This webpage presents the Complex Map Dataset used to assess the method published in the two following publications:
- Q.B. Dang, M.M. Luqman, M. Coustaty, N. Nayef, C.D. Tran, J.M. Ogier - "A system for camera-based complex map image retrieval using a multi-layer approach", published in IAPR International workshop on Document Analysis System (2014)
- Q.B. Dang, M.M. Luqman, M. Coustaty, N. Nayef, C.D. Tran, J.M. Ogier - "A multi-layer separation based system for camera-based complex map image retrieval", published in CIFED 2014
- Q.B. Dang, M.M. Luqman, M. Coustaty, N. Nayef, C.D. Tran, J.M. Ogier - "A multi-layer approach for camera-based complex map image retrieval and spotting system". published in IPTA 2014
Original image |
Frame captured |
Frame captured |
Original image |
|
|---|---|---|---|---|
 |
 |
 |
 |
|
Original image |
Frame captured |
|||
 |
 |
Here is the dataset composition:
- 12 maps stored in folder "map"
- For each map, 6 videos (corresponding to 6 different regions - a,b,c,d,e,f) have been captured and stored in folder "video"
- For the evaluation process, 20 frames have been selected in each video in order to obtain 1440 frames stored in folder "frame"
You can download it here, and we ask to people that may use it to cite the paper published in DAS (the complete reference is available at the top of this page).