2019 International Conference on Signal Processing and Communication (ICSC)
This paper presents an attempt made to recognize characters from English alphabets and numbers by... more This paper presents an attempt made to recognize characters from English alphabets and numbers by first segmenting them using bounding box and then recognizing each character individually. Each character data set contains 26 alphabets. For connected characters morphological operations are used that process the image based on shapes. The input image is processed using morphological operations by applying a structuring element and creating an output image of the same size. For the purpose of character recognition template matching technique is used. The proposed system shows good recognition rates as compared to other similar schemes for character segmentation and recognition.
2020 Sixth International Conference on Parallel, Distributed and Grid Computing (PDGC), 2020
Fatigueness of the driver is considered a major cause that account to a large numbers of death wo... more Fatigueness of the driver is considered a major cause that account to a large numbers of death worldwide. Thus it becomes necessary to develop a system that can help reduce such accidents. During drowsy state, significant differences in the facial features of the driver are observed in comparison to the normal state. The system proposed in the paper is focused on detection as well as alarming the driver after recording the physiological state of the driver. We made use of the non-intrusive approach which monitors the subject in real-time, wherein the blinking of eyes as well as the mouth shape (yawn) of the operator are observed, and if the operator's eyes are shut for more than the threshold value, or the operator is yawning, or if both of them are detected at the same instance then the driver's state is concluded for precautions. The proposed system is designed using Python Language, and OpenCV application is used for image processing employing the use of Viola - Jones Algorithm for the detection of facial features.
ABSTRACT This paper presents a new method for de-noising of images while preserving meaningful de... more ABSTRACT This paper presents a new method for de-noising of images while preserving meaningful details such as blurred thin edges and low-contrast fine features using an adaptive threshold in singular value decomposition. The existing singular value decomposition technique utilizes a global fixed threshold for entire image and does not discriminate the noisy data from the image information for the images having uneven background. In this paper, different thresholds for the different structured portions of the image have been calculated in accordance with local gradient and gray level variance at each pixel position of those portions of the image. An optimal threshold has been estimated by the analysis of signal to noise ratios of the singular value decomposed images for different thresholds. Experimental results from a variety of test images have shown that the proposed thresholding scheme on singular value decomposed images can effectively smooth noisy background along with edge preservation and restoration of fine details in the enhanced image.
2010 IEEE International Conference on Systems, Man and Cybernetics, 2010
This paper presents a new method to remove noise and enhance the image with the help of partial u... more This paper presents a new method to remove noise and enhance the image with the help of partial unsharp masking and conservative smoothing. In this method, unsharp masking is applied in partial way for detection of the edges and boundary lines in the image and then a conservative smoothing operation is applied on the selected areas to remove undesirable edges which represents the salt and pepper noise. Finally, the noise free edge image is added with the smoothed image to get the original image with reduced noise. The proposed method is compared with that of performance of mean and median filtering. The experimental results on synthetic and real images show the effectiveness of the proposed method.
ABSTRACT This paper provides a robust scheme for random valued impulsive noise reduction along wi... more ABSTRACT This paper provides a robust scheme for random valued impulsive noise reduction along with edge preservation by anisotropic diffusion with improved diffusivity. The defective impulse noisy pixels are detected by Laplacian based second order pixel difference operation where these defective pixels are replaced by appropriate values with regard of the gray level of their four directional neighbors. This de-noised image undergoes the diffusion operation where diffusion coefficient function is modified to make it adaptive by incorporating local gray level variance information. The proposed modified diffusion scheme effectively restore the edges and fine details destroyed during impulse noise reduction process. The effect of proposed diffusion scheme has been studied on various images and the results are compared with some existing diffusion methods which are independently used for impulse noise reduction and edge preservation. The results shows that the prior removal of impulsive noise before the application of diffusion process is advantageous over the direct application of diffusion for removing the impulsive noise. In addition, the results of the proposed diffusion scheme are compared with some of the median filter based methods which are effectively used for impulse noise reduction without caring of edge preservation. The proposed diffusion scheme sufficiently preserves the edges without boosting of impulsive noise components on images corrupted up to 50 % of the impulsive noise density.
2016 International Conference on Signal Processing and Communication (ICSC), 2016
The k-means initialization technique for a wireless sensor network is a newly emerging area for r... more The k-means initialization technique for a wireless sensor network is a newly emerging area for researchers. There are many constraints in designing the wireless sensor network. The primary constraint is energy consumption. Clustering is used for improving the lifetime of the system by reducing the power consumption. The most popular clustering technique is k-means algorithm but it exhibits local minima problem due to initial center selection. This paper provides the comprehensive survey of different initialization techniques such as Uniform Sampling, Random Sampling, k-means++ and Density based initialization. The above comparison has been made by taking the account of energy consumption and the lifetime of the wireless sensor network.
