• DocumentCode
    238089
  • Title

    Distinctive feature mining based on varying threshold based image extraction for single and multiple objects

  • Author

    Sandhar, Rajwinder Kaur ; Phonsa, Gurbakash

  • Author_Institution
    Dept. of Comput. Sci. & Eng., Lovely Prof. Univ., Phagwara, India
  • fYear
    2014
  • fDate
    8-10 May 2014
  • Firstpage
    1537
  • Lastpage
    1541
  • Abstract
    Object extraction is important field of image processing. In this paper we will discuss about feature extraction and performance evaluation to detect object using varying threshold values. The fundamental concept of varying threshold and frequency based method provide a new aid to computer vision. This paper proposes a new object extraction varying threshold method with the combination of existing priori research paper method. Object extraction of a given image involves detection, feature extraction on the basis of area comparison of pixels, size, enrichment and mining. The purpose of this paper is to resolves the object extraction problems to some extent but still involve lots of tinkering problems, to point out the promising directions for future research.
  • Keywords
    data mining; feature extraction; image retrieval; image segmentation; object detection; computer vision; feature extraction; feature mining; frequency based method; image detection; image enrichment; image mining; image pixels; image processing; image size; multiple-objects; object detection; object extraction varying threshold method; performance evaluation; single-objects; varying threshold based image extraction method; Biomedical imaging; Face; Face recognition; Green products; Image edge detection; Image segmentation; Monitoring; Feature miningss; Image Extraction; MATLAB; Threshold Equation;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Advanced Communication Control and Computing Technologies (ICACCCT), 2014 International Conference on
  • Conference_Location
    Ramanathapuram
  • Print_ISBN
    978-1-4799-3913-8
  • Type

    conf

  • DOI
    10.1109/ICACCCT.2014.7019363
  • Filename
    7019363