A Framework Towards Realtime Detection and Tracking of Text

• Carlos Merino (Universidad de La Laguna); homepage: http://www.nf.ull.es/Members/carlos; email: cmerino@ull.es
• Majid Mirmehdi (University of Bristol); homepage: http://www.cs.bris.ac.uk/~majid; email: majid@bris.ac.uk

Sample scenes and videos

These are the full video sequences of the samples in the paper and the CBDAR 2007 presentation.

Sample 1 «BORDERS» (Figure 7)

Download:

• Xvid encoded AVI file (2.9 Mb)

Sample 2 «UOB» (Figure 8)

Download:

• Xvid encoded AVI file (8.2 Mb)

Sample 3 «ST. MICHAEL'S HOSPITAL» (Figure 9)

Download:

• Xvid encoded AVI file (2.8 Mb)

Sample 4 «LORRY» (Figure 10)

Download:

• Xvid encoded AVI file (2.1 Mb)

Sample 5 «LA PAZ»

Download:

• Xvid encoded AVI file (1.3 Mb)

Sample 6 «DESKTOP»

Download:

• Xvid encoded AVI file (19.1 Mb)

Other sample scenes:

These additional scene scenes were obtained from this web page, from Myers et al work, and processed with our algorithm.

Sample 7

Download:

• Xvid encoded AVI file (2.9 Mb)

Sample 8

Download:

• Xvid encoded AVI file (1.7 Mb)