Pallavi Parlewar - Academia.edu (original) (raw)
Papers by Pallavi Parlewar
Lecture notes in networks and systems, Dec 31, 2022
Deleted Journal, Mar 28, 2024
The drum set is a prominent instrument in a variety of music genres including pop, rock, and jazz... more The drum set is a prominent instrument in a variety of music genres including pop, rock, and jazz. However, it costs money and space to get from nothing to purchasing a kit. The objective of these studies is to enable drummers to hone their skills, at least blithely, without a full set of drums and to expedite the initiation of drummers to their drumming experiences without incurring any costs. Drums do not fit inside a single bag, making them more difficult to travel than other instruments. We propose a virtual drum prototype that enables air-drumming using just two sticks, a computer equipped with a camera, and readily available markers that resemble the drumstick tips, such colourful papers. The detection algorithm combines tracking techniques with deep learning technology for an enhanced user experience. This was done using the Python-based OpenCV, as well as the concept of color-based blob recognition was used to find the markers. The capacity to function as a USB controller and MIDI controllers as well as the possibility for further development as a released program have all been shown by this prototype. Results from experiments show how useful and successful this method is for producing a lifelike and immersive virtual drumming experience.
Journal of Discrete Mathematical Sciences & Cryptography/Journal of discrete mathematical sciences & cryptography, 2024
2023 3rd International Conference on Intelligent Technologies (CONIT)
International Journal of Innovative Technology and Exploring Engineering, 2020
In today’s era, women are progressing and scaling the peaks of success. However, there’s a signif... more In today’s era, women are progressing and scaling the peaks of success. However, there’s a significant hike in the number of crimes against women like molestation, eve-teasing, trafficking, etc. Also, there have been numerous attempts to ensure the safety of women ranging from the infamous mobile apps to the hefty belts &safety jackets,etc. However, it is not practical to carry such bulky systems and the victim may not be able to reach the smartphone without being noticed by the assaulter.This increases the risk factor. Therefore, to ensure the security of women, in this paper we propose an IOT based Emergency security system. This system includes a gsm, gps, raspberry pi, fingerprint module, camera module and IR led blasters. It aims at providing a dual security to the women with the help of panic button and fingerprint scanning device. Whenever a woman feels like she is in danger, she can manually switch on the system which will require her to scan her fingerprint for every 1 min....
Computer Engineering and Intelligent Systems, Mar 31, 2012
Tomographic reconstruction using Radon projections taken at an angle θ[0,2π) introduce a redundan... more Tomographic reconstruction using Radon projections taken at an angle θ[0,2π) introduce a redundancy of four. Hence the projection in one quadrant θ [0,π/2) are used for tomographic reconstruction to reduce computational overheads. In this paper, we present that the though the projections at an angle θ [0,π/2) do not introduce any redundancy, the achieved tomographic reconstruction is very poor. A qudrature Radon transform is further introduced as a combination of Radon transforms at projection angles θ and (θ+π/2). The individual back projections for θ and (θ+π/2) are computed in two parts separately; 1) considering them real and imaginary parts of a complex number 2) considering average of the individual back projections. It is observed that the quadrature Radon transform yields better results numerically and/or visually compared to conventional Radon transform θ[0,2π).
International Journal of Automation and Computing, Jun 1, 2013
The conventional discrete wavelet transform (DWT) introduces artifacts during denoising of images... more The conventional discrete wavelet transform (DWT) introduces artifacts during denoising of images containing smooth curves. Finite ridgelet transform (FRIT) solved this problem by mapping the curves in terms of small curved ridges. However, blind application of FRIT all over an image is computationally heavy. Finite curvelet transform (FCT) selectively applies FRIT only to the tiles containing small portions of a curve. In this work, a novel curvelet transform named as 4-quadrant finite curvelet transform (4QFCT) based on a new concept of 4-quadrant finite ridgelet transform (4QFRIT) has been proposed. An image is band pass filtered and the high frequency bands are divided into small non-overlapping square tiles. The 4QFRIT is applied to the tiles containing at least one curve element. Unlike FRIT, the 4QFRIT takes 4 sets of radon projections in all the 4 quadrants and then averages them in time and frequency domains after denoising. The proposed algorithm is extensively tested and benchmarked for denoising of images with Gaussian noise using mean squared error (MSE) and peak signal to noise ratio (PSNR). The results confirm that 4QFCT yields consistently better denoising performance quantitatively and visually.
