Evaluation of content based image retrieval (CBIR) system using precision measure /

Content based image retrieval (CBIR) is an application of the computer system for image retrieval, where it will aid searching for digital images in a large database. CBIR operates on a totally different principle from keyword indexing. Content based means that the search will analyze the actual con...

Full description

Saved in:
Bibliographic Details
Main Author: Siti Aishah Kamaliah Mohamed
Format: Thesis
Language:English
Published: Kuala Lumpur : Kulliyyah of Information and Communication Technology, International Islamic University Malaysia, 2015
Subjects:
Online Access:http://studentrepo.iium.edu.my/handle/123456789/5371
Tags: Add Tag
No Tags, Be the first to tag this record!
LEADER 030080000a22003250004500
008 151209t2015 my a g m 000 0 eng d
040 |a UIAM  |b eng 
041 |a eng 
043 |a a-my--- 
050 0 0 |a TA1637 
100 0 |a Siti Aishah Kamaliah Mohamed  |9 60305 
245 1 |a Evaluation of content based image retrieval (CBIR) system using precision measure /  |c bySiti Aishah Kamaliah Mohamed 
260 |a Kuala Lumpur :  |b Kulliyyah of Information and Communication Technology, International Islamic University Malaysia,  |c 2015 
300 |a xii, 69 leaves :  |b ill. ;  |c 30cm. 
336 |2 rdacontent 
337 |2 rdamedia 
338 |2 rdacarrier 
502 |a Thesis (MLIS)--International Islamic University Malaysia, 2015. 
504 |a Includes bibliographical references (leaves 58-68). 
520 |a Content based image retrieval (CBIR) is an application of the computer system for image retrieval, where it will aid searching for digital images in a large database. CBIR operates on a totally different principle from keyword indexing. Content based means that the search will analyze the actual content of an image, which will be done automatically by the system, where the cost and time will be reduced greatly. The study sets out to assess the retrieval performance of a CBIR system with regards to the users' evaluation and precision measure and was modelled after Cranfield Test by Cleverdon. To collect the queries and relevance criteria used during the searching activities, a semi structured interview was carried out where two users from different professional backgrounds; school teacher and graphic designer were interviewed. Users' relevance judgment of the retrieved images were collected and later used to calculate the precision values. The precision values measured were varied among the two users because their professional backgrounds reflected their final judgments of the relevance criteria and the retrieved images. The precision values differed greatly between the two users and the low precision values were indicated as a poor retrieval performance by Retrievr. In conclusion, Retrievr did an image clustering based on the focus in the image queries whereby queries with fewer objects are more accurately matched and retrieved. 
650 0 |a Image processing  |x Digital techniques 
655 7 |a Theses, IIUM local 
690 |a Dissertations, Academic  |x Department of Library and Information Science  |z IIUM  |9 2044 
710 2 |a International Islamic University Malaysia.  |b Department of Library and Information Science  |9 2046 
856 4 |u http://studentrepo.iium.edu.my/handle/123456789/5371 
900 |a aih-sbh-ls 
942 |2 lcc  |n 0 
999 |c 438294  |d 469952 
952 |0 0  |6 T TA 001637 S623E 2015  |7 0  |8 THESES  |9 760795  |a IIUM  |b IIUM  |c MULTIMEDIA  |g 0.00  |o t TA 1637 S623E 2015  |p 11100343417  |r 2017-10-20  |t 1  |v 0.00  |y THESIS 
952 |0 0  |6 TS CDF TA 1637 S623E 2015  |7 0  |8 THESES  |9 854050  |a IIUM  |b IIUM  |c MULTIMEDIA  |g 0.00  |o ts cdf TA 1637 S623E 2015  |p 11100343418  |r 2017-10-26  |t 1  |v 0.00  |y THESISDIG