GPGPU based implementation of a high performing No Reference (NR) - IQA algorithm, BLIINDS-II

Aman Yadav, Sohum Sohoni, Damon Chandler

    Research output: Contribution to journalConference article

    2 Citations (Scopus)

    Abstract

    A relatively recent thrust in IQA research has focused on estimating the quality of a distorted image without access to the original (reference) image. Algorithms for this so-called no-reference IQA (NR IQA) have made great strides over the last several years, with some NR algorithms rivaling full-reference algorithms in terms of prediction accuracy. However, there still remains a large gap in terms of runtime performance; NR algorithms remain significantly slower than FR algorithms, owing largely to their reliance on natural-scene statistics and other ensemble-based computations. To address this issue, this paper presents a GPGPU implementation, using NVIDIA's CUDA platform, of the popular Blind Image Integrity Notator using DCT Statistics (BLIINDS-II) algorithm [8], a state of the art NR-IQA algorithm. We copied the image over to the GPU and performed the DCT and the statistical modeling using the GPU. These operations, for each 5×5 pixel window, are executed in parallel. We evaluated the implementation by using NVIDIA Visual Profiler, and we compared the implementation to a previously optimized CPU C++ implementation. By employing suitable optimizations on code, we were able to reduce the runtime for each 512×512 image from approximately 270 ms down to approximately 9 ms, which includes the time for all data transfers across PCIe bus. We discuss our unique implementation of BLIINDS-II designed specifically for use on the GPU, the insights gained from the runtime analyses, and how the GPGPU techniques developed here can be adapted for use in other NR IQA algorithms.

    Original languageEnglish (US)
    Pages (from-to)21-25
    Number of pages5
    JournalIS and T International Symposium on Electronic Imaging Science and Technology
    VolumePart F130046
    DOIs
    StatePublished - Jan 1 2017

    Fingerprint

    discrete cosine transform
    integrity
    Statistics
    statistics
    Data transfer
    thrust
    Program processors
    estimating
    platforms
    Pixels
    pixels
    optimization
    predictions

    ASJC Scopus subject areas

    • Computer Graphics and Computer-Aided Design
    • Computer Science Applications
    • Human-Computer Interaction
    • Software
    • Electrical and Electronic Engineering
    • Atomic and Molecular Physics, and Optics

    Cite this

    GPGPU based implementation of a high performing No Reference (NR) - IQA algorithm, BLIINDS-II. / Yadav, Aman; Sohoni, Sohum; Chandler, Damon.

    In: IS and T International Symposium on Electronic Imaging Science and Technology, Vol. Part F130046, 01.01.2017, p. 21-25.

    Research output: Contribution to journalConference article

    @article{020759952a934ed69ddcd0cadb4d3fcd,
    title = "GPGPU based implementation of a high performing No Reference (NR) - IQA algorithm, BLIINDS-II",
    abstract = "A relatively recent thrust in IQA research has focused on estimating the quality of a distorted image without access to the original (reference) image. Algorithms for this so-called no-reference IQA (NR IQA) have made great strides over the last several years, with some NR algorithms rivaling full-reference algorithms in terms of prediction accuracy. However, there still remains a large gap in terms of runtime performance; NR algorithms remain significantly slower than FR algorithms, owing largely to their reliance on natural-scene statistics and other ensemble-based computations. To address this issue, this paper presents a GPGPU implementation, using NVIDIA's CUDA platform, of the popular Blind Image Integrity Notator using DCT Statistics (BLIINDS-II) algorithm [8], a state of the art NR-IQA algorithm. We copied the image over to the GPU and performed the DCT and the statistical modeling using the GPU. These operations, for each 5×5 pixel window, are executed in parallel. We evaluated the implementation by using NVIDIA Visual Profiler, and we compared the implementation to a previously optimized CPU C++ implementation. By employing suitable optimizations on code, we were able to reduce the runtime for each 512×512 image from approximately 270 ms down to approximately 9 ms, which includes the time for all data transfers across PCIe bus. We discuss our unique implementation of BLIINDS-II designed specifically for use on the GPU, the insights gained from the runtime analyses, and how the GPGPU techniques developed here can be adapted for use in other NR IQA algorithms.",
    author = "Aman Yadav and Sohum Sohoni and Damon Chandler",
    year = "2017",
    month = "1",
    day = "1",
    doi = "10.2352/ISSN.2470-1173.2017.12.IQSP-220",
    language = "English (US)",
    volume = "Part F130046",
    pages = "21--25",
    journal = "IS and T International Symposium on Electronic Imaging Science and Technology",
    issn = "2470-1173",

