Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.
Khmer OCR           BarCamp     22nd September, 2012        LONG SeangmengLecturer and researcher, GIC - ITC     seangmeng...
Khmer OCR•   What is OCR?•   Khmer OCR Project•   State of the Art•   Khmer OCR System•   Project status•   Perspectives  ...
Optical Character Recognition (OCR) Text Image                  OCR  Editable Text                                      3
Khmer OCR Project• 2011• Team  –   Dr. SENG Sopheap, ITC  –   Mr. LONG Seangmeng, ITC5th  –   Mr. EN Sovann (doing master)...
State of the ArtAuthor                   Limitation                  ResultCHEY Chanoeurn, KOSIN    10 characters (បបបបប  ...
Khmer OCR System  Text ImagePre processingSegmentation Recognition                  សស ស ស សសស ស ស                      ស ...
Khmer OCR System (cont.)• Pre processing                        Binarization                        Noise removal         ...
Khmer OCR System (cont.)• Segmentation                       Page                   Line 1        Line                   L...
Khmer OCR System (cont.) • Recognition            Blob                              Training images (sample images) with l...
Khmer OCR System (cont.)• Recognition (cont.)   – How to find closest match?   – How to represent the blob image?       • ...
Khmer OCR System (cont.)• Post processing                        ស                                               Assemblin...
Project status• Pre processing   – Binarization and noise removal √   – Skew detection and correction X• Segmentation √• R...
Perspectives•   Joining characters•   Text layout•   Low quality text images•   Curve line                                13
Thanks for your attention! Demo & Questions???                             14
Upcoming SlideShare
Loading in …5
×

Khmer OCR

2,245 views

Published on

Khmer OCR

  1. 1. Khmer OCR BarCamp 22nd September, 2012 LONG SeangmengLecturer and researcher, GIC - ITC seangmeng@itc.edu.kh 1
  2. 2. Khmer OCR• What is OCR?• Khmer OCR Project• State of the Art• Khmer OCR System• Project status• Perspectives 2
  3. 3. Optical Character Recognition (OCR) Text Image OCR Editable Text 3
  4. 4. Khmer OCR Project• 2011• Team – Dr. SENG Sopheap, ITC – Mr. LONG Seangmeng, ITC5th – Mr. EN Sovann (doing master) – Ms. PRUM Sophea (doing PhD) – Mr. HAO Jeudi (year)• Develop a Khmer OCR system – Font independent – Size independent 4
  5. 5. State of the ArtAuthor Limitation ResultCHEY Chanoeurn, KOSIN 10 characters (បបបបប បបបប 92%Chamnongthai and PINIT ប)KumhomCHEY Chanoeurn, KOSIN 20 fonts 92.85% (size 22)Chamnongthai and PINIT 91.66% (size 18)Kumhom 89.27% (size 12)ING Leng Ieng and MUAZ Limon R1 22 98.88%AhmedKRUY Vanna Font and size independent 97% (manual preparation for new fonts)EN Sovann Font and size independent 96% (manual preparation for new fonts) 5
  6. 6. Khmer OCR System Text ImagePre processingSegmentation Recognition សស ស ស សសស ស ស ស ស សសPost processing Editable Text ស ស ស ស ស ស ស ស ស ស ស ស ស ស ស ស ស ស ស ស ស ស ស ស 6
  7. 7. Khmer OCR System (cont.)• Pre processing Binarization Noise removal Skew detection and correction 7
  8. 8. Khmer OCR System (cont.)• Segmentation Page Line 1 Line Line 2 Vertical Symbol Blob 8
  9. 9. Khmer OCR System (cont.) • Recognition Blob Training images (sample images) with label Closest matchBlob to be recognized Image: Search for closest Label: ស match … 9
  10. 10. Khmer OCR System (cont.)• Recognition (cont.) – How to find closest match? – How to represent the blob image? • Fourier transform: Any function f(t) with period T can be written as Blob image => 2-D Fourier transform The blob image (B) represented by Fourier coefficients: B[0], B[1], B[2], … City block distance between two blobs B and B’: Distance = |B[0] – B’[0]| + |B[1] – B’[1]| + |B[2] – B’[2]| + … 10
  11. 11. Khmer OCR System (cont.)• Post processing ស Assembling ស Blob ស ស ស ស ស ស ស ស សស សស ស ស ស ស សស ស ស ស ស ស ស ស ស ស ស ស ស ស ស ស ស ស ស Reordering ស ស ស ស ស ស ស ស ស សស ស ស ស ស ស សស ស ស ស ស ស ស ស ស ស ស ស ស ស ស ស ស ស ស ស ស ស ស ស ស ស ស ស ស ស ស ស ស ស ស ស Spell Checking ស ស ស ស ស ស ស ស 11
  12. 12. Project status• Pre processing – Binarization and noise removal √ – Skew detection and correction X• Segmentation √• Recognition – Features extraction √ – Automatic generation of training data for new fonts √• Post processing – Assembling and reordering rules • Manual √ • Automatic X – Spell checking X• Performance evaluation X 12
  13. 13. Perspectives• Joining characters• Text layout• Low quality text images• Curve line 13
  14. 14. Thanks for your attention! Demo & Questions??? 14

×