Proceedings of Spie the International Society For Optical Engineering, 2010
International Journal of Next-Generation Computing, 2021
The modern cardinal rebellion led robots to become common in many areas such as military, medicin... more The modern cardinal rebellion led robots to become common in many areas such as military, medicine, agriculture, various industry etc. for surveillance or improve the quality. Robots are specially used for safety and security of human being. This enhances the quality of human life. Surveillance can also save life of the people or protect them from serious injuries. Intentional crime can be caught with the help of surveillance. This project propose Specially Programmable Intelligent Bot (SPiBot) robot is connected to the local network and takes commands from a computer on network. This can be done using SSH or Anydesk. The raspberry pi streams the feed from the camera to the local network using a command which starts the stream using the VLC media player’s in built network streaming functionality. The user can open the stream on any computer on the local network. The video is denoised using Ridgelet Transform
Bioscience Biotechnology Research Communications, 2020
This paper presents a novel supervised structure for estimating the depth from the monocular imag... more This paper presents a novel supervised structure for estimating the depth from the monocular images. Floating point Convolution Neural Network (FCNN) which shows better results as compared to traditional algorithms. Rectified Linear Unit (ReLU) is the used as an activation function in deep learning models. As ReLu shows performance improvement between the layers as the data transferred is compatible to the ranges prescribe by the layers. KITTI and City Space dataset is use for training and testing. We have use most commonly dataset so that the benchmarking is done on the basis of same dataset and same parameter, Root Mean Square Error(RMSE) and Del< 1.25*3. Our purposed FCNN algorithm yields improved results in depth estimation of various images.
International Journal of Innovative Technology and Exploring Engineering, 2019
Presence of nodules in lung images can be an indication of multiple types of diseases such as tum... more Presence of nodules in lung images can be an indication of multiple types of diseases such as tumor, cancer, etc. Detection of nodules for lung images is a ubiquitous task, which requires lot of computations for pre-processing, tissue detection, removal of non-nodule regions and finally nodule segmentation. In this paper we propose a multi-threshold descriptor based algorithm which applies multiple levels of thresholds to the image, in order to detect and remove all the non-nodule regions and finally uses KNN algorithm in order to classify the input image into benign or malignant. The training and testing sets are carefully selected in order to obtain optimal accuracy for the system. In this work, we obtain 82.65% accuracy, sensitivity and specificity is 85.71% and 80.35% respectively for classification of the input medical image.
Artificial Intelligence Review, 2015
Digital images always inherit some extent of noise in them. This noise affects the information co... more Digital images always inherit some extent of noise in them. This noise affects the information content of the image. Removal of this noise is very important to extract useful information from an im...
