A New Approach for Video Text Detection and Localization

1
A New Approach for Video Text Detection and
Localization

• M. Cai, J. Song and M.R. Lyu
• VIEW Technologies
• The Chinese University of Hong Kong

2
Related work

• Text Area Detection
• Uncompressed domain methods
• Texture-based
• Color-based
• Edge-based
• Compressed domain methods
• DCT coefficients
• Number of intra-coded blocks on P- / B- frames
• Text String Localization
• Bottom-up scheme
• Top-down scheme

3
Language-independent characteristics

• Contrast
• An adaptive contrast threshold according to the
  background complexity
• Color
• Color bleeding caused by compression
• Orientation
• Well-defined size and orientation make it easy to
  understand
• Stationary location
• Appear a certain long time

4
Language-dependent characteristics
English Chinese
Stroke density roughly similar varies dramatically
Min(Font size) 10-pixel high 20-pixel high
Min(Aspect ratio) Relatively large Relatively small
Stroke direction statistics mainly vertical vertical horizontal Left diagonal Right diagonal
5
Workflow
6
A sequential multi-resolution paradigm
7
Text detection

• Edge detection
• Sobel edge detector
• Local thresholding
• Adaptive to background complexity
• Text-like area recovery
• Enhance the density of text areas

8
Local Thresholding

• Use a small kernel (gray) to scan the whole edge
  map row by row.
• In the bigger window surrounding the kernel,
  check the background type Clear or Noisy.
• For Clear background and Noisy background,
  determined the local threshold by low and high
  parts, respectively, of the edge strength
  histogram in the bigger window.

9
Thresholding result comparison
10
Text-like area recovery

• Labeling Classify current edge pixels as TEXT
  and NON_TEXT based on its local density.
• Recovery/Suppression
• Bring back neighboring lower-strength edge pixels
  of the TEXT edge pixels.
• The NON_TEXT edge pixels are suppressed.

11
Coarse-to-fine Text localization

• Projection-based top-down localization.
• To handle complex text layout.

12
Localization steps
13
Experimental results
14
Experimental results
15
Performance statistics

• Statistics of 10 news videos
• Processing time per frame 0.25 s (PIII 1G CPU)
• Detection rate
  93.6
• Detection accuracy
• 87.2
• Localization accuracy
• 
  gt 90