BITS Faculty Publications

Permanent URI for this communityhttp://localhost:4000/handle/123456789/1867

Browse

Filters

2013 - 2019112020 - 202415

Settings

Author: search.filters.author.Rajput, Amitesh SinghHas files: No

Search Results

Now showing 1 - 10 of 26
  • No Thumbnail Available
    Item
    An Alternate Approach for Single Image Haze Removal Using Path Prediction
    (Springer, 2023-05) Rajput, Amitesh Singh
    Haze removal is an important problem that existing studies have addressed from slight to extreme levels. It finds wide application in landscape photography where the haze causes low contrast and saturation, but it can also be used to improve images taken during rainy and foggy conditions. In this paper, considering the importance of haze removal and possible limitations of a well-known existing method, DehazeNet, we propose an alternate end-to-end method for single image haze removal using simple yet efficient image processing techniques. DehazeNet is among well performing haze removal schemes in the literature, however the problem of coloration and artifacts being produced in the output images has been observed for a certain set of images. Addressing this problem, the proposed solution is devised by taking advantage of the color features of the three color channels of an image to establish a decision criteria. Based on that, a suitable dehazing method for an input hazy image is selected. Removing the problem of poor coloration in output images, we have come up with an alternate method to remove the haze while retaining the visual and perceived quality of the image. The experimental results show that the proposed method yields better structural restoration, reduces haze content significantly, and does not cause any artifacts in the output image.
  • No Thumbnail Available
    Item
    Generation of Multi-Layered QR Codes with Efficient Compression
    (Springer, 2023-12) Rajput, Amitesh Singh
    In this modern data-centric era, securing information that is transferred over the internet is a serious concern. Various cryptographic and stenographic methods play a vital role in this purpose. In this work, we develop a multi-layered steganographic system capable of hiding payloads in different hidden layers inside QR codes. Furthermore, each layer is compressed and encrypted separately to secure the payload data. Hence, we use the QR (Quick Response) Code as the cover medium to achieve and implement the above principles. In the proposed multi-layered QR Code approach, the top layer works as a standard QR Code while the layers beneath it act as private data. The secret is efficiently compressed to accommodate more information within the same space provided, thereby increasing the holding capacity of the QR code. The data in each layer are retrieved using different methods according to the type of compression used during the encoding process of the specified layer. The proposed model can store up to nine hidden layers of data. Various robustness tests are carried out to validate the efficiency of the hidden layers in the QR code and to check whether the hidden layers can withstand alterations without any data loss. Importantly, the resulting QR code works identically to a normal version upon scanning with any typical QR code scanner.
  • No Thumbnail Available
    Item
    Distributed information fusion for secure healthcare
    (Elsevier, 2024) Rajput, Amitesh Singh
    Recent years have seen a significant increase in the demand for cutting-edge healthcare systems. With the rising potential of artificial intelligence and big data technology, all sectors, especially the healthcare sector, have been greatly supported. Huge amounts of privacy-sensitive clinical data are being generated from several sources. While processing these enormous amounts of diverse healthcare data, the problem is that the data are heterogeneous. The data vary with respect to the patient population, environment, data source, size, complexity, medical procedures, and treatment protocols at individual medical centers. This creates the need for a central knowledge base in the healthcare setting. Federated learning-based fusion techniques can turn out to be beneficial to acquire knowledge from these distributed data. This will bring the distributed data together into a single view that can help hospitals and health workers to obtain new insights and helps secure patients' personal information and safeguards them from information leakage. If the distribution of data among the classes is skewed or biased, the distribution is said to be imbalanced. This chapter discusses problems associated with imbalanced and heterogeneous healthcare data and their effects on machine learning models and proposes methods to improve data fairness in a distributed healthcare system using federated learning
  • No Thumbnail Available
    Item
    Blockchain for Privacy-Preserving Data Distribution in Healthcare
    (ICISSP, 2024) Rajput, Amitesh Singh
    As virtual transformation maintains to reshape healthcare, the security and privacy of health information have become paramount worries. This paper delves into the novel application of blockchain generation as a strategic technique to these urgent issues. In contrast to traditional centralized information control structures, blockchain introduces an intensive alternate with its decentralized, immutable, and transparent nature. This shift gives a robust alternative to comply with sensitive health data. We propose a contemporary, blockchainprimarily based method to seamlessly integrate existing healthcare records into ledgers and share them in a controlled way. The proposed method emphasizes enhanced data integrity, advanced security features, and a patient-centric technique to data governance using customized smart contracts. Experimental results underline the proposed method’s advanced performance for scalability, protection, and general machine performance, making a compelling case for its adoption in healthcare records control
  • No Thumbnail Available
    Item
    Example Based Privacy-Preserving Video Color Grading
    (Springer, 2019) Rajput, Amitesh Singh
    The integration of cloud computing and smart multimedia gadgets has made an attractive business model today. However, data privacy is one of the major concern when moving to third party driven infrastructures like cloud. Furthermore, due to diverse camera sensors, the captured multimedia may contain insufficient lightning/colors and processing them manually is a painstakingly task. A few schemes have been proposed to address this problem, however they suffered from the major drawback of computational and storage overhead, and becomes non-trivial in case of videos. Considering these challenges, we propose an automatic video color grading approach in this chapter. The proposed approach enables cloud data center to process encrypted multimedia data by transferring its colors as per an example image as the reference. We analyze the correlation between consecutive video sequences and propose to evaluate the color transformation parameters for every alternate video frame. In addition, proxy encryption based Paillier cryptosystem has been used for video encryption. As a result, the computational and storage overheads are drastically reduced with effective video grading results. The feasibility and robustness of the proposed approach are validated through various tests.
