Skip to main content


Table 1 Main parameters in the generation processes

From: First-person reading activity recognition by deep learning with synthetically generated images

Process Parameters Values
Canvas of each page \(210\sqrt {2} \times 210\) pixel by appropriate scaling
T Blank space 10% at the top, bottom, left, and right in the canvases
  Columns 1 or 2
  Pages containing figures 80% of the entire generated pages
  Place to put figures The top or the bottom in a column
  Category of figures Mathematical figures, tables, and general pictures
  Figure size Height: 12.550%, or 100% of the column height
   Width: fixed at the same length of the column
  Size of headlines 10% of the page height
  Place to put headlines Somewhere outside the figure areas
  Place to put texts Entire areas in the column except the figures and headlines
  Text format Japanese characters in random order (without any rules)
  Line-breaking Done with prob. 1% every time putting a character
D Distortion strength α[0.1,0.3]
P Homography matrix Determined as shown in Fig. 4
R Rotation angles In [ − 10°,10°]
Resize The long side shrinks to 256 pixel with keeping the ratio