Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
10 results
Search Results
Item A novel real-time face detection system using modified affine transformation and Haar cascades(Springer Verlag service@springer.de, 2019) Sharma, R.; Ashwin, T.S.; Guddeti, R.M.R.Human Face Detection is an important problem in the area of Computer Vision. Several approaches are used to detect the face for a given frame of an image but most of them fail to detect the faces which are tilted, occluded, or with different illuminations. In this paper, we propose a novel real-time face detection system which detects the faces that are tilted, occluded, or with different illuminations, any difficult pose. The proposed system is a desktop application with a user interface that not only collects the images from web camera but also detects the faces in the image using a Haar-cascaded classifier consisting of Modified Census Transform features. The problem with cascaded classifier is that it does not detect the tilted or occluded faces with different illuminations. Hence to overcome this problem, we proposed a system using Modified Affine Transformation with Viola Jones. Experimental results demonstrate that proposed face detection system outperforms Viola–Jones method by 6% (99.7% accuracy for the proposed system when compare to 93.5% for Voila Jones) with respect to three different datasets namely FDDB, YALE and “Google top 25 ‘tilted face’” image datasets. © Springer Nature Singapore Pte Ltd. 2019Item Sub-pixel mineral mapping using EO-1 hyperion hyperspectral data(International Society for Photogrammetry and Remote Sensing, 2014) Kumar, C.; Shetty, A.; Raval, S.; Champatiray, P.K.; Sharma, R.This study describes the utility of Earth Observation (EO)-1 Hyperion data for sub-pixel mineral investigation using Mixture Tuned Target Constrained Interference Minimized Filter (MTTCIMF) algorithm in hostile mountainous terrain of Rajsamand district of Rajasthan, which hosts economic mineralization such as lead, zinc, and copper etc. The study encompasses pre-processing, data reduction, Pixel Purity Index (PPI) and endmember extraction from reflectance image of surface minerals such as illite, montmorillonite, phlogopite, dolomite and chlorite. These endmembers were then assessed with USGS mineral spectral library and lab spectra of rock samples collected from field for spectral inspection. Subsequently, MTTCIMF algorithm was implemented on processed image to obtain mineral distribution map of each detected mineral. A virtual verification method has been adopted to evaluate the classified image, which uses directly image information to evaluate the result and confirm the overall accuracy and kappa coefficient of 68% and 0.6 respectively. The sub-pixel level mineral information with reasonable accuracy could be a valuable guide to geological and exploration community for expensive ground and/or lab experiments to discover economic deposits. Thus, the study demonstrates the feasibility of Hyperion data for sub-pixel mineral mapping using MTTCIMF algorithm with cost and time effective approach.Item Audio songs classification based on music patterns(Springer Verlag service@springer.de, 2016) Sharma, R.; Vishnu Srinivasa Murthy, Y.V.S.; Koolagudi, S.G.In this work, effort has been made to classify audio songs based on their music pattern which helps us to retrieve the music clips based on listener’s taste. This task is helpful in indexing and accessing the music clip based on listener’s state. Seven main categories are considered for this work such as devotional, energetic, folk, happy, pleasant, sad and, sleepy. Forty music clips of each category for training phase and fifteen clips of each category for testing phase are considered; vibrato-related features such as jitter and shimmer along with the mel-frequency cepstral coefficients (MFCCs); statistical values of pitch such as min, max, mean, and standard deviation are computed and added to the MFCCs, jitter, and shimmer which results in a 19-dimensional feature vector. feedforward backpropagation neural network (BPNN) is used as a classifier due to its efficiency in mapping the nonlinear relations. The accuracy of 82% is achieved on an average for 105 testing clips. © Springer India 2016.Item Employing Differentiable Neural Computers for Image Captioning and Neural Machine Translation(Elsevier B.V., 2020) Sharma, R.; Kumar, A.; Meena, D.; Pushp, S.In the history of artificial neural networks, LSTMs have proved to be a high-performance architecture at sequential data learning. Although LSTMs are remarkable in learning sequential data but are limited in their ability to learn long-term dependencies and representation of certain data structures because of the lack of external memory. In this paper, we tackled two main tasks, one is language translation and other is image captioning. We approached the problem of language translation by leveraging the capabilities of the recently developed DNC architectures. Here we modified the DNC architecture by including dual neural controllers instead of one and an external memory module. Inside our controller, we employed a neural network with memory-augmentation which differs from the original differentiable neural computer, we implemented a dual controller's system in which one controller is for encoding