Corpus ID: 214693119

Assessing Image Quality Issues for Real-World Problems

@article{Chiu2020AssessingIQ,
  title={Assessing Image Quality Issues for Real-World Problems},
  author={Tai-Yin Chiu and Yinan Zhao and Danna Gurari},
  journal={ArXiv},
  year={2020},
  volume={abs/2003.12511}
}
  • Tai-Yin Chiu, Yinan Zhao, Danna Gurari
  • Published 2020
  • Computer Science
  • ArXiv
  • We introduce a new large-scale dataset that links the assessment of image quality issues to two practical vision tasks: image captioning and visual question answering. First, we identify for 39,181 images taken by people who are blind whether each is sufficient quality to recognize the content as well as what quality flaws are observed from six options. These labels serve as a critical foundation for us to make the following contributions: (1) a new problem and algorithms for deciding whether… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 59 REFERENCES

    Waterloo Exploration Database: New Challenges for Image Quality Assessment Models

    VIEW 2 EXCERPTS

    Making a “Completely Blind” Image Quality Analyzer

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    NIMA: Neural Image Assessment

    A Statistical Evaluation of Recent Full Reference Image Quality Assessment Algorithms

    VIEW 6 EXCERPTS
    HIGHLY INFLUENTIAL

    Massive Online Crowdsourced Study of Subjective and Objective Picture Quality

    VIEW 11 EXCERPTS
    HIGHLY INFLUENTIAL

    CIDEr: Consensus-based image description evaluation

    VIEW 1 EXCERPT

    Deep Neural Networks for No-Reference and Full-Reference Image Quality Assessment

    VIEW 7 EXCERPTS
    HIGHLY INFLUENTIAL

    Image quality assessment: from error visibility to structural similarity

    VIEW 6 EXCERPTS
    HIGHLY INFLUENTIAL

    VizWiz Grand Challenge: Answering Visual Questions from Blind People

    VIEW 10 EXCERPTS