Phase only reconstructed images are indispensable for image understanding and processing nowadays. A couple of domain transforms like Fourier transform provide absolute phase while some like complex wavelet, curvelet e. more abstract Phase only reconstructed images are indispensable for image understanding and processing nowadays. A couple of domain transforms like Fourier transform provide absolute phase while some like complex wavelet, curvelet etc. give relative phase. It established fact that absolute phase contains the majority of the information baked into a picture. However, limited attempts happen to be designed to investigate information contributed through the relative phase. This paper analyzes the opportunity to extract the look information by relative phase quantitatively. Three indices according to structural similarity, dependency, and mutual information between original and phase only reconstructed images happen to be suggested to evaluate the data retentivity. The structural similarity (SSIM) index, correlation coefficient, and mutual information based on Shannon entropy (MISE) which by Renyi entropy (MIRE) are adopted to check the performances of relative phases provided by complex wavelet and curvelet transforms on various image database. Experimental evaluation demonstrates the potentiality of relative phase for extraction of image information and aids to decide on the most informative phase only renovation method in numerous applications.

Publication Date: Apr 2013

Publication Name: Students Conference on Engineering and Systems (SCES). IEEE, 2013

Phase only reconstructed images are indispensable for image understanding and processing nowadays. A couple of domain transforms like Fourier and S- transform provide absolute phase while some like complex wavelet, curv.

more abstract Phase only reconstructed images are indispensable for image understanding and processing nowadays. A couple of domain transforms like Fourier and S- transform provide absolute phase while some like complex wavelet, curvelet etc. give relative phase. It established fact that absolute phase contains the majority of the information baked into a picture. This synopsis analyzes the opportunity to extract the look information by relative and absolute phase quantitatively. Three indices according to structural similarity, dependency, and mutual information between original and phase only reconstructed images happen to be suggested to evaluate the data retentivity. The structural similarity (SSIM) index, correlation coefficient, and mutual information based on Shanon entropy (MISE) which by Renyi entropy (MIRE) are adopted to check the performances of absolute and relative phases provided by above transforms on various image databases. Experimental evaluation demonstrates the potentiality of absolute and relative phase for extraction of image information and aids to decide on the most informative phase only renovation method in numerous applications.

More Information: Thesis

Academia 2016

Phase only reconstructed images are indispensable for image understanding and processing nowadays. A couple of domain transforms like Fourier transform provide absolute phase while some like complex wavelet, curvelet e.

more abstract Phase only reconstructed images are indispensable for image understanding and processing nowadays. A couple of domain transforms like Fourier transform provide absolute phase while some like complex wavelet, curvelet etc. give relative phase. It established fact that absolute phase contains the majority of the information baked into a picture. However, limited attempts happen to be designed to investigate information contributed through the relative phase. This paper analyzes the opportunity to extract the look information by relative phase quantitatively. Three indices according to structural similarity, dependency, and mutual information between original and phase only reconstructed images happen to be suggested to evaluate the data retentivity. The structural similarity (SSIM) index, correlation coefficient, and mutual information based on Shannon entropy (MISE) which by Renyi entropy (MIRE) are adopted to check the performances of relative phases provided by complex wavelet and curvelet transforms on various image database. Experimental evaluation demonstrates the potentiality of relative phase for extraction of image information and aids to decide on the most informative phase only renovation method in numerous applications.

Publication Date: Apr 2013

Publication Name: Students Conference on Engineering and Systems (SCES). IEEE, 2013

Phase only reconstructed images are indispensable for image understanding and processing nowadays. A couple of domain transforms like Fourier and S- transform provide absolute phase while some like complex wavelet, curv. more abstract Phase only reconstructed images are indispensable for image understanding and processing nowadays. A couple of domain transforms like Fourier and S- transform provide absolute phase while some like complex wavelet, curvelet etc. give relative phase. It established fact that absolute phase contains the majority of the information baked into a picture. This synopsis analyzes the opportunity to extract the look information by relative and absolute phase quantitatively. Three indices according to structural similarity, dependency, and mutual information between original and phase only reconstructed images happen to be suggested to evaluate the data retentivity. The structural similarity (SSIM) index, correlation coefficient, and mutual information based on Shanon entropy (MISE) which by Renyi entropy (MIRE) are adopted to check the performances of absolute and relative phases provided by above transforms on various image databases. Experimental evaluation demonstrates the potentiality of absolute and relative phase for extraction of image information and aids to decide on the most informative phase only renovation method in numerous applications.

More Information: Thesis

Academia 2016