Nanmaran Rajendiran
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Nanmaran Rajendiran has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
- Boppudi Vinoothna
Department of Biomedical Engineering, Saveetha School of Engineering, Saveetha Institute of Medical and Technical Sciences, Saveetha University, Chennai, Tamilnadu. India
2 shared publications - Ramaswamy Arulvel
Saveetha School of Engineering, Saveetha Institute of Medical and Technical Sciences, Saveetha University, Chennai, Tamil Nadu, India
2 shared publications A. Mohamed Adil
Department of Biomedical Engineering, Saveetha School of Engineering, Chennai, Tamil Nadu. India - 602105
1 shared publicationB. Luminasree
1 shared publicationBoppudi Vinoothna
1 shared publicationK. Amrutha
1 shared publication
Latest Publications
- 1 January 2024
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 3097 (1) , 020153
Analyzing the effect of feature extraction using GLRLM method in comparison with SIFT method on ANN based cancer classification model
The purpose of this study was to investigate how feature extraction strategies like GLRLM and SIFT affect artificial neural network-based cancer classification The purpose of this study was to investigate how feature extraction strategies like GLRLM and SIFT affect artificial neural network-based cancer classification
- 1 January 2024
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 3097 (1) , 020153
Analyzing the effect of feature extraction using GLRLM method in comparison with SIFT method on ANN based cancer classification model
The purpose of this study was to investigate how feature extraction strategies like GLRLM and SIFT affect artificial neural network-based cancer classification The purpose of this study was to investigate how feature extraction strategies like GLRLM and SIFT affect artificial neural network-based cancer classification
- 1 January 2024
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 2816 (1)
Design and implementation of ANN based multimodal biometric authentication system with improved accuracy in comparison with conventional biometric authentication system
The accuracy of the biometric authentication system can be improved by including combined features from face, iris, fingerprint images. This research aimed at d
- 1 January 2024
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 2816 (1)
Design and implementation of ANN based multimodal biometric authentication system with improved accuracy in comparison with conventional biometric authentication system
The accuracy of the biometric authentication system can be improved by including combined features from face, iris, fingerprint images. This research aimed at d
- 1 January 2024
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 2816 (1)
Design and development of contrast-limited adaptive histogram equalization technique for enhancing pet images by improving joint entropy, UIQI parameters in comparison with median filtering
Aim:Image enhancement is the process of improving image quality to a more understandable level for future automated image processing tasks such as analysis, ide
- 1 January 2024
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 2816 (1)
Design and development of contrast-limited adaptive histogram equalization technique for enhancing pet images by improving joint entropy, UIQI parameters in comparison with median filtering
Aim:Image enhancement is the process of improving image quality to a more understandable level for future automated image processing tasks such as analysis, ide
- 1 January 2024
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 2816 (1)
Design and development of contrast-limited adaptive histogram equalization technique for enhancing SPECT images by improving normalized correlation, UIQI parameters in comparison with median filtering
Image enhancement is a technique of processing an image in order to make it more suitable for specific applications. Image enhancement primarily sharpens image
- 1 January 2024
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 2816 (1)
Design and development of contrast-limited adaptive histogram equalization technique for enhancing SPECT images by improving normalized correlation, UIQI parameters in comparison with median filtering
Image enhancement is a technique of processing an image in order to make it more suitable for specific applications. Image enhancement primarily sharpens image
- Open Access
- 1 January 2023
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 2587 (1)
Development of shearlet transform based image fusion technique with improved SSIM on hyperspectral and pan images in comparison with wavelet transform based image fusion technique
Image fusion is the process of merging details from two or more images of the same scene taken at the same time or at different times to create more accurate images than the individual images might provide on their own. Pixel-based methods, decision-based methods, and feature-based methods are used in image fusion. In this work, shearlet transform based image fusion technique is proposed and developed. This proposed work is compared with wavelet transform based image fusion technique using SSIM and UIQI Values and the sample size for each group is 30. For sample size calculation threshold value is set to 0.05, confidence interval is 95%, power value is 80% and enrollment ratio is 1. The performance of image fusion is measured using two parameters namely Structural Similarity Index Measures (SSIM) and Universal Image Quality Index Measure (UIQI). High values of SSIM and UIQI indicates the better performance of image fusion algorithms. Shearlet transform provides mean SSIM values of 39.6000(dB),mean UIQI of 72.2567(%) and wavelet transform method provides mean SSIM values of 1.5090(dB),mean UIQI of 11.5283(%). Based on the experiments results from MATLAB software and from statistical analysis using IBM-SPSS software it is concluded that the shearlet transform based image fusion technique provides better results than wavelet transform based image fusion technique.
