(For USM Staff/Student Only)

EngLib USM > Ω School of Electrical & Electronic Engineering >

Image processing with artificial intelligence / Kenny Toh Kal Vin

Image processing with artificial intelligence_Kenny Toh Kal Vin _E3_2009_875004527_00003095348_NI
Digital imej dari pelbagai produk elektronik pengguna pada kebiasaannya akan mengalami kerosakan dari segi kualiti imej ketika proses pemerolehan, pengrekodan, dan penghantaran yang berpunca dari pelbagai ketidak-unggulan dalam pengesan, elemen penderia, serta gangguan persekitaran ketika dalam medium penghantaran. Untuk aplikasi pemprosesan imej, sebarang hingar yang mencemarkan imej perlulah dibaiki agar proses pemprosesan imej pada peringkat berikutan (seperti segmentasi imej, pengesanan pinggir dan sebagainya) dapat dilakukan dengan sempurna. Ini termasuk penapisan dedenyut yang hadir dalam imej digital. Terutama dalam penapisan hingar impuls, penuras-penuras yang menggunakan mekanisma median dapat menapis hingar impuls dengan baik. Di samping itu, terdapat sekumpulan penuras yang menggunakan prinsip sistem pintar (penuras-penuras FIRE) turut dapat menapis hingar impuls dengan memuaskan. Dalam projek ini, sejenis penuras baru untuk penapisan hingar impuls berdasarkan median dan logik kabur telah dicadangkan dan dibina. Penuras ini bukan setakat dapat menghilangkan hingar impuls, malah dapat mengekalkan struktur halus dan bentuk objek dalam imej. Di samping itu, algoritma penuras baru ini adalah mudah untuk dijanakan dan tidak memakan masa yang panjang ketika proses penapisan dijalankan. _________________________________________________________________________________________ Digital images acquired through many consumer electronics products are often corrupted by salt-and-pepper noise during image acquisition, recording and transmission due to a number of nonidealities encountered in image sensors, communication channels and external disturbance. In most image processing applications, it is of vital importance to remove the noise from the image data because the performance of subsequent image processing tasks such as edge detection, image segmentation and others. This includes the elimination of salt-and-pepper noise contained in the images and at the same time preserving the image integrity. Specifically for the removal of salt-and-pepper noise, the median-based filters have been chief in this regard. Besides, there is the class of fuzzy-inference ruled by else-action (FIRE) filters, employing soft computing techniques to filter salt-and-pepper noise. In this project, a new fuzzy switching median (FSM) filter utilizing fuzzy techniques in image processing is developed. The designed filter is able to remove salt-and-pepper noise in digital images while preserving image details and textures very well. By incorporating fuzzy reasoning in correcting the detected noisy pixel, the low complexity FSMfilter is able to outperform some well known existing salt-and-pepper noise fuzzy and classical filters.
Contributor(s):
Kenny Toh Kal Vin - Author
Primary Item Type:
Final Year Project
Identifiers:
Accession Number : 875004527
Language:
English
Subject Keywords:
Digital images; artificial intelligence; image degradation
First presented to the public:
4/1/2009
Original Publication Date:
10/2/2018
Previously Published By:
Universiti Sains Malaysia
Place Of Publication:
School of Electrical & Electronic Engineering
Citation:
Extents:
Number of Pages - 131
License Grantor / Date Granted:
  / ( View License )
Date Deposited
2018-10-02 15:07:25.969
Date Last Updated
2019-01-07 11:24:32.9118
Submitter:
Nor Hayati Ismail

All Versions

Thumbnail Name Version Created Date
Image processing with artificial intelligence / Kenny Toh Kal Vin1 2018-10-02 15:07:25.969