Background:Wireless Sensor Networks (WSNs) refer to a group of sensors used for sensing and monit... more Background:Wireless Sensor Networks (WSNs) refer to a group of sensors used for sensing and monitoring the physical data of the environment and organizing the collected data at a central location. These networks enjoy several benefits because of their lower cost, smaller size and smarter sensors. However, a limited source of energy and lifetime of the sensors have emerged as the major setbacks for these networks.Methods:In this work, an energy-aware algorithm has been proposed for the transmission of variable data packets from sensor nodes to the base station according to the balanced energy consumption by all the nodes of a WSN.Results:Obtained simulation results verify that the lifetime of the sensor network is significantly enhanced in comparison to other existing clustering based routing algorithm.Conclusion:The proposed algorithm is comparatively easy to implement and achieves a higher gain in the lifetime of a WSN while keeping the throughput nearly same as LEACH protocol.
2014 9th International Conference on Industrial and Information Systems (ICIIS), 2014
This paper presents a two stage process for image de-noising and edge enhancement by applying sin... more This paper presents a two stage process for image de-noising and edge enhancement by applying singular value decomposition technique on anisotropic diffused images. The two diffused versions of the input noisy image are generated in the first stage by anisotropic diffusion. The first diffused image is a well smoothed image and the second diffused image is sharp edge detected image. Singular value decomposition is applied on the two diffused versions individually to remove noise and to sharpen the detected edges respectively. Finally, the two singular value decomposition filtered images are linearly added to get the output image with reduced noise and sharp edges. Experimental results have been compared with recently developed singular value decomposition techniques and advanced anisotropic diffusion methods in terms of signal to noise ratio which shows that the proposed method is efficient for image enhancement as well as de-noising.
Proceedings of the Eighth Indian Conference on Computer Vision, Graphics and Image Processing - ICVGIP '12, 2012
ABSTRACT This paper provides the use of rule based fuzzy scheme to define a new diffusion coeffic... more ABSTRACT This paper provides the use of rule based fuzzy scheme to define a new diffusion coefficient function in anisotropic diffusion for impulse noise removal with edge preservation. This is achieved by expressing the small, medium and large labels of second order pixel differences in fuzzy format. An aggregated output membership function of percentage of noisiness is then obtained by selecting an optimal linguistic value of second order pixel difference during inference process. The pixels have been classified as homogeneous, edge and noisy pixels based on the degrees of noisiness of the output membership functions. To achieve desired smoothing of the impulse noisy images with homogeneous background, the new diffusion coefficient function in anisotropic diffusion is redefined to vary it in accordance with the degrees of noisiness of the output membership functions. The experimental results have been compared with existing anisotropic diffusion methods as well as advanced median filtering method. It is observed through experimental results that the proposed method works satisfactorily for images having impulsive noise density upto 50%.
2019 International Conference on Signal Processing and Communication (ICSC)
This paper presents an attempt made to recognize characters from English alphabets and numbers by... more This paper presents an attempt made to recognize characters from English alphabets and numbers by first segmenting them using bounding box and then recognizing each character individually. Each character data set contains 26 alphabets. For connected characters morphological operations are used that process the image based on shapes. The input image is processed using morphological operations by applying a structuring element and creating an output image of the same size. For the purpose of character recognition template matching technique is used. The proposed system shows good recognition rates as compared to other similar schemes for character segmentation and recognition.
2020 Sixth International Conference on Parallel, Distributed and Grid Computing (PDGC), 2020
Fatigueness of the driver is considered a major cause that account to a large numbers of death wo... more Fatigueness of the driver is considered a major cause that account to a large numbers of death worldwide. Thus it becomes necessary to develop a system that can help reduce such accidents. During drowsy state, significant differences in the facial features of the driver are observed in comparison to the normal state. The system proposed in the paper is focused on detection as well as alarming the driver after recording the physiological state of the driver. We made use of the non-intrusive approach which monitors the subject in real-time, wherein the blinking of eyes as well as the mouth shape (yawn) of the operator are observed, and if the operator's eyes are shut for more than the threshold value, or the operator is yawning, or if both of them are detected at the same instance then the driver's state is concluded for precautions. The proposed system is designed using Python Language, and OpenCV application is used for image processing employing the use of Viola - Jones Algorithm for the detection of facial features.
ABSTRACT This paper presents a new method for de-noising of images while preserving meaningful de... more ABSTRACT This paper presents a new method for de-noising of images while preserving meaningful details such as blurred thin edges and low-contrast fine features using an adaptive threshold in singular value decomposition. The existing singular value decomposition technique utilizes a global fixed threshold for entire image and does not discriminate the noisy data from the image information for the images having uneven background. In this paper, different thresholds for the different structured portions of the image have been calculated in accordance with local gradient and gray level variance at each pixel position of those portions of the image. An optimal threshold has been estimated by the analysis of signal to noise ratios of the singular value decomposed images for different thresholds. Experimental results from a variety of test images have shown that the proposed thresholding scheme on singular value decomposed images can effectively smooth noisy background along with edge preservation and restoration of fine details in the enhanced image.
