Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
9 results
Search Results
Item Super-resolution video generation algorithm for surveillance applications(Maney Publishing Suite 1C, Joseph's Well, Hanover Walk Leeds LS3 1AB, 2014) Pais, A.R.; D'Souza, J.; Reddy, R.M.Video surveillance is one of the major applications where high-resolution (HR) images are crucial. Since the video camera has limited spatial and temporal resolution, there is a need for super resolution video generation algorithms. In this paper, we have presented a novel technique for activity detection in the surveillance video. To achieve this goal, we have proposed and investigated efficient algorithms for Video Object Plane (VOP) generation, shadow removal from VOP and super-resolved VOP generation, for activity detection from surveillance video. The proposed VOP generation algorithm is computationally efficient and works for both dynamic and static backgrounds. The novel shadow removal algorithm for the VOP is based on texture and its performance has been studied based on average shadow detection and discrimination rates. The proposed super-resolution video generation algorithm has been designed using edge models. The performance of this algorithm has been evaluated using a numerical analysis technique and is found to be better than bi-cubic and bi-linear interpolation techniques. © 2014 RPS.Item Guided depth image reconstruction from very sparse measurements(SPIE spie@spie.org, 2018) Balure, C.S.; Bhavsar, A.; Ramesh Kini, M.Depth images captured from modern depth cameras generally suffer from low spatial resolution, noise, and missing regions. These kinds of images cannot be used directly in applications related to depth images, e.g., robot navigation, 3DTV, and augmented reality, which basically need high-resolution input images with no noise o missing regions to function properly. To address the problem of low spatial resolution, noise degradation, and missing regions in depth images, we propose methods based on a guidance color image for depth reconstruction (DR) from sparse depth inputs and depth image super-resolution (SR). We also suggest a scenario wherein these problems can be integrated and addressed simultaneously. Further, we also demonstrate applications of the proposed approach for depth image denoising and depth image inpainting. In our approach, the guidance color image is used for obtaining the segment cues by applying mean-shift (MS) or simple linear iterative clustering (SLIC) segmentation on it. These strong segment cues help in aiding the DR and SR problems by considering the corresponding segments in the input depth image, and estimate the unknown pixels by either plane fitting or median filling approaches. Furthermore, we explore both direct and pyramidal (hierarchical) approaches for SR and DR-SR for higher upsampling factor. As such, our approaches are relatively simpler than some of the contemporary methods, yet the experimental results of the proposed methods show superior performance as compared with some other state-of-the-art DR and SR methods. © 2018 SPIE and IS&T.Item Contrast enhancement of Progressive Visual Secret Sharing (PVSS) scheme for gray-scale and color images using super-resolution(Elsevier B.V., 2019) Mhala, N.C.; Pais, A.R.Traditional Visual Secret Sharing (VSS) scheme encrypts the secret image into multiple shares. It recovers the secret image based on the “all or nothing” methodology (i.e. all shares must be stacked together to recover the secret image else nothing will be revealed). The modern VSS schemes differ from traditional VSS by progressively recovering the secret image by stacking number of shares. These are also referred as Progressive VSS (PVSS). PVSS schemes generate two types of shares namely 1) meaningful (are the shares which have a meaningful image embedded as the cover image on top of the shares) and 2) noise-like (shares have a random noise-like appearance). In the previous work, we have proposed PVSS based Randomized VSS (RVSS) scheme to recover the secret image by hiding random data into the shares. RVSS achieves the maximum contrast of 70–80% and 70–90% for meaningful and noise-like shares respectively. In this paper, we propose a novel PVSS based super-resolution technique to improve the contrast of RVSS scheme. The experimental results showed that the proposed scheme achieves the contrast of 70–80% for meaningful shares and 99% for noise-like shares. Also, proposed scheme recovers the secret image free from blocking artifacts, for noise-like shares. © 2019 Elsevier B.V.Item A novel fingerprint template protection and fingerprint authentication scheme using visual secret sharing and super-resolution(Springer, 2021) Muhammed, A.; Mhala, N.C.; Pais, A.R.Fingerprint is the most recommended and extensively practicing biometric trait for personal authentication. Most of the fingerprint authentication systems trust minutiae as the characteristic for authentication. These characteristics are preserved as fingerprint templates in the database. However, it is observed that the databases are not secure and can be negotiated. Recent studies reveal that, if a person’s minutiae points are dripped, fingerprint can be restored from these points. Similarly, if the fingerprint records are lost, it is a permanent damage. There is no mechanism to replace the fingerprint as it is part of the human body. Hence there is a necessity to secure the fingerprint template in the database. In this paper, we introduce a novel fingerprint template protection and fingerprint authentication scheme using visual secret sharing and super-resolution. During enrollment, a secret fingerprint image is encrypted into n shares. Each share is stored in a distinct database. During authentication, the shares are collected from various databases. The original secret fingerprint image is restored using a multiple image super-resolution procedure. The experimental results show that the reconstructed fingerprints are similar to the original fingerprints. The proposed method is robust, secure, and efficient in terms of fingerprint template protection and authentication. © 2020, Springer Science+Business Media, LLC, part of Springer Nature.Item Efficient Channel Prediction Technique Using AMC and Deep Learning Algorithm for 5G (NR) mMTC Devices(Institute of Electrical and Electronics Engineers Inc., 2022) Sharma, V.; Arya, R.K.; Kumar, S.Efficient utilisation of adaptive modulation and coding ensures the quality transmission of information bits through the significant reduction in bit error rate (BER). Channel prediction using parametric estimation is not efficient for massive machine-type communication (mMTC) devices under the 5G New Radio (NR). In this paper, we have proposed a channel prediction scheme based on a deep learning (DL) algorithm possessed by parametric analysis. In deep learning, the pipeline methodology is