International Journal of Next-Generation Computing
A quick deployment and high-efficiency helium surveillance balloon which can be used as a mobile ... more A quick deployment and high-efficiency helium surveillance balloon which can be used as a mobile surveillance systemto monitor and locate trespassers near borders and high-security facilities are presented in the paper. The paperprovides the description of a motorized helium-filled balloon that is remotely controlled and provides a real-timevideo of any site that needs surveillance. The paper also provides the conceptual design, fabrication, and, calculationof the payload connected to of the helium balloon tracker. The payload consists of the control and monitoringsystem which has a camera and sensors and streams this data to the user over the internet which can be used forpatrolling and monitoring infiltration
Second International Conference on Digital Image Processing, 2010
Image Processing always aims at extracting maximum information from an image. To achieve this we ... more Image Processing always aims at extracting maximum information from an image. To achieve this we have to analyze the image completely along its periphery. But the parts of an image are hardly straight, they contain continuously varying slopes. Wavelet based image processing gives low resolution when the image has largely varying slopes and they give redundant coefficients. If we tile
Lecture notes in networks and systems, Dec 31, 2022
Deleted Journal, Mar 28, 2024
The drum set is a prominent instrument in a variety of music genres including pop, rock, and jazz... more The drum set is a prominent instrument in a variety of music genres including pop, rock, and jazz. However, it costs money and space to get from nothing to purchasing a kit. The objective of these studies is to enable drummers to hone their skills, at least blithely, without a full set of drums and to expedite the initiation of drummers to their drumming experiences without incurring any costs. Drums do not fit inside a single bag, making them more difficult to travel than other instruments. We propose a virtual drum prototype that enables air-drumming using just two sticks, a computer equipped with a camera, and readily available markers that resemble the drumstick tips, such colourful papers. The detection algorithm combines tracking techniques with deep learning technology for an enhanced user experience. This was done using the Python-based OpenCV, as well as the concept of color-based blob recognition was used to find the markers. The capacity to function as a USB controller and MIDI controllers as well as the possibility for further development as a released program have all been shown by this prototype. Results from experiments show how useful and successful this method is for producing a lifelike and immersive virtual drumming experience.
Journal of Discrete Mathematical Sciences & Cryptography/Journal of discrete mathematical sciences & cryptography, 2024
2023 3rd International Conference on Intelligent Technologies (CONIT)
International Journal of Innovative Technology and Exploring Engineering, 2020
In today’s era, women are progressing and scaling the peaks of success. However, there’s a signif... more In today’s era, women are progressing and scaling the peaks of success. However, there’s a significant hike in the number of crimes against women like molestation, eve-teasing, trafficking, etc. Also, there have been numerous attempts to ensure the safety of women ranging from the infamous mobile apps to the hefty belts &safety jackets,etc. However, it is not practical to carry such bulky systems and the victim may not be able to reach the smartphone without being noticed by the assaulter.This increases the risk factor. Therefore, to ensure the security of women, in this paper we propose an IOT based Emergency security system. This system includes a gsm, gps, raspberry pi, fingerprint module, camera module and IR led blasters. It aims at providing a dual security to the women with the help of panic button and fingerprint scanning device. Whenever a woman feels like she is in danger, she can manually switch on the system which will require her to scan her fingerprint for every 1 min....
Computer Engineering and Intelligent Systems, Mar 31, 2012
Tomographic reconstruction using Radon projections taken at an angle θ[0,2π) introduce a redundan... more Tomographic reconstruction using Radon projections taken at an angle θ[0,2π) introduce a redundancy of four. Hence the projection in one quadrant θ [0,π/2) are used for tomographic reconstruction to reduce computational overheads. In this paper, we present that the though the projections at an angle θ [0,π/2) do not introduce any redundancy, the achieved tomographic reconstruction is very poor. A qudrature Radon transform is further introduced as a combination of Radon transforms at projection angles θ and (θ+π/2). The individual back projections for θ and (θ+π/2) are computed in two parts separately; 1) considering them real and imaginary parts of a complex number 2) considering average of the individual back projections. It is observed that the quadrature Radon transform yields better results numerically and/or visually compared to conventional Radon transform θ[0,2π).
International Journal of Automation and Computing, Jun 1, 2013
The conventional discrete wavelet transform (DWT) introduces artifacts during denoising of images... more The conventional discrete wavelet transform (DWT) introduces artifacts during denoising of images containing smooth curves. Finite ridgelet transform (FRIT) solved this problem by mapping the curves in terms of small curved ridges. However, blind application of FRIT all over an image is computationally heavy. Finite curvelet transform (FCT) selectively applies FRIT only to the tiles containing small portions of a curve. In this work, a novel curvelet transform named as 4-quadrant finite curvelet transform (4QFCT) based on a new concept of 4-quadrant finite ridgelet transform (4QFRIT) has been proposed. An image is band pass filtered and the high frequency bands are divided into small non-overlapping square tiles. The 4QFRIT is applied to the tiles containing at least one curve element. Unlike FRIT, the 4QFRIT takes 4 sets of radon projections in all the 4 quadrants and then averages them in time and frequency domains after denoising. The proposed algorithm is extensively tested and benchmarked for denoising of images with Gaussian noise using mean squared error (MSE) and peak signal to noise ratio (PSNR). The results confirm that 4QFCT yields consistently better denoising performance quantitatively and visually.