the query sequence whereas another controller is for decoding the translated sequences. During the encoding cycle, new inputs are read and the memory is updated accordingly. In the decoding cycle, the memory is protected from any writing from the decoding controller. Thus, the decoder phase generates a translated sequence at a time step. Therefore, the proposed dual controller neural network with memory-augmentation is then trained and tested on the Europarl dataset. For the image captioning task, our architecture is inspired by an end-to-end image captioning model where CNN's output is passed to RNN as input only once and the RNN generates words depending on the input. We trained our DNC captioning model on 2015 MSCOCO dataset. In the end, we compared and shows the superiority of our architecture as compared to conventionally used LSTM and NTM architectures. © 2020 The Authors. Published by Elsevier B.V.Item Vocal Tract Articulatory Contour Detection in Real-Time Magnetic Resonance Images Using Spatio-Temporal Context(Institute of Electrical and Electronics Engineers Inc., 2020) Hebbar, S.A.; Sharma, R.; Somandepalli, K.; Toutios, A.; Narayanan, S.Due to its ability to visualize and measure the dynamics of vocal tract shaping during speech production, real-time magnetic resonance imaging (rtMRI) has emerged as one of the prominent research tools. The ability to track different articulators such as the tongue, lips, velum, and the pharynx is a crucial step toward automating further scientific and clinical analysis. Recently, various researchers have addressed the problem of detecting articulatory boundaries, but those are primarily limited to static-image based methods. In this work, we propose to use information from temporal dynamics together with the spatial structure to detect the articulatory boundaries in rtMRI videos. We train a convolutional LSTM network to detect and label the articulatory contours. We compare the produced contours against reference labels generated by iteratively fitting a manually created subject-specific template. We observe that the proposed method outperforms solely image-based methods, especially for the difficult-to-track articulators involved in airway constriction formation during speech. © 2020 IEEE.Item Automatizing the Khasra Maps Generation Process Using Open Source Software: QGIS and Python Coding Language(Springer Science and Business Media Deutschland GmbH, 2022) Sharma, R.; Beg, M.K.; Bhojaraja, B.E.; Umesh, P.Humans are trying to acquire a piece of land from the time they have come into existence. In modern era, the management of land and its ownership is taken up by the Land and Revenue Department of the State. In order to do that, they need maps with specific objectives, so that even a laymen can understand and use it. The process explained in this paper automate the process of map making after getting the digitized shapefile of the khasra (property identification number), as a single village is divided into numerous grids and it is a tedious work and can have lots of errors while doing it manually. So in order to do the process in swift manner and without having any errors, the process was developed using the Quantum Geographic Information System (QGIS) and Python. The proposed method involves making the use of models built in QGIS along with the Python console. It helps to run the whole process on its own with taking the required input parameters and storing the outputs in a specific folder designed for them. The requirement of the project was to do the same operations on a village file and to get the final khasra map from the village polygon file. Depending upon the village area and its dimensions, the numbers of grids for a particular village is decided and the same GIS tools need to be run on each grid files which make this process a tedious work and more prone to errors. By making use of the method suggested in the paper, all the work can be done error proof with the use of Python. The use of Python code helps to do work in just couple of seconds which would have taken days to complete. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.Item Visualisation and Assessment of Seasonal Variations in Bus Passenger Mobility Pattern(Springer Science and Business Media Deutschland GmbH, 2024) Nithin, K.S.; Mulangi, R.H.; Sharma, R.; Baishya, H.; Panth, P.; Mohtashim, M.D.Passenger mobility pattern is an essential characteristic in designing, managing and operating the public transit system. It depicts how passenger behaviour responds to changes in spatial and temporal attributes. In the past, studies have done the spatiotemporal analysis of hourly and daily variations but the effect of seasonal variation on the passenger mobility pattern has been neglected which causes inadequate planning and has led to an inefficient transit system. In the present study, non-negative tensor decomposition (NTD) is used to carry out spatiotemporal analysis of bus passengers by considering seasonal variation in passenger mobility. Six months of electronic ticketing machine (ETM) data of the intra-city bus service of Davangere is used. From the analysis, it is observed that people coming from outside, majorly from suburban and village areas used public transit more during the wet season compared to dry months. It portrays that people are sensitive to weather conditions and tend to shift from private vehicles to public transit and vice-versa. Hence, this methodology helps transit planners in the managerial aspect through rescheduling services and frequency. