000087044 001__ 87044
000087044 005__ 20190316233746.0
000087044 037__ $$aREP_WORK
000087044 245__ $$aLearning Structured Dictionaries for Image Representation
000087044 269__ $$a2004
000087044 260__ $$c2004$$aEcublens
000087044 336__ $$aReports
000087044 520__ $$aThe dictionary approach to signal and image processing has been massively investigated in the last two decades, proving very attractive for a wide range of applications. The effectiveness of dictionary-based methods, however, is strongly influenced by the choice of the set of basis functions. Moreover the structure of the dictionary is of paramount importance regarding efficient implementation and practical applications such as image coding. In this work, an overcomplete code for sparse representation of natural images has been learnt from a set a real-world scenes. Experiments have been carried out using images of different sizes in order to check the influence of this parameter on the learnt bases. The functions found have been organized into a hierarchical structure. We take advantage of this representation of the dictionary, adopting a tree-structured greedy algorithm to build sparse approximations of images. Using this procedure, no a-priori constraint is imposed on the structure of the dictionary, allowing great flexibility in its design and lower computational complexity.
000087044 6531_ $$adictionary learning.
000087044 6531_ $$aimage representation
000087044 6531_ $$aLTS2
000087044 6531_ $$aredundant expansion
000087044 6531_ $$aSparse representation
000087044 700__ $$0241005$$g150417$$aMonaci, G.
000087044 700__ $$aVandergheynst, P.$$g120906$$0240428
000087044 8564_ $$uhttps://infoscience.epfl.ch/record/87044/files/Monaci2004_750.pdf$$zn/a$$s748452
000087044 909C0 $$xU10380$$0252392$$pLTS2
000087044 909CO $$qGLOBAL_SET$$pSTI$$ooai:infoscience.tind.io:87044$$preport
000087044 937__ $$aEPFL-REPORT-87044
000087044 970__ $$aMonaci2004_750/LTS
000087044 973__ $$sPUBLISHED$$aEPFL
000087044 980__ $$aREPORT