used along with the image processing technique to predict the channel condition for optimal selection of the adaptive modulation and coding (AMC) profile. The deep learning-based pipelining approach utilises image restoration (IR) and image super-resolution (SR). The super-resolution method is used to de-noise the low-pixel 2-D image that is obtained from the parametric value of the beacon to predict the channel condition. The estimation results are compared with the conventional minimum mean square error (MMSE) and an approximation to the linear MMSE (ALMMSE) method, which is obtained through channel state information (CSI). The comparison results show that the parametric-enabled deep learning approach is superior, especially in poorer channel conditions. The performance of BER through parametric estimation along with the DL approach is 66% more efficient as compared to the conventional MMSE method for BPSK mapping. © 2013 IEEE.Item An Effective GPGPU Visual Secret Sharing by Contrast-Adaptive ConvNet Super-Resolution(Springer, 2022) Holla, M.R.; Pais, A.R.In this paper, we propose an effective secret image sharing model with super-resolution utilizing a Contrast-adaptive Convolution Neural Network (CCNN or CConvNet). The two stages of this model are the share generation and secret image reconstruction. The share generation step generates information embedded shadows (shares) equal to the number of participants. The activities involved in the share generation are to create a halftone image, create shadows, and transforming the image to the wavelet domain using Discrete Wavelet Transformation (DWT) to embed information into the shadows. The reconstruction stage is the inverse of the share generation supplemented with CCNN to improve the reconstructed image’s quality. This work is significant as it exploits the computational power of the General-Purpose Graphics Processing Unit (GPGPU) to perform the operations. The extensive use of memory optimization using GPGPU-constant memory in all the activities brings uniqueness and efficiency to the proposed model. The contrast-adaptive normalization between the CCNN layers in improving the quality during super-resolution impart novelty to our investigation. The objective quality assessment proved that the proposed model produces a high-quality reconstructed image with the SSIM of (89 - 99.8 %) for the noise-like shares and (71.6 - 90 %) for the meaningful shares. The proposed technique achieved a speedup of 800 × in comparison with the sequential model. © 2021, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.Item High-performance medical image secret sharing using super-resolution for CAD systems(Springer, 2022) Holla, M.R.; Pais, A.R.Visual Secret Sharing (VSS) is a field of Visual Cryptography (VC) in which the secret image (SI) is distributed to a certain number of participants in the form of different encrypted shares. The decryption then uses authorized shares in a pre-defined manner to obtain that secret information. Medical image secret sharing (MISS) is an emerging VSS field to address the performance challenges in sharing medical images, such as efficiency and effectiveness. Here, we propose a novel MISS for the histopathological medical images to achieve high performance in these two parameters. The novelty here is the Graphics Processing Unit (GPU) to exploit the data-parallelism in MISS during encryption and super-resolution (SR), supplementing effectiveness with efficiency. A Convolution Neural Network (CNN) for SR produces a high-contrast reconstructed image. We evaluate the presented model using standard objective assessment parameters and the Computer-Aided Diagnosis (CAD) systems. The result analysis confirmed the high-performance of the proposed MISS with a 98% SSIM of the deciphered image. Compared with the state-of-art deep learning models designed for the histopathological medical images, MISS outperformed with 99.71% accuracy. Also, we achieved a categorization precision that fits the CAD systems. We attained an overall speedup of 800 × over the sequential model. This speedup is significant compared to the speedups of the benchmark GPGPU-based medical image reconstruction models. © 2021, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.Item A secure fingerprint template generation mechanism using visual secret sharing with inverse halftoning(Academic Press Inc., 2023) Muhammed, A.; Pais, A.R.Fingerprints are the most popular and widely practiced biometric trait for human recognition and authentication. Due to the wide approval, reliable fingerprint template generation and secure saving of the generated templates are highly vital. Since fingers are permanently connected to the human body, loss of fingerprint data is irreversible. Cancelable fingerprint templates are used to overcome this problem. This paper introduces a novel cancelable fingerprint template generation mechanism using Visual Secret Sharing (VSS), data embedding, inverse halftoning, and super-resolution. During the fingerprint template generation, VSS shares with some hidden information are formulated as the secure cancelable template. Before authentication, the secret fingerprint image is reconstructed back from the VSS shares. The experimental results show that the proposed cancelable templates are simple, secure, and fulfill all the properties of the ideal cancelable templates, such as security, accuracy, non-invertibility, diversity, and revocability. The experimental analysis shows that the reconstructed fingerprint images are similar to the original fingerprints in terms of visual parameters and matching error rates. © 2023 Elsevier Inc.Item Accelerating randomized image secret sharing with GPU: contrast enhancement and secure reconstruction using progressive and convolutional approaches(Springer, 2024) Holla, M.; Suma, D.; Pais, A.R.Image Secret Sharing (ISS) is a cryptographic technique used to distribute secret images among multiple users. However, current Visual Secret Sharing (VSS) schemes produce a halftone image with only 50% contrast when reconstructing the original image. To overcome this limitation, the Randomized Image Secret Sharing (RISS) scheme was introduced. RISS achieves a higher contrast of 70% when extracting the secret image but comes with a high computational cost. This research paper presents a novel approach called Graphics Processing Unit (GPU)-based Randomized Image Secret Sharing (GRISS), which utilizes data parallelism within the RISS pipeline. The proposed technique also incorporates an Autoencoder-based Single Image Super-Resolution (ASISR) to enhance the contrast of the recovered image. The performance of GRISS is evaluated against RISS, and the contrast of the ASISR images is compared to current benchmark models. The results demonstrate that GRISS outperforms state-of-the-art models in both efficiency and effectiveness. © The Author(s) 2024.