Image Comparisson using CBIR and OCR -


working on project retrieving content given image , compare other images in repository , list out matching images.

what should right approach search wont slowdown eventually.

what planning first level of filtering use image querying (cbir technique) retrieve images matching pattern of given image. ocr image content , match check.

please let me know if there better approach this.

steps done

softwares 1. tesseract ocr 2. image magick - image cleaning 3. textcleaner script

  1. found out image orientation using image magick software

    • convert package has feature find image orientation using exif data not useful.
    • for image rotated 90 degree thrice , ocr data each compared other find correct orientation. ( image maximum number of words wins)
  2. ocred image text , applied filtering bill no, date , amount.

    • on success stores details on db future search
    • on failure
      • created 10 different images different filters (gray scale mode , sharpment applied)
      • ocred images , found out required data form data got.
  3. saved data used future search feature eradicate duplication


Comments

Popular posts from this blog

c# - Binding a comma separated list to a List<int> in asp.net web api -

Delphi 7 and decode UTF-8 base64 -

html - Is there any way to exclude a single element from the style? (Bootstrap) -