- 1 January 2023
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 2587 (1)
Open AccessDevelopment of shearlet transform based image fusion technique with improved SSIM on hyperspectral and pan images in comparison with wavelet transform based image fusion technique
Image fusion is the process of merging details from two or more images of the same scene taken at the same time or at different times to create more accurate images than the individual images might provide on their own. Pixel-based methods, decision-based methods, and feature-based methods are used in image fusion. In this work, shearlet transform based image fusion technique is proposed and developed. This proposed work is compared with wavelet transform based image fusion technique using SSIM and UIQI Values and the sample size for each group is 30. For sample size calculation threshold value is set to 0.05, confidence interval is 95%, power value is 80% and enrollment ratio is 1. The performance of image fusion is measured using two parameters namely Structural Similarity Index Measures (SSIM) and Universal Image Quality Index Measure (UIQI). High values of SSIM and UIQI indicates the better performance of image fusion algorithms. Shearlet transform provides mean SSIM values of 39.6000(dB),mean UIQI of 72.2567(%) and wavelet transform method provides mean SSIM values of 1.5090(dB),mean UIQI of 11.5283(%). Based on the experiments results from MATLAB software and from statistical analysis using IBM-SPSS software it is concluded that the shearlet transform based image fusion technique provides better results than wavelet transform based image fusion technique.
- Open Access
- 1 January 2023
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 2587 (1)
Brain tumor detection in MRI images using morphological watershed segmentation method to improve accuracy in comparison with threshold based segmentation method
Image segmentation is a method of processing digital images by using a series of algorithms to segment a portion of the image that contains enough information to match the input images. The aim of this study was to use image segmentation algorithms to improve brain tumour detection in MRI images. The use of a morphological watershed transform for segmenting brain tumour affected regions in mri images is suggested in this study. The proposed work is compared to threshold dependent segmentation, another image segmentation technique, with a sample size of 30 for each group. The performance of the image segmentation algorithm is measured using (SSIM) and universal index quality measure (UIQI) parameters. High values of SSIM and UIQI indicates better segmentation. Watershed transform provides mean SSIM values of 12.1814, mean of UIQI 61.3080 and threshold transform provides mean SSIM values of 8.8774, mean of UIQI 59.426. According to experimental results and statistical analysis using independent sample T-test, the watershed transform performs significantly better than the threshold-based transform with SSIM (0.1) and UIQI(0.5).
- 1 January 2023
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 2587 (1)
Open AccessBrain tumor detection in MRI images using morphological watershed segmentation method to improve accuracy in comparison with threshold based segmentation method
Image segmentation is a method of processing digital images by using a series of algorithms to segment a portion of the image that contains enough information to match the input images. The aim of this study was to use image segmentation algorithms to improve brain tumour detection in MRI images. The use of a morphological watershed transform for segmenting brain tumour affected regions in mri images is suggested in this study. The proposed work is compared to threshold dependent segmentation, another image segmentation technique, with a sample size of 30 for each group. The performance of the image segmentation algorithm is measured using (SSIM) and universal index quality measure (UIQI) parameters. High values of SSIM and UIQI indicates better segmentation. Watershed transform provides mean SSIM values of 12.1814, mean of UIQI 61.3080 and threshold transform provides mean SSIM values of 8.8774, mean of UIQI 59.426. According to experimental results and statistical analysis using independent sample T-test, the watershed transform performs significantly better than the threshold-based transform with SSIM (0.1) and UIQI(0.5).
- Open Access
- 1 January 2023
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 2587 (1)
Fibonacci transform based satellite image scrambling and reconstruction technique with improved SSIM parameter for increasing the robustness of digital watermarking algorithms in comparison with random shuffling method
Digital watermarking is the method of altering a piece of data in order to incorporate data-related information. In some cases, the watermarks may be visible so unauthorized persons can easily access the data. In order to protect the information from being copied and used without authorization, a unique technique is proposed. In this research a Fibonacci transform based image scrambling technique is proposed to enhance the security by applying scrambling algorithm to watermark before embedding them with input images. The proposed work is compared with another scrambling technique called Random Shuffling method and the sample size for each group is 30. The performance of image scrambling algorithm is measured using Structural similarity index measure (SSIM) and Universal index quality measure (UIQI) parameters. Low values of SSIM and UIQI indicates better scrambling. Fibonacci transform provides mean SSIM values of 15.8723%, mean UIQI of 66.8050% and Random shuffling method provides mean SSIM values of 23.0210% and UIQI of 76.2750%. Based on experimental results and statistical analysis using Independent sample T test, the Fibonacci transform based image scrambling method performs significantly better than Random Shuffling method with SSIM (P=0.007) and UIQI (P=0.008).
