Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
9 results
Search Results
Item A Framework for Quality Enhancement of Multispectral Remote Sensing Images(Institute of Electrical and Electronics Engineers Inc., 2018) Suresh, S.; Das, D.; Lal, S.Researches in satellite image enhancement have been particularly confined to two major areas-contrast enhancement and image de noising of remote sensing images. The processing of relatively dark or shadowed images necessitates the need for robust remote sensing enhancement techniques. In this paper, a robust framework for quality enhancement of multispectral remote sensing images is proposed. The quantitative results of proposed algorithm and other existing remote sensing enhancement algorithms are calculated in terms of DE, NIQMC, BIQME, PisDist and CM on different remote sensing and other image databases. Results reveal that visual enhancement of the proposed algorithm is better than other existing remote sensing enhancement algorithms. Finally, the simulation experimental results show that proposed algorithm is effective and efficient for remotes sensing as well as natural images. © 2017 IEEE.Item The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics(Association for Computational Linguistics (ACL), 2021) Gehrmann, S.; Adewumi, T.; Aggarwal, K.; Ammanamanchi, P.S.; Anuoluwapo, A.; Bosselut, A.; Chandu, K.R.; Clinciu, M.; Das, D.; Dhole, K.D.; Du, W.; Durmus, E.; DuÅ¡ek, O.; Emezue, C.; Gangal, V.; Gârbacea, C.; Hashimoto, T.; Hou, Y.; Jernite, Y.; Jhamtani, H.; Ji, Y.; Jolly, S.; Kale, M.; Kumar, D.; Ladhak, F.; Madaan, A.; Maddela, M.; Mahajan, K.; Mahamood, S.; Majumder, B.P.; Martins, P.H.; McMillan-Major, A.; Mille, S.; van Miltenburg, E.; Nadeem, M.; Narayan, S.; Nikolaev, V.; Niyongabo, R.A.; Osei, S.; Parikh, A.; Perez-Beltrachini, L.; Rao, N.R.; Raunak, V.; Rodriguez, J.D.; Santhanam, S.; Sedoc, J.; Sellam, T.; Shaikh, S.; Shimorina, A.; Sobrevilla Cabezudo, M.A.S.; Strobelt, H.; Subramani, N.; Xu, W.; Yang, D.; Yerukola, A.; Zhou, J.We introduce GEM, a living benchmark for natural language Generation (NLG), its Evaluation, and Metrics. Measuring progress in NLG relies on a constantly evolving ecosystem of automated metrics, datasets, and human evaluation standards. Due to this moving target, new models often still evaluate on divergent anglo-centric corpora with well-established, but flawed, metrics. This disconnect makes it challenging to identify the limitations of current models and opportunities for progress. Addressing this limitation, GEM provides an environment in which models can easily be applied to a wide set of tasks and in which evaluation strategies can be tested. Regular updates to the benchmark will help NLG research become more multilingual and evolve the challenge alongside models. This paper serves as the description of the data for which we are organizing a shared task at our ACL 2021 Workshop and to which we invite the entire NLG community to participate. © 2021 Association for Computational LinguisticsItem Image quality restoration framework for contrast enhancement of satellite remote sensing images(Elsevier B.V., 2018) Suresh, S.; Das, D.; Lal, S.; Gupta, D.Researches in satellite remote sensing images mainly revolves around enhancement of contrast and removal of noise in image, which affects the data comprehensibility and clarity. Hence, it is always a challenge to process the satellite remote sensing images in order to obtain better quality images with enhanced visibility and minimum image artifacts for improving their application value. In this paper, an effective quality enhancement framework is proposed, which mainly focuses on contrast enhancement of satellite remote sensing images. Several satellite remote sensing images were tested to ratify the effectiveness of the proposed method over other existing remote sensing enhancement methods and their quantitative results are borne out by NIQMC (No Reference Image Quality Metric for Contrast distortion), BIQME (Blind Image Quality Measure of Enhanced images), MICHELSON (Michelson Contrast), DE (Discrete Entropy), EME (Measure of enhancement) and PIXDIST (Pixel distance) along with qualitative results comparison. Results depict that the visual enhancement obtained using the proposed method is superior to other existing enhancement methods. Finally, the simulation results unveil that proposed method is effective and efficient for satellite remotes sensing images. © 2018 Elsevier B.V.Item A robust framework for quality enhancement of aerial remote sensing images(Elsevier B.V., 2018) Karuna Kumari, E.; Das, D.; Suresh, S.; Lal, S.; Narasimhadhan, A.V.This paper proposes a robust framework for quality restoration of remotely sensed aerial images. Proposed framework works in three steps: (1) Efficient color balancing and saturation adjustment, (2) Efficient color restoration, (3) Modified contrast enhancement using particle swarm optimization (PSO). In order to show the robustness, step-wise results of proposed framework is illustrated. Several aerial images from two publically available datasets are tested to support the robustness of the proposed framework over existing image quality restoration methods. The experimental results of proposed framework and other existing quality restoration methods are compared in terms of NIQMC, BIQME, MICHELSON, DE, EME and PIXDIST along with visual experimental results. Based on experimental results conducted on several aerial images suggest that the proposed framework is outperform over existing quality restoration methods. © 2018 Elsevier B.V.Item Studies for removal of tar from producer gas in small scale biomass gasifiers using biodiesel(Elsevier Ltd, 2019) Madav, V.; Das, D.; Kumar, M.; Surwade, M.; Parikh, P.P.; Sethi, V.Biomass gasification based electricity generation systems are emerging as an important component of the decentralised energy supply systems in rural India. Each type of gasifier has different reaction conditions, temperature, residence time, pressure, feedstock, reactor design, and therefore the tar and particulate matter (PM) compositions and concentrations are found to vary. A field study was conducted on a 35 kWe downdraft gasifier to measure and characterize the tar in producer gas using GC-MS, for rice husk and pine needles as the two biomass feeds. Use of water-based scrubbers for removal of tar and PM is prevalent, however it is often the case that such clean-up is not adequate for meeting the engine manufacturers’ requirements for the quality of intake gas. Limited attempts have been reported for the use of organic solvent based gas cleaning in small scale downdraft gasifiers in the range 15–50 kWe. In the present work, toluene, naphthalene and phenol were selected as representative compounds of tar, and methyl oleate was selected to represent biodiesel as an organic solvent. A bench scale packed bed scrubber was designed for 95% removal of toluene. An 86–97% removal of toluene from the gas stream was achieved, and similar results were obtained for phenol and naphthalene. Further experiments were carried out with actual producer gas from a 1 kWe downdraft wood gasifier. Pongamia pinnata based biodiesel was used as the solvent, and 88–92% of the tar removal from the producer gas stream was achievable. © 2019 Elsevier LtdItem Room-temperature ultraviolet-ozone annealing of ZnO and ZnMgO nanorods to attain enhanced optical properties(Springer, 2020) Alam, M.J.; Murkute, P.; Sushama, S.; Ghadi, H.; Mondal, S.; Paul, S.; Das, D.; Pandey, S.K.; Chakrabarti, S.ZnO and ZnMgO nanorods have proven to be promising materials for sensing, UV and deep UV based optoelectronic applications. A major drawback of ZnO and ZnMgO based thin films and nanorods is the presence of native point defects which deteriorates their optical efficiency and becomes an impediment to their efficient device applications. The furnace and rapid thermal annealing processes have overcome this up to a great extent but being high temperature processes, they put many fabrication and technological limits in device fabrication. Especially keeping an eye on the future flexible devices, herein we report ultraviolet-ozone (UVO) annealing as a room-temperature, simple and cost-effective annealing method to improve the optical efficiency of ZnO and ZnMgO nanorods along with control of defect states. The ZnO and ZnMgO nanorods were grown by hydrothermal method and annealed in UVO irradiation. UVO annealing substantially improved near band emission and suppressed defect band emissions. It is found that zinc interstitial atoms migrate from the top portion of ZnO nanorods towards the bottom of nanorods after UVO annealing, resulting in reduced zinc interstitial defects in the top portion of nanorods. X-ray diffraction results showed improvement in structural properties. XPS results confirmed suppression of oxygen vacancies and zinc interstitials and improvement in lattice oxygen in the ZnO nanorods after UVO annealing. Optimum times of UVO annealing for ZnO and ZnMgO nanorods were 30 and 50 min respectively. These findings will be helpful for the further development of ZnO and ZnMgO nanorods based high performance optoelectronic devices and sensors. © 2020, Springer Science+Business Media, LLC, part of Springer Nature.Item NucleiSegNet: Robust deep learning architecture for the nuclei segmentation of liver cancer histopathology images(Elsevier Ltd, 2021) Lal, S.; Das, D.; Alabhya, K.; Kanfade, A.; Kumar, A.; Kini, J.R.The nuclei segmentation of hematoxylin and eosin (H&E) stained histopathology images is an important prerequisite in designing a computer-aided diagnostics (CAD) system for cancer diagnosis and prognosis. Automated nuclei segmentation methods enable the qualitative and quantitative analysis of tens of thousands of nuclei within H&E stained histopathology images. However, a major challenge