    }

    TY - JOUR

    T1 - GPGPU based implementation of a high performing No Reference (NR) - IQA algorithm, BLIINDS-II

    AU - Yadav, Aman

    AU - Sohoni, Sohum

    AU - Chandler, Damon

    PY - 2017/1/1

    Y1 - 2017/1/1

    N2 - A relatively recent thrust in IQA research has focused on estimating the quality of a distorted image without access to the original (reference) image. Algorithms for this so-called no-reference IQA (NR IQA) have made great strides over the last several years, with some NR algorithms rivaling full-reference algorithms in terms of prediction accuracy. However, there still remains a large gap in terms of runtime performance; NR algorithms remain significantly slower than FR algorithms, owing largely to their reliance on natural-scene statistics and other ensemble-based computations. To address this issue, this paper presents a GPGPU implementation, using NVIDIA's CUDA platform, of the popular Blind Image Integrity Notator using DCT Statistics (BLIINDS-II) algorithm [8], a state of the art NR-IQA algorithm. We copied the image over to the GPU and performed the DCT and the statistical modeling using the GPU. These operations, for each 5×5 pixel window, are executed in parallel. We evaluated the implementation by using NVIDIA Visual Profiler, and we compared the implementation to a previously optimized CPU C++ implementation. By employing suitable optimizations on code, we were able to reduce the runtime for each 512×512 image from approximately 270 ms down to approximately 9 ms, which includes the time for all data transfers across PCIe bus. We discuss our unique implementation of BLIINDS-II designed specifically for use on the GPU, the insights gained from the runtime analyses, and how the GPGPU techniques developed here can be adapted for use in other NR IQA algorithms.

    AB - A relatively recent thrust in IQA research has focused on estimating the quality of a distorted image without access to the original (reference) image. Algorithms for this so-called no-reference IQA (NR IQA) have made great strides over the last several years, with some NR algorithms rivaling full-reference algorithms in terms of prediction accuracy. However, there still remains a large gap in terms of runtime performance; NR algorithms remain significantly slower than FR algorithms, owing largely to their reliance on natural-scene statistics and other ensemble-based computations. To address this issue, this paper presents a GPGPU implementation, using NVIDIA's CUDA platform, of the popular Blind Image Integrity Notator using DCT Statistics (BLIINDS-II) algorithm [8], a state of the art NR-IQA algorithm. We copied the image over to the GPU and performed the DCT and the statistical modeling using the GPU. These operations, for each 5×5 pixel window, are executed in parallel. We evaluated the implementation by using NVIDIA Visual Profiler, and we compared the implementation to a previously optimized CPU C++ implementation. By employing suitable optimizations on code, we were able to reduce the runtime for each 512×512 image from approximately 270 ms down to approximately 9 ms, which includes the time for all data transfers across PCIe bus. We discuss our unique implementation of BLIINDS-II designed specifically for use on the GPU, the insights gained from the runtime analyses, and how the GPGPU techniques developed here can be adapted for use in other NR IQA algorithms.

    UR - http://www.scopus.com/inward/record.url?scp=85041529649&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=85041529649&partnerID=8YFLogxK

    U2 - 10.2352/ISSN.2470-1173.2017.12.IQSP-220

    DO - 10.2352/ISSN.2470-1173.2017.12.IQSP-220

    M3 - Conference article

    AN - SCOPUS:85041529649

    VL - Part F130046

    SP - 21

    EP - 25

    JO - IS and T International Symposium on Electronic Imaging Science and Technology

    JF - IS and T International Symposium on Electronic Imaging Science and Technology

    SN - 2470-1173

    ER -