- 1 January 2023
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 2587 (1)
Open AccessFibonacci transform based satellite image scrambling and reconstruction technique with improved SSIM parameter for increasing the robustness of digital watermarking algorithms in comparison with random shuffling method
Digital watermarking is the method of altering a piece of data in order to incorporate data-related information. In some cases, the watermarks may be visible so unauthorized persons can easily access the data. In order to protect the information from being copied and used without authorization, a unique technique is proposed. In this research a Fibonacci transform based image scrambling technique is proposed to enhance the security by applying scrambling algorithm to watermark before embedding them with input images. The proposed work is compared with another scrambling technique called Random Shuffling method and the sample size for each group is 30. The performance of image scrambling algorithm is measured using Structural similarity index measure (SSIM) and Universal index quality measure (UIQI) parameters. Low values of SSIM and UIQI indicates better scrambling. Fibonacci transform provides mean SSIM values of 15.8723%, mean UIQI of 66.8050% and Random shuffling method provides mean SSIM values of 23.0210% and UIQI of 76.2750%. Based on experimental results and statistical analysis using Independent sample T test, the Fibonacci transform based image scrambling method performs significantly better than Random Shuffling method with SSIM (P=0.007) and UIQI (P=0.008).
- Open Access
- 1 January 2023
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 2587 (1)
Design and development of contrast-limited adaptive histogram equalization technique for enhancing CT images by improving SSIM, UIQI parameters in comparison with median filtering
Image enhancement is used to enhance and sharpen image features in order to produce a more detailed, or less noisy output image. In order to enhance the quality of CT images histogram based image enhancement technique is developed in this work. In this research, a contrast limited adaptive histogram equalization (CLAHE) based image enhancement technique is proposed and developed for CT images and the proposed work is compared with another image enhancement technique called median filtering method. Input medical images (N=30) of both group were downloaded from standard medical database. The enrollment ratio is obtained as 1 with 95% confidence interval and a threshold value 0.05. The performance of image enhancement is measured using two parameters namely structural similarity index measure (SSIM) and universal image quality index(UIQI). These parameters are calculated and evaluated to assess the proposed methods efficacy. High values of SSIM and UIQI indicate better enhancement. Contrast limited adaptive histogram equalization (CLAHE) provides mean SSIM values of 0.6503(%), mean UIQI of 86.3497% and median filtering method provides mean SSIM values of 0.5254(%) and mean UIQI of 81.3473%. Based on the experiments results from MATLAB software and from independent sample T test results of IBM-SPSS software, the contrast limited adaptive histogram equalization(CLAHE) based image enhancement technique significantly performed better than the median filtering(MF) based image enhancement technique with PSNR(P=0.091) and UIQI(P=0.070).
- 1 January 2023
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 2587 (1)
Open AccessDesign and development of contrast-limited adaptive histogram equalization technique for enhancing CT images by improving SSIM, UIQI parameters in comparison with median filtering
Image enhancement is used to enhance and sharpen image features in order to produce a more detailed, or less noisy output image. In order to enhance the quality of CT images histogram based image enhancement technique is developed in this work. In this research, a contrast limited adaptive histogram equalization (CLAHE) based image enhancement technique is proposed and developed for CT images and the proposed work is compared with another image enhancement technique called median filtering method. Input medical images (N=30) of both group were downloaded from standard medical database. The enrollment ratio is obtained as 1 with 95% confidence interval and a threshold value 0.05. The performance of image enhancement is measured using two parameters namely structural similarity index measure (SSIM) and universal image quality index(UIQI). These parameters are calculated and evaluated to assess the proposed methods efficacy. High values of SSIM and UIQI indicate better enhancement. Contrast limited adaptive histogram equalization (CLAHE) provides mean SSIM values of 0.6503(%), mean UIQI of 86.3497% and median filtering method provides mean SSIM values of 0.5254(%) and mean UIQI of 81.3473%. Based on the experiments results from MATLAB software and from independent sample T test results of IBM-SPSS software, the contrast limited adaptive histogram equalization(CLAHE) based image enhancement technique significantly performed better than the median filtering(MF) based image enhancement technique with PSNR(P=0.091) and UIQI(P=0.070).
