| import math |
| import numpy as np |
|
|
| def _percentiles(b: np.ndarray, qs=(0.02, 0.5, 0.98)) -> list[float]: |
| """np.percentile(b, 100 * qs) (linear) of a uint8 array, from its histogram: |
| no sort of the pixels.""" |
| n = b.size |
| cum = np.cumsum(np.bincount(b.ravel(), minlength=256)) |
| out = [] |
| for q in qs: |
| x = q * (n - 1) |
| i = math.floor(x) |
| g = x - i |
| lo = float(np.searchsorted(cum, i, side="right")) |
| hi = float(np.searchsorted(cum, min(i + 1, n - 1), side="right")) |
| d = hi - lo |
| |
| out.append(hi - d * (1 - g) if g >= 0.5 else lo + d * g) |
| return out |
|
|
| def is_dark_line(gray: np.ndarray, box) -> bool: |
| """Light text on a dark ground (a banner, a dark table head, a slide): the |
| ground (the median of the line box) lies nearer the dark end than the text |
| does, so the bright tail is the longer one. A shadowed line keeps dark text |
| on a dimmer ground. The recognizers read dark text on light paper, so a |
| light-on-dark line is read inverted.""" |
| H, W = gray.shape |
| x0, y0, x1, y1 = (float(v) for v in box[:4]) |
| b = gray[ |
| max(0, int(y0)) : min(H, int(y1) + 1), max(0, int(x0)) : min(W, int(x1) + 1) |
| ] |
| if not b.size: |
| return False |
| lo, med, hi = ( |
| _percentiles(b) if b.dtype == np.uint8 else np.percentile(b, (2, 50, 98)) |
| ) |
| return bool(hi - med > 2 * (med - lo) + 8) |
|
|
