Detta är ett uppsatsförslag hämtat från Nationella Exjobb-poolen. Klicka här för att komma tillbaka till samtliga exjobbsförslag.
Algorithm for similar query suggestion
Picsearch uses its own technology to crawl the web and to create a searchable index of family-friendly images.
You will develop a natural-language independent method based on query analysis for providing similar query suggestions in image search services. You will start with researching the algorithms described in the literature, in order to identify their strengths and weaknesses in the context of image search. Next you will propose and implement a program for building a database of similar queries, reusing existing components whenever possible, and accompanied with a look-up method to retrieve the similar queries. Finally you will compare your solution to alternatives in terms of quality and in terms of CPU / disk resource usage, if possible.
C++ programming is expected, experience with handling large data sets and the Linux operating system would be beneficial.
This thesis is intended for one or more Masters students over 20 weeks. Interested candidates should apply with a personal letter and your CV including education, professional experience and grades. Regular attendance at our offices will be expected.
Informationen om uppsatsförslag är hämtad från Nationella Exjobb-poolen.