The Experts below are selected from a list of 26622 Experts worldwide ranked by ideXlab platform

Michael S Brown - One of the best experts on this subject based on the ideXlab platform.

  • training based spectral reconstruction from a single RGB Image
    European Conference on Computer Vision, 2014
    Co-Authors: Rang M H Nguyen, Dilip K Prasad, Michael S Brown
    Abstract:

    This paper focuses on a training-based method to reconstruct a scene’s spectral reflectance from a single RGB Image captured by a camera with known spectral response. In particular, we explore a new strategy to use training Images to model the mapping between camera-specific RGB values and scene reflectance spectra. Our method is based on a radial basis function network that leverages RGB white-balancing to normalize the scene illumination to recover the scene reflectance. We show that our method provides the best result against three state-of-art methods, especially when the tested illumination is not included in the training stage. In addition, we also show an effective approach to recover the spectral illumination from the reconstructed spectral reflectance and RGB Image. As a part of this work, we present a newly captured, publicly available, data set of hyperspectral Images that are useful for addressing problems pertaining to spectral imaging, analysis and processing.

  • ECCV (7) - Training-Based Spectral Reconstruction from a Single RGB Image
    Computer Vision – ECCV 2014, 2014
    Co-Authors: Rang M H Nguyen, Dilip K Prasad, Michael S Brown
    Abstract:

    This paper focuses on a training-based method to reconstruct a scene’s spectral reflectance from a single RGB Image captured by a camera with known spectral response. In particular, we explore a new strategy to use training Images to model the mapping between camera-specific RGB values and scene reflectance spectra. Our method is based on a radial basis function network that leverages RGB white-balancing to normalize the scene illumination to recover the scene reflectance. We show that our method provides the best result against three state-of-art methods, especially when the tested illumination is not included in the training stage. In addition, we also show an effective approach to recover the spectral illumination from the reconstructed spectral reflectance and RGB Image. As a part of this work, we present a newly captured, publicly available, data set of hyperspectral Images that are useful for addressing problems pertaining to spectral imaging, analysis and processing.

Rang M H Nguyen - One of the best experts on this subject based on the ideXlab platform.

  • training based spectral reconstruction from a single RGB Image
    European Conference on Computer Vision, 2014
    Co-Authors: Rang M H Nguyen, Dilip K Prasad, Michael S Brown
    Abstract:

    This paper focuses on a training-based method to reconstruct a scene’s spectral reflectance from a single RGB Image captured by a camera with known spectral response. In particular, we explore a new strategy to use training Images to model the mapping between camera-specific RGB values and scene reflectance spectra. Our method is based on a radial basis function network that leverages RGB white-balancing to normalize the scene illumination to recover the scene reflectance. We show that our method provides the best result against three state-of-art methods, especially when the tested illumination is not included in the training stage. In addition, we also show an effective approach to recover the spectral illumination from the reconstructed spectral reflectance and RGB Image. As a part of this work, we present a newly captured, publicly available, data set of hyperspectral Images that are useful for addressing problems pertaining to spectral imaging, analysis and processing.

  • ECCV (7) - Training-Based Spectral Reconstruction from a Single RGB Image
    Computer Vision – ECCV 2014, 2014
    Co-Authors: Rang M H Nguyen, Dilip K Prasad, Michael S Brown
    Abstract:

    This paper focuses on a training-based method to reconstruct a scene’s spectral reflectance from a single RGB Image captured by a camera with known spectral response. In particular, we explore a new strategy to use training Images to model the mapping between camera-specific RGB values and scene reflectance spectra. Our method is based on a radial basis function network that leverages RGB white-balancing to normalize the scene illumination to recover the scene reflectance. We show that our method provides the best result against three state-of-art methods, especially when the tested illumination is not included in the training stage. In addition, we also show an effective approach to recover the spectral illumination from the reconstructed spectral reflectance and RGB Image. As a part of this work, we present a newly captured, publicly available, data set of hyperspectral Images that are useful for addressing problems pertaining to spectral imaging, analysis and processing.

Manish Kumar - One of the best experts on this subject based on the ideXlab platform.

  • A new RGB Image encryption using generalized Vigenére-type table over symmetric group associated with virtual planet domain
    Multimedia Tools and Applications, 2019
    Co-Authors: Manish Kumar, R. N. Mohapatra, Sajal Agarwal, G. Sathish
    Abstract:

    The primary aim of this paper is to provide an efficient encryption algorithm for RGB Images. A new , fast , and secure RGB Image encryption algorithm using generalized Vigenére table over the symmetric group S n $S_{n}$ associated with Virtual Planet Domain (VPD) is proposed. Also a new method to generate random key space using generalized Vigenére cipher is introduced. Randomness of the proposed key space has been verified by using NIST statistical test suite. A formula for the key space has also been obtained and it is shown that this key space resists brute force attack. The VPD has been designed to encode RGB Image into VPD, which provides a fine interlacing among binary bit for each pixel. The proposed algorithm has been tested on standard RGB Images. Robustness of the proposed algorithm has been successfully verified by using commonly known attacks (such as, differential, cropped, and noise, entropy attacks). Finally, the proposed technique has been compared with other existing algorithms and the data (shown in tables) confirm that the proposed algorithm is competitive and can resist exhaustive attacks efficiently.

