Home | Bahasa | Sitemap | HelpDesk | UG-Pedia | Contact
Direktori UG : A - Z
Uzbek-Indonesian Joint International Conference, October 8-9, 2013  
Uzbek-Indonesian Joint International Conference On Economics And Management Toward Nation Character Development. Branch Of Russian Economic University After G.V.Plekhanov In Tashkent, Uzbekistan And ...

Indonesia Open Source Award 2012  
Indonesia Open Source Award (IOSA) 2012. For Further Information http://iosa.web.id/ ...

Home > Archive >
Thesis Defence of Doctoral in Information Technology Pipit Dewi A dan Yuli Karyanti

Information Technology Doctoral Program Gunadarma University held a Thesis Defence for Pipit Dewi Arnesia  and Yuli Karyanti on November 19, 2010 at Gunadarma University Auditorium, Campus D, Jl. Margonda Raya, Pondok Cina, Depok.
The first doctoral candidate was Pipit Dewi Arnesia who presented her dissertation with the title "Image Matching with Textual Document Through Image Processing and Text Mining". Doctoral candidate is guided by Prof. Dr. Sarifuddin Madenda as a promoter, Dr. Ernastuti and Dr. Ravi A. Salim as co-promoter.

In her presentation explained, this study merged the text and image retrieval based on content that is color, as a tool for building databases notation keywords and text or document, where this research adopted the MIRA (Multimedia Information Retrieval Application).

Based on the resukt of the text-based image retrieval using keyterm, it can be concluded the umage search is successfullydistributed, and so is color-based image retrieval. The developed system which is text and color-based image retrieval is capable og image searching which suit the hopes with optimal result.

Second session, a doctoral candidate who brought the Yuli Karyanti dissertation with the title 'Local Search Image Based on Texture Features'. Doctoral candidate is guided by prof. Dr. Sarifuddin Madenda as a promoter, and Dr. Dr.Lussiana ETP. Eri Prasetyo Wibowo as co-promoter.

In her presentation explained, this study developed an extraction method with dynamic reorganization approach to overcome the problem of texture methods. With this method, a different texture from one region to another region can be described diektraksi and optimally. In this test using 999 texture images taken from Brodatz database. As a comparison of the systems developed, used recognizable image retrieval systems that exist on site, as well as a survey conducted by 10 respondents. The results show that the system is developed using dynamic reorganization is better than the familiar image retrieval system on site and more in line with the perception of respondents.

Expected from the results of these study can contribute and benefit theoretically and technology development.