Finds lines in the input image.

lines = lsd.detect(img)
[lines, width, prec, nfa] = lsd.detect(img)

Input

• img A grayscale (uint8) input image.

Output

• lines A cell-array of 4-element vectors of the form {[x1, y1, x2, y2], ..} specifying the beginning and ending point of a line. Where point 1 [x1,y1] is the start, point 2 `[x2,y2] the end. Returned lines are strictly oriented depending on the gradient.
• width Vector of widths of the regions, where the lines are found. E.g. Width of line.
• prec Vector of precisions with which the lines are found.
• nfa Vector containing number of false alarms in the line region, with precision of 10%. The bigger the value, logarithmically better the detection. This vector will be calculated only when the object refine type is 'Advanced', empty otherwise.
  • -1 corresponds to 10 mean false alarms
  • 0 corresponds to 1 mean false alarm
  • 1 corresponds to 0.1 mean false alarms