Title :
Logo Retrieval in Document Images
Author :
Jain, Rajiv ; Doermann, David
Author_Institution :
Univ. of Maryland, College Park, MD, USA
Abstract :
This paper presents a scalable algorithm for segmentation free logo retrieval in document images. The contributions include the use of the SURF feature for logo retrieval, a novel indexing algorithm for efficient retrieval and a method to filter results using the orientation of local features and geometric constraints. Results demonstrate that logo retrieval can be performed with high accuracy and efficiently scaled to a large datasets.
Keywords :
document image processing; feature extraction; image retrieval; indexing; information filtering; visual databases; SURF feature; document images; geometric constraints; indexing algorithm; local feature orientation; segmentation free logo retrieval; Context; Feature extraction; Image retrieval; Indexing; Matched filters; Vectors; Document Images; Indexing; Logo retrieval; SURF;
Conference_Titel :
Document Analysis Systems (DAS), 2012 10th IAPR International Workshop on
Conference_Location :
Gold Cost, QLD
Print_ISBN :
978-1-4673-0868-7
DOI :
10.1109/DAS.2012.54
