"""角点回画预览:把已落盘的四角画回原图,供二次确认。 用途:把落盘的数字角点重新变成可看的画面。 本脚本把四边形 + 四角标记 + 边标签画回原图,让"数字"重新变成可看的画面, 在出件前确认四条边是否真的压在纸张亮面与桌面暗面的交界线上。 图上元素: 绿色四边形 —— 当前角点连线,应紧贴纸边 红色十字 + 序号 —— 四个角点(1左上 2右上 3右下 4左下) 黄色短刻度线 —— 每条边中点的外法线,用于看边是否贴边 右下角文字 —— 两行:文件名 / 角点串(避开顶部/左侧刻度) 用法: python3 doc_deskew/preview_quad.py 图1.jpg 图2.jpg python3 doc_deskew/preview_quad.py --corners .tmp/corners.json python3 doc_deskew/preview_quad.py --corners .tmp/corners.json --zoom 右 输出:.tmp/quad_<名称>.png --zoom 另存右侧/左侧/上边/下边放大块,.tmp/quad_<名称>_<区域>.png """ import argparse import json import os import sys from PIL import Image, ImageDraw, ImageFont HERE = os.path.dirname(os.path.abspath(__file__)) sys.path.insert(0, HERE) DEFAULT_CORNERS = '.tmp/corners.json' OUT_DIR = '.tmp' LABELS = ['1 左上', '2 右上', '3 右下', '4 左下'] COLOR_QUAD = (0, 255, 0) COLOR_CORNER = (255, 40, 40) COLOR_EDGE = (255, 220, 0) def load_corners(path): with open(path, encoding='utf-8') as f: data = json.load(f) out = {} for name, quad in data.items(): if isinstance(quad, dict): quad = quad.get('quad') or quad.get('corners') out[name] = [(float(p[0]), float(p[1])) for p in quad] return out def get_font(size=26): # 先找中文字体(图上要画 "1 左上" 这类标签,西文字体会变成豆腐块) for p in ('/usr/share/fonts/opentype/noto/NotoSansCJK-Bold.ttc', '/usr/share/fonts/opentype/noto/NotoSansCJK-Regular.ttc', '/usr/share/fonts/truetype/noto/NotoSansCJK-Regular.ttc', '/usr/share/fonts/truetype/dejavu/DejaVuSans-Bold.ttf', '/usr/share/fonts/truetype/liberation/LiberationSans-Bold.ttf'): if os.path.exists(p): try: return ImageFont.truetype(p, size) except Exception: pass return ImageFont.load_default() def draw_quad(img_path, pts, scale=1.0, with_grid=False): im = Image.open(img_path).convert('RGB') # 角标图默认叠上与网格图同一套网格:坐标读数与框边可以对着看 if with_grid: from grid import draw_grid_on im = draw_grid_on(im) if scale != 1.0: im = im.resize((int(im.width * scale), int(im.height * scale)), Image.LANCZOS) d = ImageDraw.Draw(im) font = get_font(max(14, int(26 * min(1.0, scale + 0.15)))) sml = get_font(max(11, int(18 * min(1.0, scale + 0.15)))) w = max(2, int(3 * scale + 0.5)) P = [(x * scale, y * scale) for x, y in pts] # 四边形 d.line(P + [P[0]], fill=COLOR_QUAD, width=w) # 四角十字 + 序号 r = max(10, int(22 * scale + 0.5)) for i, (x, y) in enumerate(P): d.line([(x - r, y), (x + r, y)], fill=COLOR_CORNER, width=w) d.line([(x, y - r), (x, y + r)], fill=COLOR_CORNER, width=w) tx, ty = x + r + 4, y - r - 4 d.text((tx, ty), LABELS[i], fill=COLOR_CORNER, font=sml, stroke_width=2, stroke_fill=(0, 0, 0)) # 每条边中点外法线刻度 cx = sum(p[0] for p in P) / 4.0 cy = sum(p[1] for p in P) / 4.0 L = max(16, int(40 * scale + 0.5)) for i in range(4): a, b = P[i], P[(i + 1) % 4] mx, my = (a[0] + b[0]) / 2.0, (a[1] + b[1]) / 2.0 dx, dy = mx - cx, my - cy n = (dx * dx + dy * dy) ** 0.5 or 1.0 dx, dy = dx / n, dy / n d.line([(mx, my), (mx + dx * L, my + dy * L)], fill=COLOR_EDGE, width=max(2, w - 1)) # 右下角信息条(避开顶部/左侧的网格刻度):第一行文件名,第二行角点串 lines = [os.path.basename(img_path), ';'.join('%g,%g' % (p[0], p[1]) for p in pts)] pad = 8 gap = 6 tw = int(max(d.textlength(s, font=font) for s in lines)) ascent, descent = font.getmetrics() line_h = ascent + descent th = line_h * len(lines) + gap * (len(lines) - 1) tx = max(pad, im.width - tw - pad * 2) ty = max(pad, im.height - th - pad * 2) d.rectangle([tx - 4, ty - 4, tx + tw + 4, ty + th + 4], fill=(0, 0, 0)) for i, s in enumerate(lines): d.text((tx, ty + i * (line_h + gap)), s, fill=(255, 255, 255), font=font) return im def zoom_boxes(im, pts): """按角点外接框给出四侧放大区域。""" xs = [p[0] for p in pts] ys = [p[1] for p in pts] x0, x1, y0, y1 = min(xs), max(xs), min(ys), max(ys) W, H = im.size mx = (x1 - x0) * 0.18 my = (y1 - y0) * 0.18 boxes = { 'left': (max(0, x0 - mx), max(0, y0 - my), min(W, x0 + mx), min(H, y1 + my)), 'right': (max(0, x1 - mx), max(0, y0 - my), min(W, x1 + mx), min(H, y1 + my)), 'top': (max(0, x0 - mx), max(0, y0 - my), min(W, x1 + mx), min(H, y0 + my)), 'bottom': (max(0, x0 - mx), max(0, y1 - my), min(W, x1 + mx), min(H, y1 + my)), } return boxes def main(): ap = argparse.ArgumentParser(description='把角点画回原图做二次确认') ap.add_argument('images', nargs='*', help='图片文件名(角点已在 corners.json 中)') ap.add_argument('--corners', default=DEFAULT_CORNERS) ap.add_argument('--zoom', choices=['left', 'right', 'top', 'bottom', 'all'], default=None, help='另存某侧放大块') ap.add_argument('--scale', type=float, default=1.0, help='整体缩放,>1 放大') ap.add_argument('--out', default=None, help='输出目录,默认 .tmp') args = ap.parse_args() data = load_corners(args.corners) names = args.images or list(data.keys()) missing = [n for n in names if n not in data] if missing: raise SystemExit('corners.json 中没有这些图的角点:%s' % ', '.join(missing)) outdir = args.out or OUT_DIR os.makedirs(outdir, exist_ok=True) for name in names: pts = data[name] im = draw_quad(name, pts, args.scale) base = os.path.splitext(os.path.basename(name))[0] dst = os.path.join(outdir, 'quad_%s.png' % base) im.save(dst) print('written %s (%dx%d) %s' % (dst, im.width, im.height, ';'.join('%g,%g' % p for p in pts))) if args.zoom: boxes = zoom_boxes(im, [(x * args.scale, y * args.scale) for x, y in pts]) keys = list(boxes) if args.zoom == 'all' else [args.zoom] for k in keys: box = tuple(int(v) for v in boxes[k]) if box[2] <= box[0] or box[3] <= box[1]: continue crop = im.crop(box) f = min(3.0, max(1.0, 700.0 / max(1, crop.width))) if f > 1.0: crop = crop.resize((int(crop.width * f), int(crop.height * f)), Image.LANCZOS) z = os.path.join(outdir, 'quad_%s_%s.png' % (base, k)) crop.save(z) print('written %s (%dx%d)' % (z, crop.width, crop.height)) if __name__ == '__main__': main()