Iconic Search: Visual Image Retrieval by Sample Selection

DSpace Repository

Iconic Search: Visual Image Retrieval by Sample Selection

Show full item record

Files for download

Iconic Search- ...

Simple item record

Publication 2-year master student thesis
Title Iconic Search: Visual Image Retrieval by Sample Selection
Author(s) Bouhendi, Nafiseh
Date 2012
English abstract
The considerable growth of digital images online in recent years has shifted users’ concern from whether or not an image is available to how to find a specific image in a sea of online imagery. Image Search Engines cannot satisfy every user, especially users that require specific images with more details. Furthermore, the variety and quantity of available images do not add value for users if they cannot find what they require in an appropriate timeframe. Therefore, an Image Retrieval is required that lets users define detailed search perimeters and find images that match their requirements. This thesis focuses on providing better communication and interaction between users and Image Search Engines. The work presented here aims to let users describe their requirements visually and make approximations of the images that they require by setting perimeters like color, scale and position. This approximation can help in retrieving more appropriate images which more closely match users’ needs. This thesis also proposes to involve users first in improving the Image Search Engine database by uploading their photographs and images, and second in helping other users that are not satisfied with search results, by sending an image as response to their request. To achieve this goal, the thesis applied two methodologies, Research through Design and User Centered Design. These methodologies allowed considering future possibilities and users’ requirements. The communication with users provided by low-fidelity and high-fidelity prototypes as sketches, that were used in workshops and helped in framing the concept and improving different aspects of it.
Publisher Malmö högskola/Kultur och samhälle
Pages 92
Language eng (iso)
Subject(s) Iconic
Image Search
Image Retrieval
Handle http://hdl.handle.net/2043/14414 (link to this page)

This item appears in the following Collection(s)

Show full item record



My Account