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.Item Photo- and Electrocatalytic Reduction of CO2 over Metal-Organic Frameworks and Their Derived Oxides: A Correlation of the Reaction Mechanism with the Electronic Structure(American Chemical Society, 2022) Payra, S.; Ray, S.; Sharma, R.; Tarafder, K.; Mohanty, P.; Roy, S.A Ce/Ti-based bimetallic 2-aminoterephthalate metal-organic framework (MOF) was synthesized and evaluated for photocatalytic reduction of CO2 in comparison with an isoreticular pristine monometallic Ce-terephthalate MOF. Owing to highly selective CO2 adsorption capability, optimized band gaps, higher flux of photogenerated electron-hole pairs, and a lower rate of recombination, this material exhibited better photocatalytic reduction of CO2 and lower hydrogen evolution compared to Ce-terephthalate. Thorough probing of the surface and electronic structure inferred that the reducibility of Ce4+ to Ce3+ was due to the introduction of an amine functional group into the linker, and low-lying Ti(3d) orbitals in Ce/Ti-2-aminoterephthalate facilitated the photoreduction reaction. Both the MOFs were calcined to their respective oxides of Ce1-xTixO2 and CeO2, and the electrocatalytic reduction of CO2 was performed over the oxidic materials. In contrast to the photocatalytic reaction mechanism, the lattice substitution of Ti in the CeO2 fluorite cubic structure showed a better hydrogen evolution reaction and consequently, poorer electroreduction of CO2 compared to pristine CeO2. Density functional theory calculations of the competitive hydrogen evolution reaction on the MOF and the oxide surfaces corroborated the experimental findings. © 2022 American Chemical Society.Item WideCaps: a wide attention-based capsule network for image classification(Springer Science and Business Media Deutschland GmbH, 2023) Pawan, S.J.; Sharma, R.; Reddy, H.; Vani, M.; Rajan, J.The capsule network is a distinct and promising segment of the neural network family that has drawn attention due to its unique ability to maintain equivariance by preserving spatial relationships among the features. The capsule network has attained unprecedented success in image classification with datasets such as MNIST and affNIST by encoding the characteristic features into capsules and building a parse-tree structure. However, on datasets involving complex foreground and background regions, such as CIFAR-10 and CIFAR-100, the performance of the capsule network is suboptimal due to its naive data routing policy and incompetence in extracting complex features. This paper proposes a new design strategy for capsule network architectures for efficiently dealing with complex images. The proposed method incorporates the optimal placement of the novel wide bottleneck residual block and squeeze and excitation Attention Blocks into the capsule network upheld by the modified factorized machines routing algorithm to address the defined problem. This setup allows channel interdependencies at almost no computational cost, thereby enhancing the representation ability of capsules on complex images. We extensively evaluate the performance of the proposed model on the five publicly available datasets, namely the CIFAR-10, Fashion MNIST, Brain Tumor, SVHN, and the CIFAR-100 datasets. The proposed method outperformed the top-5 capsule network-based methods on Fashion MNIST, CIFAR-10, SVHN, Brain Tumor, and gave a highly competitive performance on the CIFAR-100 datasets. © 2023, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.Item N-Acyl phenothiazines as mycobacterial ATP synthase inhibitors: Rational design, synthesis and in vitro evaluation against drug sensitive, RR and MDR-TB(Academic Press Inc., 2024) Reddyrajula, R.; Perveen, S.; Negi, A.; Etikyala, U.; Vijjulatha, V.; Sharma, R.; Udayakumar, D.The mycobacterial F-ATP synthase is responsible for the optimal growth, metabolism and viability of Mycobacteria, establishing it as a validated target for the development of anti-TB therapeutics. Herein, we report the discovery of an N-acyl phenothiazine derivative, termed PT6, targeting the mycobacterial F-ATP synthase. PT6 is bactericidal and active against the drug sensitive, Rifampicin-resistant as well as Multidrug-resistant tuberculosis strains. Compound PT6 showed noteworthy inhibition of F-ATP synthesis, exhibiting an IC50 of 0.788 µM in M. smegmatis IMVs and was observed that it could deplete intracellular ATP levels, exhibiting an IC50 of 30 µM. PT6 displayed a high selectivity towards mycobacterial ATP synthase compared to mitochondrial ATP synthase. Compound PT6 showed a minor synergistic effect in combination with Rifampicin and Isoniazid. PT6 demonstrated null cytotoxicity as confirmed by assessing its toxicity against VERO cell lines. Further, the binding mechanism and the activity profile of PT6 were validated by employing in silico techniques such as molecular docking, Prime MM/GBSA, DFT and ADMET analysis. These results suggest that PT6 presents an attractive lead for the discovery of a novel class of mycobacterial F-ATP synthase inhibitors. © 2024 Elsevier Inc.