  • A new RGB Image encryption using generalized Vigenére-type table over symmetric group associated with virtual planet domain
    Multimedia Tools and Applications, 2018
    Co-Authors: Manish Kumar, R. N. Mohapatra, Sajal Agarwal, G. Sathish, S. N. Raw
    Abstract:

    The primary aim of this paper is to provide an efficient encryption algorithm for RGB Images. A new, fast, and secure RGB Image encryption algorithm using generalized Vigenere table over the symmetric group $S_{n}$ associated with Virtual Planet Domain (VPD) is proposed. Also a new method to generate random key space using generalized Vigenere cipher is introduced. Randomness of the proposed key space has been verified by using NIST statistical test suite. A formula for the key space has also been obtained and it is shown that this key space resists brute force attack. The VPD has been designed to encode RGB Image into VPD, which provides a fine interlacing among binary bit for each pixel. The proposed algorithm has been tested on standard RGB Images. Robustness of the proposed algorithm has been successfully verified by using commonly known attacks (such as, differential, cropped, and noise, entropy attacks). Finally, the proposed technique has been compared with other existing algorithms and the data (shown in tables) confirm that the proposed algorithm is competitive and can resist exhaustive attacks efficiently.

  • a new RGB Image encryption algorithm based on dna encoding and elliptic curve diffie hellman cryptography
    Signal Processing, 2016
    Co-Authors: Manish Kumar, Akhlad Iqbal, Pranjal Kumar
    Abstract:

    With the increasing use of media in communications, there is a need for Image encryption for security against attacks. In this paper, we have proposed a new algorithm for Image security using Elliptic Curve Cryptography (ECC) diversified with DNA encoding. The algorithm first encodes the RGB Image using DNA encoding followed by asymmetric encryption based on Elliptic Curve Diffie-Hellman Encryption (ECDHE). The proposed algorithm is applied on standard test Images for analysis. The analysis is performed on key spaces, key sensitivity, and statistical analysis. The results of the analysis conclude that the proposed algorithm can resist exhaustive attacks and is apt for practical applications. HighlightsA robust Image encryption algorithm is proposed based on DNA and ECDHE.No need for biological DNA expriments.The constructed key space is designed to provide the users' with high level of security.

  • An interlaced secure algorithm for RGB Image encryption in wavelet packet domain
    International Journal of Wavelets Multiresolution and Information Processing, 2016
    Co-Authors: Manish Kumar, Kashyap L. S. J. Josyula
    Abstract:

    We propose a secure interlaced algorithm for RGB Image encryption associated with Arithmetic Random Matrix Affine Cipher (ARMAC) in wavelet packet domain. In this approach, the arrangement of ARMAC parameters along with correct de-interlacing is mandatory for correct decryption. Computer simulation with standard example and result (security analysis) is given to analyze the capability and robustness of the proposed approach and comparison with existing methods are drawn. We have designed a highly secure algorithm wherein an RGB Image can be encrypted with varied computational cost depending on the user, enabling real-time Image encryption. Moreover, the proposed approach can be used in transmission of Images over unsecured network.

  • an RGB Image encryption using diffusion process associated with chaotic map
    Workshop on Information Security Applications, 2015
    Co-Authors: Manish Kumar, Pradeep Powduri, Avinash Reddy
    Abstract:

    Image encryption and decryption are essential for securing Images from various types of security attacks. In this paper, we have proposed a new algorithm for RGB Image encryption and decryption using diffusion method with a combination of chaotic maps. We have formulated a new algorithm for the entire possible range to choose keys for encrypting and decrypting RGB Image. Computer simulation with two standard examples and results are given to analyse the capability of the proposed approach. Several important analysis like key space, key sensitivity, NPCR, UACI, MSE and PSNR analysis are performed. Results of various analysis and computer simulation confirm that the new algorithm offers high security and is suitable for practical Image encryption.

Dilip K Prasad - One of the best experts on this subject based on the ideXlab platform.

  • training based spectral reconstruction from a single RGB Image
    European Conference on Computer Vision, 2014
    Co-Authors: Rang M H Nguyen, Dilip K Prasad, Michael S Brown
    Abstract:

    This paper focuses on a training-based method to reconstruct a scene’s spectral reflectance from a single RGB Image captured by a camera with known spectral response. In particular, we explore a new strategy to use training Images to model the mapping between camera-specific RGB values and scene reflectance spectra. Our method is based on a radial basis function network that leverages RGB white-balancing to normalize the scene illumination to recover the scene reflectance. We show that our method provides the best result against three state-of-art methods, especially when the tested illumination is not included in the training stage. In addition, we also show an effective approach to recover the spectral illumination from the reconstructed spectral reflectance and RGB Image. As a part of this work, we present a newly captured, publicly available, data set of hyperspectral Images that are useful for addressing problems pertaining to spectral imaging, analysis and processing.