Proceedings of Spie the International Society For Optical Engineering, 2010
International Journal of Next-Generation Computing, 2021
The modern cardinal rebellion led robots to become common in many areas such as military, medicin... more The modern cardinal rebellion led robots to become common in many areas such as military, medicine, agriculture, various industry etc. for surveillance or improve the quality. Robots are specially used for safety and security of human being. This enhances the quality of human life. Surveillance can also save life of the people or protect them from serious injuries. Intentional crime can be caught with the help of surveillance. This project propose Specially Programmable Intelligent Bot (SPiBot) robot is connected to the local network and takes commands from a computer on network. This can be done using SSH or Anydesk. The raspberry pi streams the feed from the camera to the local network using a command which starts the stream using the VLC media player’s in built network streaming functionality. The user can open the stream on any computer on the local network. The video is denoised using Ridgelet Transform
Bioscience Biotechnology Research Communications, 2020
This paper presents a novel supervised structure for estimating the depth from the monocular imag... more This paper presents a novel supervised structure for estimating the depth from the monocular images. Floating point Convolution Neural Network (FCNN) which shows better results as compared to traditional algorithms. Rectified Linear Unit (ReLU) is the used as an activation function in deep learning models. As ReLu shows performance improvement between the layers as the data transferred is compatible to the ranges prescribe by the layers. KITTI and City Space dataset is use for training and testing. We have use most commonly dataset so that the benchmarking is done on the basis of same dataset and same parameter, Root Mean Square Error(RMSE) and Del< 1.25*3. Our purposed FCNN algorithm yields improved results in depth estimation of various images.
International Journal of Innovative Technology and Exploring Engineering, 2019
Presence of nodules in lung images can be an indication of multiple types of diseases such as tum... more Presence of nodules in lung images can be an indication of multiple types of diseases such as tumor, cancer, etc. Detection of nodules for lung images is a ubiquitous task, which requires lot of computations for pre-processing, tissue detection, removal of non-nodule regions and finally nodule segmentation. In this paper we propose a multi-threshold descriptor based algorithm which applies multiple levels of thresholds to the image, in order to detect and remove all the non-nodule regions and finally uses KNN algorithm in order to classify the input image into benign or malignant. The training and testing sets are carefully selected in order to obtain optimal accuracy for the system. In this work, we obtain 82.65% accuracy, sensitivity and specificity is 85.71% and 80.35% respectively for classification of the input medical image.
Artificial Intelligence Review, 2015
Digital images always inherit some extent of noise in them. This noise affects the information co... more Digital images always inherit some extent of noise in them. This noise affects the information content of the image. Removal of this noise is very important to extract useful information from an im...
International Journal of Next-Generation Computing
A quick deployment and high-efficiency helium surveillance balloon which can be used as a mobile ... more A quick deployment and high-efficiency helium surveillance balloon which can be used as a mobile surveillance systemto monitor and locate trespassers near borders and high-security facilities are presented in the paper. The paperprovides the description of a motorized helium-filled balloon that is remotely controlled and provides a real-timevideo of any site that needs surveillance. The paper also provides the conceptual design, fabrication, and, calculationof the payload connected to of the helium balloon tracker. The payload consists of the control and monitoringsystem which has a camera and sensors and streams this data to the user over the internet which can be used forpatrolling and monitoring infiltration
Second International Conference on Digital Image Processing, 2010
Image Processing always aims at extracting maximum information from an image. To achieve this we ... more Image Processing always aims at extracting maximum information from an image. To achieve this we have to analyze the image completely along its periphery. But the parts of an image are hardly straight, they contain continuously varying slopes. Wavelet based image processing gives low resolution when the image has largely varying slopes and they give redundant coefficients. If we tile