Spelling suggestions: "subject:"bildsökning"" "subject:"bildsökningar""
1 |
Optimerad bildsökning : Bör vissa egenskaper prioriteras vid sökning efter en viss kategori av bilder? / Optimized image search : Should certain features be emphasized when searching for a specific image category?Larsson, Carl January 2009 (has links)
As the information society becomes increasingly flooded with digital images, the need for efficient image retrieval systems increases as well. To handle the vast amounts of data involved, the indexing process needs to be run automatically, using content-based descriptors extracted directly from the digital image, such as colour composition, shape and texture features. These content-based image retrieval systems are often slow and cumbersome, and can appear confusing to an ordinary user who does not understand the underlying mechanisms. One step towards more efficient and user-friendly retrieval systems might be to adjust the weight placed on various descriptors depending on which image category is being searched for. The results of this thesis show that certain categories of digital images would benefit from having extra weight assigned to colour, texture or shape features when searching for images of that category.
|
2 |
Känslan i bilden : Sociala taggars användbarhet vid bildsökning i FlickrBoye, Anna January 2014 (has links)
Image indexing research today is either conducted on a visual attribute level or on a higher semantic level, forming a semantic gap between the two. There is much to gain if research progress from the two fields is combined. Image retrieval using access points in both visual and semantic significations could improve retrieval and bridge the gap. In social media today, images are often the primary communication agent and the number of images on the web is increasing in an uncontrolled way. New and efficient ways to index and retrieve the images are needed.The purpose of this study is to examine if emotions could be a semantic access point for image retrieval and if folksonomy indexing is useful when searching for images that represent emotions. Images are retrieved from Flickr and Sara Shatford’s matrix for image indexing is used to classify image tags into categories.The result shows that for some emotions it is useful and there is a clear pattern in the retrieved relevant images. For other emotions there are a lot of images that have been tagged on a cluster of images and all images in the cluster is not relevant. Therefore the search result is ambiguous.An interesting observation is that index words expressing abstractions and feelings are more common in folksonomies compared to professional indexers. For specific web image collections where searches could be conducted on feelings, folksonomies is a successful method for the indexing and retrieval of images.
|
Page generated in 0.0484 seconds