The purpose of this thesis is to evaluate 7 different search strategies for content-based image retrieval with respect to retrieval effectiveness. The strategies are based on different levels of resolution implemented by the Haar transformation. The result of the study shows an improvement in both mean average precision and mean recall in strategies based on lower levels of resolution. / Uppsatsnivå: D

<p>Uppsatsen handlar om möjligheten till demokratisk bildindexering. Den traditionella intellektuella indexeringens representation av tolkande bildattribut och av aboutness brister. Hur skulle då användares egna bildbeskrivningar konstrueras och vilka aspekter av bilden skulle beskrivas? En experimentell metod har valts där 22 deltagare instruerats att skriva en bildtext, en innehållsbeskrivning och en beskrivning av upplevelsen av tre fotografier. Deltagarna beskrev bilderna med viss likhet i konstruktion oavsett bild. Detta pekar både på viss effekt av instruktionen men också på att de kan beskriva bilder och att beskrivningar kan samlas in. Viss samstämmighet i begreppsligt innehåll ger frågor om variationens värde vid bilders representation. Beskrivningarna skulle ge sökingångar till bildernas abstrakta och emotiva aspekter. Beskrivningarna utformas ofta som en story, vilket stödjer tidigare studiers upptäckta narrativitetsmönster.</p>

The aim of this master thesis is to evaluate the performance of the content-based image retrieval system ImBrowse from a semantic point of view. Evaluation of retrieval performance is a problem in content-based image retrieval (CBIR). There are many different methods for measuring the performance of content-based image retrieval systems, but no common way for performing the evaluation. The main focus is on image retrieval regarding the extraction of the visual features in the image, from three semantic levels. The thesis tries to elucidate the semantic gap, which is the problem when the systems extraction of the visual features from the image and the user’s interpretation of that same information do not correspond. The method of this thesis is based on similar methods in evaluation studies of CBIR systems. The thesis is an evaluation of ImBrowse’s feature descriptors for 30 topics at three semantic levels and compared the descriptors performance based on our relevance assessment. For the computation of the results the precision at DCV = 20 is used. The results are presented in tables and a chart. The conclusion from this evaluation is that the retrieval effectiveness from a general point of view did not meet the semantic level of our relevance assessed topics. However, since the thesis do not have another system with the same search functions to compare with it is difficult to draw a comprehensive conclusion of the results. / Uppsatsnivå: D

This essay explores to what extent the Swedish language version of Google Images meets the usability requirements of average everyday users. Previously published studies on user behaviour and users‟ interface and search option preferences define the usability requirements, which are matched against Google Images‟ actual interface and search options. The retrieval method of Google Images is also briefly discussed, and users‟ opinions about Google Images too, as they come across in the previously published user studies. The findings are that Google Images lack some of the things that users ask for, but it still seems to be the most used image search engine among average internet users and more appreciated than other search engines. Since the user studies were conducted, Google Images has changed its interface and added new options in a way that indicates that the developers have read and taken inspiration from the user-oriented image retrieval research, and still do so. This should mean that Google Images is even more user-oriented and therefore appreciated today, and it might improve even more in the near future.

Uppsatsen handlar om möjligheten till demokratisk bildindexering. Den traditionella intellektuella indexeringens representation av tolkande bildattribut och av aboutness brister. Hur skulle då användares egna bildbeskrivningar konstrueras och vilka aspekter av bilden skulle beskrivas? En experimentell metod har valts där 22 deltagare instruerats att skriva en bildtext, en innehållsbeskrivning och en beskrivning av upplevelsen av tre fotografier. Deltagarna beskrev bilderna med viss likhet i konstruktion oavsett bild. Detta pekar både på viss effekt av instruktionen men också på att de kan beskriva bilder och att beskrivningar kan samlas in. Viss samstämmighet i begreppsligt innehåll ger frågor om variationens värde vid bilders representation. Beskrivningarna skulle ge sökingångar till bildernas abstrakta och emotiva aspekter. Beskrivningarna utformas ofta som en story, vilket stödjer tidigare studiers upptäckta narrativitetsmönster.