  • ECCV (7) - Training-Based Spectral Reconstruction from a Single RGB Image
    Computer Vision – ECCV 2014, 2014
    Co-Authors: Rang M H Nguyen, Dilip K Prasad, Michael S Brown
    Abstract:

    This paper focuses on a training-based method to reconstruct a scene’s spectral reflectance from a single RGB Image captured by a camera with known spectral response. In particular, we explore a new strategy to use training Images to model the mapping between camera-specific RGB values and scene reflectance spectra. Our method is based on a radial basis function network that leverages RGB white-balancing to normalize the scene illumination to recover the scene reflectance. We show that our method provides the best result against three state-of-art methods, especially when the tested illumination is not included in the training stage. In addition, we also show an effective approach to recover the spectral illumination from the reconstructed spectral reflectance and RGB Image. As a part of this work, we present a newly captured, publicly available, data set of hyperspectral Images that are useful for addressing problems pertaining to spectral imaging, analysis and processing.

Radu Timofte - One of the best experts on this subject based on the ideXlab platform.

  • NTIRE 2020 Challenge on Spectral Reconstruction from an RGB Image.
    arXiv: Image and Video Processing, 2020
    Co-Authors: Boaz Arad, Radu Timofte, Ohad Ben-shahar, Yi-tun Lin, Graham D. Finlayson, Shai Givati
    Abstract:

    This paper reviews the second challenge on spectral reconstruction from RGB Images, i.e., the recovery of whole-scene hyperspectral (HS) information from a 3-channel RGB Image. As in the previous challenge, two tracks were provided: (i) a "Clean" track where HS Images are estimated from noise-free RGBs, the RGB Images are themselves calculated numerically using the ground-truth HS Images and supplied spectral sensitivity functions (ii) a "Real World" track, simulating capture by an uncalibrated and unknown camera, where the HS Images are recovered from noisy JPEG-compressed RGB Images. A new, larger-than-ever, natural hyperspectral Image data set is presented, containing a total of 510 HS Images. The Clean and Real World tracks had 103 and 78 registered participants respectively, with 14 teams competing in the final testing phase. A description of the proposed methods, alongside their challenge scores and an extensive evaluation of top performing methods is also provided. They gauge the state-of-the-art in spectral reconstruction from an RGB Image.

  • ICCV Workshops - Towards Spectral Estimation from a Single RGB Image in the Wild
    2019 IEEE CVF International Conference on Computer Vision Workshop (ICCVW), 2019
    Co-Authors: Berk Kaya, Yigit Baran Can, Radu Timofte
    Abstract:

    In contrast to the current literature, we address the problem of estimating the spectrum from a single common trichromatic RGB Image obtained under unconstrained settings (e.g. unknown camera parameters, unknown scene radiance, unknown scene contents). For this we use a reference spectrum as provided by a hyperspectral Image camera, and propose efficient deep learning solutions for sensitivity function estimation and spectral reconstruction from a single RGB Image. We further expand the concept of spectral reconstruction such that to work for RGB Images taken in the wild and propose a solution based on a convolutional network conditioned on the estimated sensitivity function. Besides the proposed solutions, we study also generic and sensitivity specialized models and discuss their limitations. We achieve state-of-the-art competitive results on the standard example-based spectral reconstruction benchmarks: ICVL, CAVE and NUS. Moreover, our experiments show that, for the first time, accurate spectral estimation from a single RGB Image in the wild is within our reach.

  • Towards Spectral Estimation from a Single RGB Image in the Wild
    arXiv: Computer Vision and Pattern Recognition, 2018
    Co-Authors: Berk Kaya, Yigit Baran Can, Radu Timofte
    Abstract:

    In contrast to the current literature, we address the problem of estimating the spectrum from a single common trichromatic RGB Image obtained under unconstrained settings (e.g. unknown camera parameters, unknown scene radiance, unknown scene contents). For this we use a reference spectrum as provided by a hyperspectral Image camera, and propose efficient deep learning solutions for sensitivity function estimation and spectral reconstruction from a single RGB Image. We further expand the concept of spectral reconstruction such that to work for RGB Images taken in the wild and propose a solution based on a convolutional network conditioned on the estimated sensitivity function. Besides the proposed solutions, we study also generic and sensitivity specialized models and discuss their limitations. We achieve state-of-the-art competitive results on the standard example-based spectral reconstruction benchmarks: ICVL, CAVE, NUS and NTIRE. Moreover, our experiments show that, for the first time, accurate spectral estimation from a single RGB Image in the wild is within our reach.