APLIKASI TEKNIK PENCOCOKAN CITRA DENGAN PENDEKATAN METRIK DALAM SUATU BASIS DATA CITRA
<b>Abstract :</b><p align="justify"> <br /> Database application is provided in wide range applications based on information system technology, evolving from conventional database to multimedia database which handle several types of data such as image, audio, video...
Saved in:
Main Author: | |
---|---|
Format: | Theses |
Language: | Indonesia |
Online Access: | https://digilib.itb.ac.id/gdl/view/5346 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Institut Teknologi Bandung |
Language: | Indonesia |
Summary: | <b>Abstract :</b><p align="justify"> <br />
Database application is provided in wide range applications based on information system technology, evolving from conventional database to multimedia database which handle several types of data such as image, audio, video, text, numeric, handwritten etc. in one integrated database system. Images data comprise the vast majority of acquired and processed data for commercial and science researches.<p align="justify"> <br />
<br />
<br />
Applications used in image database for recognition, authentication or detection supported by image matching algorithm incorporated in the program. Visage matching technique has the capability to query the images from database by using the information attribute query (SQL) and query by image (content base retrieval).<p align="justify"> <br />
<br />
<br />
Multimedia database with visage matching computation in this research applies the image property comparison viz., the RGB values extracted from the pixel, for 24 bit each colour of ROB has value from zero to 255.<p align="justify"> <br />
<br />
<br />
Pocess to reduce the distorsion factors, by eliminating the disadvantage background using the ellipse boundary surrounded the face. This system extracts the image properties inside the ellipse, compared and perform the images with the minimum metric distance between the image query and the images stored in the database.<p align="justify"> <br />
<br />
<br />
The result of this research is the application of the image matching technique by using metric approach in image database with the ability to retrieve the similar images from the database. We expect, this research to be improved concerning to the accuracy and the robustness of the system to achieve the identification system to fulfill the commercial needs.<p align="justify"> <br />
<br />
|
---|