2017 · 2 papers

    Sketch-based image retrieval (SBIR) lets one express a precise visual query with simple and widespread means. In the SBIR approaches, the challenge consists in representing the image dataset features in a structure that allows one to efficiently and effectively retrieve images in a scalable system. We put forward a sketch-based image retrieval solution where sketches and natural image contours are represented and compared, in both, the compressed-domain of wavelet and in the pixel domain. The query is efficiently performed in the wavelet domain, while effectiveness refinements are achieved using the pixel domain to verify the spatial consistency between the sketch strokes and the natural image contours. Also, we present an efficient scheme of inverted lists for sketch-based image retrieval using the compressed-domain of wavelets. Our proposal of indexing presents two main advantages, the amount of the data to compute the query is smaller than the traditional method while it presents a better effectiveness.

 @article{ PimentelFilho2017,
   author    = "Carlos Alberto Fraga Pimentel Filho and  Benjamin Bustos and  Arnaldo Albuquerque Ara{\'u}jo and  Silvio Jamil Ferzoli Guimar{\~a}es",
   title     = "Combining pixel domain and compressed domain index for sketch based image retrieval",
   journal   = "Multimedia Tools and Applications",
   pages     = "1--24",
   url       = "http://dx.doi.org/10.1007/s11042-017-4758-y",
   year      = "2017",
 }

 @inproceedings{ DBLP:conf/ijcnn/almeida17,
   author    = "Raquel Almeida and  Zenilton Kleber Gon{\c{c}}alves Patroc{\'{\i}}nio Jr. and  Silvio Jamil Ferzoli Guimar{\~{a}}es",
   title     = "Exploring quantization error to improve human action classification",
   booktitle = "2017 International Joint Conference on Neural Networks (IJCNN 2017), Anchorage, Alaska, May 14-19, 2017.",
   year      = "2017",
 }