- Open Access
- 1 January 2023
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 2587 (1)
Development of wavelet packet transform based image fusion technique with improved SSIM on PAN and hyperspectral images for quality enhancement in comparison with wavelet transform based image fusion technique
Image fusion is the process of merging two or more images into a single image with the characteristics of both input images. Image fusion is used to enhance the quality of input images. This research work focuses on to use transform domain methods to design image fusion algorithms. In this work, wavelet packet transform based image fusion technique is proposed and developed to improve the quality of image. The proposed work is compared with wavelet transform based image fusion technique using structural similarity index measures (SSIM) and universal image quality index (UIQI) values and sample size for each group is 30. The enrolment ratio is obtained as 1 with threshold value 0.05 and 95% confidence interval. The performance of image fusion is measured by using two parameters namely structural similarity index measures (SSIM) and universal image quality index (UIQI). High values of SSIM and UIQI indicate better performance of image fusion techniques. Wavelet packet transform provides mean SSIM-1 of 17.1437 %.mean SSIM-2 of 17.7810 %. mean UIQI of 78.9833 % and wavelet transform provides mean SSIM-1 of 11.5937 %,mean SSIM-2 of 9.9557 %, mean UIQI of 56.3563 %. Based on the experiments results from MATLAB software and from statistical analysis using IBM-SPSS software, it is concluded that the wavelet packet transform based image fusion technique provides better results than wavelet transform based image fusion technique with SSIM 1(P=0.192),SSIM 2(P=0.064) and UIQI(P=0.000).
- 1 January 2023
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 2587 (1)
Open AccessDevelopment of wavelet packet transform based image fusion technique with improved SSIM on PAN and hyperspectral images for quality enhancement in comparison with wavelet transform based image fusion technique
Image fusion is the process of merging two or more images into a single image with the characteristics of both input images. Image fusion is used to enhance the quality of input images. This research work focuses on to use transform domain methods to design image fusion algorithms. In this work, wavelet packet transform based image fusion technique is proposed and developed to improve the quality of image. The proposed work is compared with wavelet transform based image fusion technique using structural similarity index measures (SSIM) and universal image quality index (UIQI) values and sample size for each group is 30. The enrolment ratio is obtained as 1 with threshold value 0.05 and 95% confidence interval. The performance of image fusion is measured by using two parameters namely structural similarity index measures (SSIM) and universal image quality index (UIQI). High values of SSIM and UIQI indicate better performance of image fusion techniques. Wavelet packet transform provides mean SSIM-1 of 17.1437 %.mean SSIM-2 of 17.7810 %. mean UIQI of 78.9833 % and wavelet transform provides mean SSIM-1 of 11.5937 %,mean SSIM-2 of 9.9557 %, mean UIQI of 56.3563 %. Based on the experiments results from MATLAB software and from statistical analysis using IBM-SPSS software, it is concluded that the wavelet packet transform based image fusion technique provides better results than wavelet transform based image fusion technique with SSIM 1(P=0.192),SSIM 2(P=0.064) and UIQI(P=0.000).
- Open Access
- 1 January 2023
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 2587 (1)
Extraction of iris features using grey level co-occurrence matrix method with improved FAR and FRR for iris authentication in comparison with principal component analysis
The accuracy of the iris authentication system can be improved by including more features from Iris videos or images. This research aimed at developing Iris authentication systems using different feature extraction methods and ANN classifiers. In this research a grey-level co-occurrence matrix(GLCM) based feature extraction technique is proposed to improve the performance of the iris authentication system. The proposed work is compared with another feature extraction technique called Principal component analysis(PCA) and the sample size for each group is 30. The Artificial neural network (ANN) is used for iris detection and the performance of iris authentication is measured using two parameters namely False acceptance rate (FAR) and False rejection rate (FRR). Grey-level co-occurrence matrix(GLCM) provides mean FAR (0.1743) and FRR (86.86) and PCA provides mean FAR (0.0154)and FRR (76.33). Based on the experimental results and statistical analysis using independent sample T test, the Grey-level co-occurrence matrix(GLCM) method based Iris authentication significantly performs better than Principal component analysis(PCA) method with FAR(P=0.005) and FRR(P=0.001).
- 1 January 2023
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 2587 (1)
Open AccessExtraction of iris features using grey level co-occurrence matrix method with improved FAR and FRR for iris authentication in comparison with principal component analysis
The accuracy of the iris authentication system can be improved by including more features from Iris videos or images. This research aimed at developing Iris authentication systems using different feature extraction methods and ANN classifiers. In this research a grey-level co-occurrence matrix(GLCM) based feature extraction technique is proposed to improve the performance of the iris authentication system. The proposed work is compared with another feature extraction technique called Principal component analysis(PCA) and the sample size for each group is 30. The Artificial neural network (ANN) is used for iris detection and the performance of iris authentication is measured using two parameters namely False acceptance rate (FAR) and False rejection rate (FRR). Grey-level co-occurrence matrix(GLCM) provides mean FAR (0.1743) and FRR (86.86) and PCA provides mean FAR (0.0154)and FRR (76.33). Based on the experimental results and statistical analysis using independent sample T test, the Grey-level co-occurrence matrix(GLCM) method based Iris authentication significantly performs better than Principal component analysis(PCA) method with FAR(P=0.005) and FRR(P=0.001).