2010 IEEE International Conference on Systems, Man and Cybernetics, 2010
This paper presents a new method to remove noise and enhance the image with the help of partial u... more This paper presents a new method to remove noise and enhance the image with the help of partial unsharp masking and conservative smoothing. In this method, unsharp masking is applied in partial way for detection of the edges and boundary lines in the image and then a conservative smoothing operation is applied on the selected areas to remove undesirable edges which represents the salt and pepper noise. Finally, the noise free edge image is added with the smoothed image to get the original image with reduced noise. The proposed method is compared with that of performance of mean and median filtering. The experimental results on synthetic and real images show the effectiveness of the proposed method.
ABSTRACT This paper provides a robust scheme for random valued impulsive noise reduction along wi... more ABSTRACT This paper provides a robust scheme for random valued impulsive noise reduction along with edge preservation by anisotropic diffusion with improved diffusivity. The defective impulse noisy pixels are detected by Laplacian based second order pixel difference operation where these defective pixels are replaced by appropriate values with regard of the gray level of their four directional neighbors. This de-noised image undergoes the diffusion operation where diffusion coefficient function is modified to make it adaptive by incorporating local gray level variance information. The proposed modified diffusion scheme effectively restore the edges and fine details destroyed during impulse noise reduction process. The effect of proposed diffusion scheme has been studied on various images and the results are compared with some existing diffusion methods which are independently used for impulse noise reduction and edge preservation. The results shows that the prior removal of impulsive noise before the application of diffusion process is advantageous over the direct application of diffusion for removing the impulsive noise. In addition, the results of the proposed diffusion scheme are compared with some of the median filter based methods which are effectively used for impulse noise reduction without caring of edge preservation. The proposed diffusion scheme sufficiently preserves the edges without boosting of impulsive noise components on images corrupted up to 50 % of the impulsive noise density.
2016 International Conference on Signal Processing and Communication (ICSC), 2016
The k-means initialization technique for a wireless sensor network is a newly emerging area for r... more The k-means initialization technique for a wireless sensor network is a newly emerging area for researchers. There are many constraints in designing the wireless sensor network. The primary constraint is energy consumption. Clustering is used for improving the lifetime of the system by reducing the power consumption. The most popular clustering technique is k-means algorithm but it exhibits local minima problem due to initial center selection. This paper provides the comprehensive survey of different initialization techniques such as Uniform Sampling, Random Sampling, k-means++ and Density based initialization. The above comparison has been made by taking the account of energy consumption and the lifetime of the wireless sensor network.
Background:Wireless Sensor Networks (WSNs) refer to a group of sensors used for sensing and monit... more Background:Wireless Sensor Networks (WSNs) refer to a group of sensors used for sensing and monitoring the physical data of the environment and organizing the collected data at a central location. These networks enjoy several benefits because of their lower cost, smaller size and smarter sensors. However, a limited source of energy and lifetime of the sensors have emerged as the major setbacks for these networks.Methods:In this work, an energy-aware algorithm has been proposed for the transmission of variable data packets from sensor nodes to the base station according to the balanced energy consumption by all the nodes of a WSN.Results:Obtained simulation results verify that the lifetime of the sensor network is significantly enhanced in comparison to other existing clustering based routing algorithm.Conclusion:The proposed algorithm is comparatively easy to implement and achieves a higher gain in the lifetime of a WSN while keeping the throughput nearly same as LEACH protocol.
2014 9th International Conference on Industrial and Information Systems (ICIIS), 2014
This paper presents a two stage process for image de-noising and edge enhancement by applying sin... more This paper presents a two stage process for image de-noising and edge enhancement by applying singular value decomposition technique on anisotropic diffused images. The two diffused versions of the input noisy image are generated in the first stage by anisotropic diffusion. The first diffused image is a well smoothed image and the second diffused image is sharp edge detected image. Singular value decomposition is applied on the two diffused versions individually to remove noise and to sharpen the detected edges respectively. Finally, the two singular value decomposition filtered images are linearly added to get the output image with reduced noise and sharp edges. Experimental results have been compared with recently developed singular value decomposition techniques and advanced anisotropic diffusion methods in terms of signal to noise ratio which shows that the proposed method is efficient for image enhancement as well as de-noising.
Proceedings of the Eighth Indian Conference on Computer Vision, Graphics and Image Processing - ICVGIP '12, 2012
ABSTRACT This paper provides the use of rule based fuzzy scheme to define a new diffusion coeffic... more ABSTRACT This paper provides the use of rule based fuzzy scheme to define a new diffusion coefficient function in anisotropic diffusion for impulse noise removal with edge preservation. This is achieved by expressing the small, medium and large labels of second order pixel differences in fuzzy format. An aggregated output membership function of percentage of noisiness is then obtained by selecting an optimal linguistic value of second order pixel difference during inference process. The pixels have been classified as homogeneous, edge and noisy pixels based on the degrees of noisiness of the output membership functions. To achieve desired smoothing of the impulse noisy images with homogeneous background, the new diffusion coefficient function in anisotropic diffusion is redefined to vary it in accordance with the degrees of noisiness of the output membership functions. The experimental results have been compared with existing anisotropic diffusion methods as well as advanced median filtering method. It is observed through experimental results that the proposed method works satisfactorily for images having impulsive noise density upto 50%.
Uploads
Papers by nafis khan