during nuclei segmentation is the segmentation of variable sized, touching nuclei. To address this challenge, we present NucleiSegNet - a robust deep learning network architecture for the nuclei segmentation of H&E stained liver cancer histopathology images. Our proposed architecture includes three blocks: a robust residual block, a bottleneck block, and an attention decoder block. The robust residual block is a newly proposed block for the efficient extraction of high-level semantic maps. The attention decoder block uses a new attention mechanism for efficient object localization, and it improves the proposed architecture's performance by reducing false positives. When applied to nuclei segmentation tasks, the proposed deep-learning architecture yielded superior results compared to state-of-the-art nuclei segmentation methods. We applied our proposed deep learning architecture for nuclei segmentation to a set of H&E stained histopathology images from two datasets, and our comprehensive results show that our proposed architecture outperforms state-of-the-art methods. As part of this work, we also introduced a new liver dataset (KMC liver dataset) of H&E stained liver cancer histopathology image tiles, containing 80 images with annotated nuclei procured from Kasturba Medical College (KMC), Mangalore, Manipal Academy of Higher Education (MAHE), Manipal, Karnataka, India. The proposed model's source code is available at https://github.com/shyamfec/NucleiSegNet. © 2020 Elsevier LtdItem Efficient deep learning architecture with dimension-wise pyramid pooling for nuclei segmentation of histopathology images(Elsevier Ltd, 2021) Aatresh, A.A.; Yatgiri, R.P.; Chanchal, A.K.; Kumar, A.; Ravi, A.; Das, D.; Raghavendra, B.S.; Lal, S.; Kini, J.Image segmentation remains to be one of the most vital tasks in the area of computer vision and more so in the case of medical image processing. Image segmentation quality is the main metric that is often considered with memory and computation efficiency overlooked, limiting the use of power hungry models for practical use. In this paper, we propose a novel framework (Kidney-SegNet) that combines the effectiveness of an attention based encoder-decoder architecture with atrous spatial pyramid pooling with highly efficient dimension-wise convolutions. The segmentation results of the proposed Kidney-SegNet architecture have been shown to outperform existing state-of-the-art deep learning methods by evaluating them on two publicly available kidney and TNBC breast H&E stained histopathology image datasets. Further, our simulation experiments also reveal that the computational complexity and memory requirement of our proposed architecture is very efficient compared to existing deep learning state-of-the-art methods for the task of nuclei segmentation of H&E stained histopathology images. The source code of our implementation will be available at https://github.com/Aaatresh/Kidney-SegNet. © 2021 Elsevier LtdItem Novel edge detection method for nuclei segmentation of liver cancer histopathology images(Springer Science and Business Media Deutschland GmbH, 2023) Roy, S.; Das, D.; Lal, S.; Kini, J.In automatic cancer detection, nuclei segmentation is a very essential step which enables the classification task simpler and computationally more efficient. However, automatic nuclei detection is fraught with the problems of inter-class variability of nuclei size and shapes. In this research article, a novel unsupervised edge detection technique, is proposed for segmenting the nuclei regions in liver cancer Hematoxylin and Eosin (H&E) stained histopathology images. In this novel edge detection technique, the notion of computing local standard deviation is incorporated, instead of computing gradients. Since, local standard deviation value is correlated with the edge information of image, this novel method can extract the nuclei edges efficiently, even at multiscale. The edge-detected image is further converted into a binary image by employing Ostu (IEEE Trans Syst Man Cybern 9(1):62–66, 1979)’s thresholding operation. Subsequently, an adaptive morphological filter is also employed in order to refine the final segmented image. The proposed nuclei segmentation method is also tested on a well-recognized multi-organ dataset, in order to check its effectiveness over wide variety of dataset. The visual results of both datasets indicate that the proposed segmentation method overcomes the limitations of existing unsupervised methods, moreover, its performance is comparable with the same of recent deep neural models like DIST, HoverNet, etc. Furthermore, three quality metrics are computed in order to measure the performance of several nuclei segmentation methods quantitatively. The mean value of quality metrics reveals that proposed segmentation method indeed outperformed other existing nuclei segmentation methods. © 2021, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.