ligands has undoubtedly been their biological properties and the majority of the 3000 or so publications on thiosemicarbazones since 2000 have alluded to this feature. Thiosemicarbazones with potential donor atoms in their structural skeleton fascinate coordination chemists with their versatile chelating behavior. The thiosemicarbazones of aromatic aldehydes and ketones form stable chelates with transition metal cations by utilizing both their sulfur and azomethine nitrogen as donor atoms. They have been shown to possess a diverse range of biological activities including anticancer, antitumor, antibacterial, antiviral, antimalarial and antifungal properties owing to their ability to diffuse through the semipermeable membrane of the cell lines. The enhanced effect may be attributed to the increased lipophilicity of the metal complexes compared to the ligand alone.

Mono- and binuclear transition metal complexes of n(4)-substituted thiosel\licarbazones derived frol\i salicylaldehyde and 2-hydroxyacetophenone synthesis, spectral and structural studies

The work embodied in the thesis is divided into eight chapters. Chapter I gives a brief introduction about metal complexes of thiosemicarbazones, including their structural and bonding properties. Chapter 2 deals with the synthesis and single crystal X-ray diffraction studies of various thiosemicarbazones used up for the present investigations and various characterization techniques. Chapter 3 deals with synthesis, spectral and structural studies of Cu(U) complexes with ONS donor thiosemicarbazones. Chapter 4 deals with synthesis and spectral studies of Ni(II) complexes \vith 2-hydroxyacetophenone N(4)-cyclohexyl thiosemicarbazone as the ligand. Chapter 5 includes synthesis and spectral studies of Mn(II) complexes. Chapter 6 deals with synthesis, spectral and structural studies of Zn(II) complexes. Chapter 7 includes synthesis and spectral studies of oxovanadium(IV) complexes. Chapter 8 deals with synthesis, spectral and single crystal X-ray diffraction studies of dioxomolybdenum(VI) complexes.

Spectral, Structural And Biological Studies Of Some Metal Complexes Of ‘Nsubstituted 2-Benzoylpyridine Thiosemicarbazones

Aqua complex ions of metals must have existed since the appearance of water on the earth, and the subsequent appearance of life depended on, and may even have resulted from the interaction of metal ions with organic molecules. Studies on the coordinating ability of metal ions with other molecules and anions culminated in the theories of/\lfred Werner. Thereon the progress in the studies of metal complex chemistry was rapid. Many factors, like the utility and economic importance of metal chemistry, the intrinsic interest _in many of the compounds and the intellectual challenge of the structural problems to be solved, have contributed to this rapid progress. X—ray diffraction studies further accelerated the progress. The work cited in this thesis was carried out by the author in the Department of Applied Chemistry during 2001-2004. The primary aim of these investigations was to synthesise and characterize some transition metal complexes of 2-benzoylpyridine N(4)-substituted thiosemicarbazones and to study the antimicrobial activities of the ligands and their metal complexes. The work is divided into eight chapters

CBIR Using Local and Global Properties of Image Sub-blocks

This paper proposes a content based image retrieval (CBIR) system using the local colour and texture features of selected image sub-blocks and global colour and shape features of the image. The image sub-blocks are roughly identified by segmenting the image into partitions of different configuration, finding the edge density in each partition using edge thresholding, morphological dilation and finding the corner density in each partition. The colour and texture features of the identified regions are computed from the histograms of the quantized HSV colour space and Gray Level Co- occurrence Matrix (GLCM) respectively. A combined colour and texture feature vector is computed for each region. The shape features are computed from the Edge Histogram Descriptor (EHD). Euclidean distance measure is used for computing the distance between the features of the query and target image. Experimental results show that the proposed method provides better retrieving result than retrieval using some of the existing methods

Content Based Image Retrieval Using Low Level Features of Automatically Extracted Regions of Interest

This paper proposes a region based image retrieval system using the local colour and texture features of image sub regions. The regions of interest (ROI) are roughly identified by segmenting the image into fixed partitions, finding the edge map and applying morphological dilation. The colour and texture features of the ROIs are computed from the histograms of the quantized HSV colour space and Gray Level co- occurrence matrix (GLCM) respectively. Each ROI of the query image is compared with same number of ROIs of the target image that are arranged in the descending order of white pixel density in the regions, using Euclidean distance measure for similarity computation. Preliminary experimental results show that the proposed method provides better retrieving result than retrieval using some of the existing methods.

A Sub-block Based Image Retrieval Using Modified Integrated Region Matching.

This paper proposes a content based image retrieval (CBIR) system using the local colour and texture features of selected image sub-blocks and global colour and shape features of the image. The image sub-blocks are roughly identified by segmenting the image into partitions of different configuration, finding the edge density in each partition using edge thresholding, morphological dilation. The colour and texture features of the identified regions are computed from the histograms of the quantized HSV colour space and Gray Level Co- occurrence Matrix (GLCM) respectively. A combined colour and texture feature vector is computed for each region. The shape features are computed from the Edge Histogram Descriptor (EHD). A modified Integrated Region Matching (IRM) algorithm is used for finding the minimum distance between the sub-blocks of the query and target image. Experimental results show that the proposed method provides better retrieving result than retrieval using some of the existing methods

Development of a Fully Automated Image Analysis Method for High Density cDNA and array CGH Microarray Based Genomic Studies

In this thesis, different techniques for image analysis of high density microarrays have been investigated. Most of the existing image analysis techniques require prior knowledge of image specific parameters and direct user intervention for microarray image quantification. The objective of this research work was to develop of a fully automated image analysis method capable of accurately quantifying the intensity information from high density microarrays images. The method should be robust against noise and contaminations that commonly occur in different stages of microarray development.

