Khmer OCR
Transcript of Khmer OCR
![Page 1: Khmer OCR](https://reader035.fdocuments.us/reader035/viewer/2022062220/555a401bd8b42a83368b4fbb/html5/thumbnails/1.jpg)
1
Khmer OCR
LONG SeangmengLecturer and researcher, GIC - ITC
BarCamp 22nd September, 2012
![Page 2: Khmer OCR](https://reader035.fdocuments.us/reader035/viewer/2022062220/555a401bd8b42a83368b4fbb/html5/thumbnails/2.jpg)
2
Khmer OCR
• What is OCR?• Khmer OCR Project• State of the Art• Khmer OCR System• Project status• Perspectives
![Page 3: Khmer OCR](https://reader035.fdocuments.us/reader035/viewer/2022062220/555a401bd8b42a83368b4fbb/html5/thumbnails/3.jpg)
3
Optical Character Recognition (OCR)
OCR
Text Image
Editable Text
![Page 4: Khmer OCR](https://reader035.fdocuments.us/reader035/viewer/2022062220/555a401bd8b42a83368b4fbb/html5/thumbnails/4.jpg)
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
![Page 5: Khmer OCR](https://reader035.fdocuments.us/reader035/viewer/2022062220/555a401bd8b42a83368b4fbb/html5/thumbnails/5.jpg)
5
State of the ArtAuthor Limitation Result
CHEY Chanoeurn, KOSIN Chamnongthai and PINIT Kumhom
10 characters (បពជកភណឃសវទ)
92%
CHEY Chanoeurn, KOSIN Chamnongthai and PINIT Kumhom
20 fonts 92.85% (size 22)91.66% (size 18)89.27% (size 12)
ING Leng Ieng and MUAZ Ahmed
Limon R1 22 98.88%
KRUY Vanna Font and size independent(manual preparation for new fonts)
97%
EN Sovann Font and size independent(manual preparation for new fonts)
96%
![Page 6: Khmer OCR](https://reader035.fdocuments.us/reader035/viewer/2022062220/555a401bd8b42a83368b4fbb/html5/thumbnails/6.jpg)
Khmer OCR System
6
Pre processing
Segmentation
Recognition
Post processing
Text Image
Editable Text
សា លា �្ ក �្ ង �្ ភ ្�
សាលាក�ងភ��ពេពញនិ�ងសហជ�ព
![Page 7: Khmer OCR](https://reader035.fdocuments.us/reader035/viewer/2022062220/555a401bd8b42a83368b4fbb/html5/thumbnails/7.jpg)
7
Khmer OCR System (cont.)
• Pre processing Binarization
Noise removal
Skew detection and correction
![Page 8: Khmer OCR](https://reader035.fdocuments.us/reader035/viewer/2022062220/555a401bd8b42a83368b4fbb/html5/thumbnails/8.jpg)
8
Khmer OCR System (cont.)• Segmentation
Line
Vertical Symbol
Blob
Page
Line 1
Line 2
![Page 9: Khmer OCR](https://reader035.fdocuments.us/reader035/viewer/2022062220/555a401bd8b42a83368b4fbb/html5/thumbnails/9.jpg)
9
Khmer OCR System (cont.)• Recognition
Blob
Training images (sample images) with label
…
Blob to be recognized
Search for closest match
Closest match
Image:
Label: ក
![Page 10: Khmer OCR](https://reader035.fdocuments.us/reader035/viewer/2022062220/555a401bd8b42a83368b4fbb/html5/thumbnails/10.jpg)
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 transformThe 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]| + …
![Page 11: Khmer OCR](https://reader035.fdocuments.us/reader035/viewer/2022062220/555a401bd8b42a83368b4fbb/html5/thumbnails/11.jpg)
11
Khmer OCR System (cont.)• Post processing ឦ
ញAssembling
Blob
សា លា �្ ក �្ ង �្ ភ ្� ពេ្ ព ញ �្ និ ង
សា លា �្ក �្ ង �្ភ ្� ពេ្ព ញ �្និ ង
សាលា �្ក�ង�ភ�ពញ�និង
សាលាក�ងភ��ពេពញ
Reordering
ក��
ត្�ង ក�ង
ពេបស�
ភ��
របស�
Spell Checking
![Page 12: Khmer OCR](https://reader035.fdocuments.us/reader035/viewer/2022062220/555a401bd8b42a83368b4fbb/html5/thumbnails/12.jpg)
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
![Page 13: Khmer OCR](https://reader035.fdocuments.us/reader035/viewer/2022062220/555a401bd8b42a83368b4fbb/html5/thumbnails/13.jpg)
13
Perspectives• Joining characters• Text layout• Low quality text images• Curve line
![Page 14: Khmer OCR](https://reader035.fdocuments.us/reader035/viewer/2022062220/555a401bd8b42a83368b4fbb/html5/thumbnails/14.jpg)
14
Thanks for your attention!
Demo & Questions???