  • No Thumbnail Available
    Item
    Efficient single image haze removal using CLAHE and Dark Channel Prior for Internet of Multimedia Things
    (Elsevier, 2022) Rajput, Amitesh Singh
    The immersive growth of multimedia sensors in conjunction with IoT in smart cities has increased the requirement of efficient multimedia computing. One such example is the degradation of images during bad weather and their efficient processing to help surveillance, driving assistance, etc. Haze removal is an important procedure to avoid ill-condition visibility of the captured images. An optimized haze removal technique helps the local administrative authorities by integrating multimedia sensors with the IoT to improve the quality of life. In this chapter, we analyze the well-known single image dehazing technique – Dark Channel Prior (DCP) in terms of getting better image quality and optimized computational time. The DCP method is stable and a benchmark for dehazing. However, we found that the haze removal effects obtained by the DCP can be further enhanced by preprocessing the underlying image for contrast enhancement. Also, the computational time is improved with respect to the underlying refinements. Considering the dehazing quality and computational efficiency, we analyze the image quality and demonstrate that it can be further improved with a better preprocessing mechanism. The experiments are conducted over a wide variety of haze images from standard datasets and sufficient improvements over the original DCP method are demonstrated.
  • No Thumbnail Available
    Item
    Towards the growth of image encryption and authentication schemes
    (IEEE, 2013) Rajput, Amitesh Singh
    This paper is simply the gathering of recent developments in the field of image security and presents further improvements in the same field. Images are the most important utility of our life. They are used in many applications. There are two main goals of image security: image encryption and authentication. During the past years, several image encryption and authentication algorithms have been proposed. Image encryption techniques scramble the pixels of the image and decrease the correlation among the pixels, such that the encrypted image cannot be accessed by unauthorized user. Chaotic encryption method seems to be much better day by day. Chaotic encryption technique is the new way of cryptography. Many chaos-based encryption methods have been proposed in the last decade. This paper presents a survey of different chaotic image encryption schemes proposed in the last decade. The paper also presents different image encryption and authentication schemes and discusses the problems and resolution associated with them. Emphasizing the image security, the paper discusses a hybrid scheme for image encryption and authentication, such that further advances in the field of image security can be enhanced.
  • No Thumbnail Available
    Item
    A Novel Image Encryption and Authentication Scheme Using Chaotic Maps
    (Springer, 2014) Rajput, Amitesh Singh
    The paper presents an amalgam approach for image encryption and authentication. An ideal image cipher should be such that any adversary cannot modify the image and if any modifications are made, can be detected. The proposed scheme is novel and presents a unique approach to provide two level security to the image. Hashing and two chaotic maps are used in the algorithm where hash of the plain image is computed and the image is encrypted using key dependent masking and diffusion techniques. Initial key length is 132-bits which is extended to 148-bits. Performance and security analysis show that the proposed scheme is secure against different types of attacks and can be adopted for real time applications.
  • No Thumbnail Available
    Item
    CryptFine: Towards secure cloud based filtering in encrypted domain
    (IEEE, 2017) Rajput, Amitesh Singh
    Cloud computing is a shift towards increasing the capabilities dynamically without investing in new infrastructure. Enormous storage of data and high-speed computing to customers over the internet can be accomplished using cloud. Security of data in cloud is one of the chief concerns which acts as an obstacle in the realization of cloud computing. Along with quick expansion and application of cloud computing, users concern more and more regarding security and privacy issues involved in these techniques. An efficient method to perform privacy preserving image filtering operations in encrypted domain over cloud is proposed in this paper. The proposed method provides facility for distributed secure processing and storage of the secret image using Shamir's secret sharing method and Chinese remainder theorem. The plain secret image is divided into number of shares in a manner that each share by itself does not reveal any meaningful information about the original image, while collectively, they retain all the information. Two secret keys are used to avail security of image shares and without knowledge of such keys, one cannot restore the secret image back. Hence, the proposed scheme is highly secured and the image can be processed without revealing any information at the cloud data center. Experimental results demonstrate that number of image filtering procedures for enhancement can be carried out efficiently in encrypted domain using the proposed method.
  • No Thumbnail Available
    Item
    Fire Detection Using Dense Trajectories
    (Springer, 2018) Rajput, Amitesh Singh
    This paper proposes an automatic computer vision-based system for fire detection in videos. There are many previous methods for video-based fire detection but only very few of them have considered the challenge of camera motion or motion of the background scene while finding features based on motion of fire. Our method is divided into two phases. First, we train our system for color characteristics of fire with the help of Gaussian mixture model (GMM), and for texture features which are computed using local binary patterns (LBPs). Next, dense trajectories are computed for motion features which are free from camera motion or challenges of moving scene. Bounding boxes are detected with the help of color and texture models. Subsequently, dense trajectories are projected onto codebooks for feature vector computation, and chi-square kernel-based SVM is employed for classification of fire and non-fire motion representations. Quantitative evaluation of our method indicates the fitness of temporal features for fire detection.