PRESENT A HIERARCHICAL STRUCTURE OF NEURAL NETWORK FOR PRINTED FARSI DOCUMENTS

Q: How can I download an article?

To download an article from SID, first log in to the site, search for the article title, and click on the 'Download Article' option.

Q: How can I download an ISI article?

To download an ISI article on SID, enter the keyword or article title in the search bar, view the relevant results, click on the desired article, and select the 'Download Article' option.

Q: How can I access the SID database?

To access the SID database, visit SID.ir, create an account, and log in to access scientific resources.

Q: Is downloading articles from SID free?

Some articles on SID are available for free, while others require payment. Details are specified on the article's page.

Bahmani Zahra; AZMI REZA

مرکز اطلاعات علمی Scientific Information Database (SID) - Trusted Source for Research and Academic Resources

Seminar Paper

Paper Information

Seminar: CONFERENCE ON RECENT RESEARCH IN SCIENCE AND TECHNOLOGY
Year:2020 | Issue:19

Download Full-Text

View:

144

Download:

Information Seminar Paper

Title

PRESENT A HIERARCHICAL STRUCTURE OF NEURAL NETWORK FOR PRINTED FARSI DOCUMENTS

Author(s)

Bahmani Zahra | AZMI REZA

Keywords

PRINTED DOCUMENTS RETRIEVAL

SUB LETTER

NEURAL NETWORK

Abstract

IN THIS PAPER, A NOVEL METHOD FOR PRINTED FARSI DOCUMENTS RETRIEVAL IS PROPOSED. HERE, USED OF A HIERARCHICAL STRUCTURE OF RBF NEURAL NETWORK. THE FEATURE VECTOR IS PROFILES IN FOUR STANDARD DIRECTIONS. SUB LETTERS ARE DIVIDED INTO FOUR CATEGORIES, FIRST, MIDDLE, END AND SINGLE ACCORDING TO THE POSITION OF THE SUB-LETTERS IN SUB WORDS. ONE RBF NN IS TRAINED FOR ANY CATEGORY. THE OUTPUT OF THE NEURAL NETWORK IS PROPORTIONAL TO THE NUMBER OF SUB-LETTERS OF EACH CATEGORY, AS WELL AS THE NUMBER OF MERGING SUB-LETTERS WITH HIGH INTERFERENCE. IN THE NEXT STEP, A NEURAL NETWORK IS TRAINED FOR EACH SUBGROUP THAT HAS BEEN MERGED. TO EVALUATE THE SYSTEM, 50 DOCUMENTS HAVE BEEN SCANNED AND AFTER THE PREPROCESSING STAGES, THE LINES AND WORDS HAVE BEEN EXTRACTED. THEN THE BODY OF THE WORDS IS EXTRACTED AND ARE SEPARATED TO SUB-LETTERS. PERCENT OF CORRECT SUB-LETTER RECOGNITION IS 99%.

Cites

No record.

References

No record.

Cite

APA: Copy

Bahmani, Zahra, & AZMI, REZA. (2020). PRESENT A HIERARCHICAL STRUCTURE OF NEURAL NETWORK FOR PRINTED FARSI DOCUMENTS. INTERNATIONAL CONFERENCE ON RECENT RESEARCH IN SCIENCE AND TECHNOLOGY. SID. https://sid.ir/paper/949491/en

Vancouver: Copy

Bahmani Zahra, AZMI REZA. PRESENT A HIERARCHICAL STRUCTURE OF NEURAL NETWORK FOR PRINTED FARSI DOCUMENTS. 2020. Available from: https://sid.ir/paper/949491/en

IEEE: Copy

Zahra Bahmani, and REZA AZMI, “PRESENT A HIERARCHICAL STRUCTURE OF NEURAL NETWORK FOR PRINTED FARSI DOCUMENTS,” presented at the INTERNATIONAL CONFERENCE ON RECENT RESEARCH IN SCIENCE AND TECHNOLOGY. 2020, [Online]. Available: https://sid.ir/paper/949491/en

Related Journal Papers

No record.

Related Seminar Papers

No record.

Related Plans

No record.

Recommended Workshops