Synthesis, Spectral and Structural Studies of a Novel Semicarbazone Synthesized from Quinoline-2-Carboxaldehyde and N4-Phenyl-3-Semicarbazide

A new semicarbazone, HL has been synthesized from quinoline-2-carboxaldehyde and N4-phenyl-3- semicarbazide and structurally and spectrochemically characterized. 1H NMR, 13C NMR, IR and electronic spectra of the compound are studied. The existence of keto form in the solid state is supported by the crystal structure and IR data. The compound crystallizes into an orthorhombic space group P212121. Intra and intermolecular hydrogen bonding interactions facilitates unit cell packing in the crystal lattice

Copper(II) complexes derived from di-2-pyridyl ketone-N4-phenyl-3-semicarbazone: Synthesis and spectral studies

Five copper(II) complexes [CuLCl]2·CuCl2·4H2O (1), [CuLOAc] (2), [CuLNO3]2 (3), [CuLN3] (4) and [CuLNCS]·3/2H2O (5) of di-2-pyridyl ketone-N4-phenyl-3-semicarbazone (HL) were synthesized and characterized by elemental analyses and electronic, infrared and EPR spectral techniques. In all these complexes the semicarbazone undergoes deprotonation and coordinates through enolate oxygen, azomethine and pyridyl nitrogen atoms. All the complexes are EPR active due to the presence of an unpaired electron. EPR spectra of all the complexes in DMF at 77K suggest axial symmetry and the presence of half field signals for the complexes 1 and 3 indicates dimeric structures

Synthesis, spectral and structural studies of oxovanadium(IV/V) complexes derived from 2-hydroxyacetophenone-3-hydroxy- 2-naphthoylhydrazone: polymorphs of oxovanadium(V) complex [VOL(OCH3)]

Oxovanadium(IV/V) complexes of 2-hydroxyacetophenone- 3-hydroxy-2-naphthoylhydrazone (H2L) have been synthesized and characterized. The complexes were characterized by elemental analyses, IR, electronic and EPR spectra. The oxovanadium(V) complex [VOL (OCH3)] is crystallized in two polymorphic forms, denoted by 1a and 1b, with space groups Pn21a and P 1, respectively. Both have distorted square pyramidal structures.

Synthesis and spectral investigations of Mn(II) complexes of pentadentate bis(thiosemicarbazones)

Five Mn(II) complexes of bis(thiosemicarbazones) which are represented as [Mn(H2Ac4Ph)Cl2] (1), [Mn(Ac4Ph)H2O] (2), [Mn(H2Ac4Cy)Cl2]·H2O (3), [Mn(H2Ac4Et)Cl2]·3H2O (4) and [Mn(H2Ac4Et)(OAc)2]·3H2O (5) have been synthesized and characterized by elemental analyses, electronic, infrared and EPR spectral techniques. In all the complexes except [Mn(Ac4Ph)H2O], the ligands act as pentadentate neutral molecules and coordinate to Mn(II) ion through two thione sulfur atoms, two azomethine nitrogens and the pyridine nitrogen, suggesting a heptacoordination. While in compound [Mn(Ac4Ph)H2O], the dianionic ligand is coordinated to the metal suggesting six coordination in this case. Magnetic studies indicate the high spin state of Mn(II). Conductivity measurements reveal their non-electrolyte nature. EPR studies indicate five g values for [Mn(Ac4Ph)H2O] showing zero field splitting.

Synthesis, spectral and structural studies of novel binuclear Ni(II) complex of salicylaldehyde 3-azacyclothiosemicarbazone

A novel binuclear Ni(II) complex of salicylaldehyde 3-azacyclothiosemicarbazone (H2L) has been synthesized and characterized by elemental analysis, IR and UV–Vis spectroscopy. The single crystal X-ray structure of the complex shows that bridging occurs through thiolato sulfur and phenolic oxygen atoms. Nickel centers in the complex have square planar and octahedral geometries

Preparation, magnetic and EPR spectral studies of copper(II) complexes of an anticancer drug analogue

Ten new copper(II) complexes of five potential bisthiocarbohydrazone and biscarbohydrazone ligands were synthesized and physico-chemically characterized. The spectral and magnetic studies of compounds are consistent with the formation of asymmetric di-, tri- or tetranuclear copper(II) complexes of deprotonated forms of respective ligands. The variable temperature magnetic susceptibility measurements of all complexes showantiferromagnetic interactions between the Cu(II) centers, in agreement with very broad powder EPR spectra. However, frozen solution EPR spectral studies are found in contradiction with the solid-state magnetic studies and indicate that the complexes are not very stable in solutions; the possible fragmentations of complexes are found in agreement with MALDI MS results. The EPR spectral simulation of most of the compounds is in agreement with the presence of two uncoupled Cu(II) species in solution.