Friday, February 19, 2021

Optical character recognition system for Baybayin scripts using support vector machine

A new publishing related to SVM method on OCR case, "Optical character recognition system for Baybayin scripts using support vector machine" -  https://peerj.com/articles/cs-360/


Thanks for citation that to have more clearer that the method could work in some other cases.



This part is delight me and remind it back.




Abstract (of the paper)

 In 2018, the Philippine Congress signed House Bill 1022 declaring the Baybayin script as the Philippines’ national writing system. In this regard, it is highly probable that the Baybayin and Latin scripts would appear in a single document. In this work, we propose a system that discriminates the characters of both scripts. The proposed system considers the normalization of an individual character to identify if it belongs to Baybayin or Latin script and further classify them as to what unit they represent. This gives us four classification problems, namely: (1) Baybayin and Latin script recognition, (2) Baybayin character classification, (3) Latin character classification, and (4) Baybayin diacritical marks classification. To the best of our knowledge, this is the first study that makes use of Support Vector Machine (SVM) for Baybayin script recognition. This work also provides a new dataset for Baybayin, its diacritics, and Latin characters. Classification problems (1) and (4) use binary SVM while (2) and (3) apply the multiclass SVM classification. On average, our numerical experiments yield satisfactory results: (1) has 98.5% accuracy, 98.5% precision, 98.49% recall, and 98.5% F1 Score; (2) has 96.51% accuracy, 95.62% precision, 95.61% recall, and 95.62% F1 Score; (3) has 95.8% accuracy, 95.85% precision, 95.8% recall, and 95.83% F1 Score; and (4) has 100% accuracy, 100% precision, 100% recall, and 100% F1 Score.

Wednesday, July 22, 2020

i2ocr - Free Online Khmer OCR, It works!

i2OCR.com has provided Khmer OCR free for everyone to use, I have tested and got a good enough result, I can say around 95% is OK if it is the Khmer Unicode text.

I will try out sometimes on old Limon or ABC fonts, for handwriting text is not working.

So you may try when you need: http://www.i2ocr.com/free-online-khmer-ocr

The tool now is added into my list, Khmer Tools.



Sample testing


Sunday, November 24, 2019

Application of Support Vector Machine in Prediction Secondary Structure Protein

Application of Support Vector Machine in Prediction Secondary Structure Protein
NI Jabbar, RI Jabbar

This paper studying the predication of secondary structure protein from primary
structure protein using support vector machine (SVM). We classify 64 types of
proteins in three types: Helices (H), Strand (E) and Coil (C).


View Here.



Thanks for citation.

Monday, July 1, 2019

Wring Lunar Date in Khmer: Khmer Date Converter

Writing Lunar Date in Khmer is for all official documents using in Cambodia's government if you have noticed.

And of course, it is also a hardest one for other people who are not in government office as we are mostly not using Lunar calendar in private but when we need to use it, we always check Lunar calendar issued by corresponding organization.

Here is a help tool: https://tools.wikischool.asia/KhmerLunar

The tool helps for writing the correct date and in Khmer language.


If you find this useful and also want to continue engage with WikiSchool, reach them at facebook.

Updated (2021/02):
  • The tool unpublished for sometimes being, be back, will inform.

Wednesday, March 13, 2019

Tools That Will Help Writer in Khmer

KhmerWriters.com is a new tool, provided by Danh Hong who is always providing the support for Khmer language in computing.

Danh Hong was also the one who handle khmerocr.org which is now no longer maintenance and the domain is listed on sale already but this time, he comes again with another tool that will be very helpful for Khmer writers who mostly face issue such as: wrong Khmer spelling, typing without zero space (ZWSP).

Khmer Spelling Checker (with Auto correction)



You can just pass the text and click on check spelling (ពិនិត្យអក្ខរាវិរុទ្ធ) then click on the next buttn for auto correction (កែដោយស្វ័យប្រវត្តិ).



Auto Zero Space

The next action, you need to aware for Khmer writing is to provide zero space to handle justify alignment and well line breaking. Just click put ZWSP as on the screen, then you can check the result by passing to your word document, you will see the different as following:



Of course, when you use it some words might not well detected, this require more corpus to put at his side, so hope it will be soon more accurate but at this stage, you can also use.

Let's try and see, let me know in comment for your thought.

Do you think is it helpful for you?
If you find it's helpful, please also consider to donate to Danh Hong's team to continue his work.

Friday, July 27, 2018

Naming Transliteration Tool (Khmer to Latin/English)

I just see that there is a tool by NIPTITC institute to help writing Khmer name to Latin written, it is very useful for Cambodian people to write their name in Latin characters.


Example here, the name in Khmer is កុសល ចំរើន the tool provide 3 kinds of written :

  1. Character Model: e.g. KOSOL CHAMREUN
  2. Syllable Model: e.g. KOSOL CHAMRAEUN
  3. SMT Model(*): e.g. KOL CHAMROEUN

So if you are looking for the Khmer transliteration tool, I think this research r&d tool, you can try: http://rnd.niptict.edu.kh/tran/.

Remark:
(*) I don't really find a source of translation, I think "SMT" should stand for: Statistical Machine Translation which is in another research by this organization.

Thursday, April 12, 2018

Segmentation - New Zero Width Space (ZWSP) Online Tool - ondra.cf by Danh Hong

Thank Danh Hong who always be with Khmer Unicode solution from font design, OCR... and now segmentation tool: ondra.cf

Danh Hong's Tool for ZWSP


Online tool and even the API available tools are required for bushing more product related in Khmer.
Mostly I use tool from kheng.info as I've been listing them in my list as I can see both tools are great to have in the community and hope for heavy content organization will support them for continuous development.

kheng.info

I've tried out both tools to see the result, there are some points in yellow remark base on the text:
ondra.cf vs kheng.info

Of course, base on above highlight, it would be better when training data is enough but I could see Danh Hong's tool made correctly for numeric data, although requires more data training to correct some concrete words such as country names as example.

Anyway, the tool will help our community growing.

Thanks everyone for hard work and share to us.