Files
hair/face_analysis/annotation.py
T
xslandCursor 45bda80859 feat: 接口1/6 标注层字号上调一档 + 眉心改用 9 号点定位
- annotation: 自适应字号系数 0.017→0.020(下限 8→9),标注文字更大更清晰
- measure: _brow_center 只取 FaceMesh 9 号点(眉间上点),不再与 151 取中点

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-07-30 22:58:49 +08:00

381 lines
18 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
"""标注图层生成(透明底 RGBA PNG,仅标注、不含人物)。
规格(技术方案 §6 + img1.png 版本5):线/字色 #FFFFFF、透明底。
- 字号/线宽/虚线/箭头尺寸全部按图片尺寸自适应缩放(大图也清晰)。
- 四庭水平分界线:numpy 向量化渐变消失(中间亮、两侧渐隐)。
- 纵向竖线 8 条:人头最左 + 左脸颊/左眼外/内角/右眼内/外角/右脸颊 + 人头最右,
把头宽切 7 段(七眼),段宽数值上下交替(上 3 / 下 4),带虚线双箭头。
人头最左/最右取自耳朵分割外缘,看不到耳朵则省略该侧(最少 6 点 5 段)。
- 四庭:图片左侧,「名」「数值(带 cm)」「百分比」三行换行,带竖向虚线双箭头。
- 五条横线右侧标名:头顶/发际线/眉心/鼻翼下缘/下巴尖。
- 每段数值直接带 cm 后缀,下方另起一行标百分比(不再单独标底部「单位cm」)。
中文字体用打包的思源黑体绝对路径加载,缺字体直接抛错(不静默降级成方块)。
"""
import os
import numpy as np
from PIL import Image, ImageDraw, ImageFont
FONT_PATH = os.path.join(os.path.dirname(__file__), "fonts", "NotoSansCJKsc-Regular.otf")
LINE_COLOR = (255, 255, 255, 255) # #FFFFFF 100%
def _load_font(size):
if not os.path.isfile(FONT_PATH):
raise FileNotFoundError(f"中文字体缺失:{FONT_PATH}(请按 OFFLINE_ASSETS.md 放置)")
return ImageFont.truetype(FONT_PATH, size)
def draw_gradient_horizontal_line(buf, cx, cy, color=LINE_COLOR, half_length=None, width=1):
"""在 RGBA numpy 缓冲 buf 上,以 (cx,cy) 为中心画向两侧渐变消失的水平线。"""
h, w = buf.shape[:2]
cy = int(round(cy)); cx = int(round(cx))
half = half_length or (w // 3)
xs = np.arange(w)
dist = np.abs(xs - cx)
alpha = np.clip(1.0 - dist / half, 0.0, 1.0) * color[3]
mask = alpha > 0
for off in range(-(width // 2), width - width // 2):
y = cy + off
if not (0 <= y < h):
continue
row = buf[y]
row[mask, 0] = color[0]
row[mask, 1] = color[1]
row[mask, 2] = color[2]
row[mask, 3] = np.maximum(row[mask, 3], alpha[mask].astype(np.uint8))
def draw_gradient_vertical_line(buf, cx, y0, y1, color=LINE_COLOR, fade=None, width=1):
"""在 RGBA numpy 缓冲 buf 上画一条竖线,两端渐变消失(中间实、上下淡)。"""
h, w = buf.shape[:2]
cx = int(round(cx))
y0, y1 = int(round(y0)), int(round(y1))
y0, y1 = max(0, min(y0, y1)), min(h - 1, max(y0, y1))
if y1 <= y0:
return
ys = np.arange(y0, y1 + 1)
span = y1 - y0
fade = fade or max(1, span // 5) # 仅两端 ~1/5 段渐隐
d = np.minimum(ys - y0, y1 - ys) # 到最近端点的距离
alpha = np.clip(d / fade, 0.0, 1.0) * color[3]
m = alpha > 0
for off in range(-(width // 2), width - width // 2):
x = cx + off
if not (0 <= x < w):
continue
col = buf[y0:y1 + 1, x]
col[m, 0] = color[0]
col[m, 1] = color[1]
col[m, 2] = color[2]
col[m, 3] = np.maximum(col[m, 3], alpha[m].astype(np.uint8))
def draw_dashed_line_with_arrows(draw, x1, y1, x2, y2, color=LINE_COLOR,
dash_len=6, gap_len=4, arrow_size=5, width=1):
"""两点间画稀疏虚线主干,两端用实心三角箭头(尖端精确落在端点,便于对齐)。
虚线只画到「端点向内 arrow_len」处,箭头三角填补剩余,避免虚线穿出箭头。
"""
total = ((x2 - x1) ** 2 + (y2 - y1) ** 2) ** 0.5
if total == 0:
return
dx = (x2 - x1) / total
dy = (y2 - y1) / total
nx, ny = -dy, dx # 法向量
arrow_len = arrow_size * 2.0 # 三角沿线方向长度
arrow_half = arrow_size # 三角底边半宽
# 主干虚线:两端各留出 arrow_len 给箭头
pos = arrow_len
main_end = max(arrow_len, total - arrow_len)
while pos < main_end:
seg_end = min(pos + dash_len, main_end)
draw.line([(x1 + dx * pos, y1 + dy * pos),
(x1 + dx * seg_end, y1 + dy * seg_end)], fill=color, width=width)
pos += dash_len + gap_len
# 两端实心三角箭头:尖端=端点,底边在向内 arrow_len 处展开 ±arrow_half
for (tipx, tipy, ix, iy) in [(x1, y1, dx, dy), (x2, y2, -dx, -dy)]:
bx, by = tipx + ix * arrow_len, tipy + iy * arrow_len
draw.polygon([(tipx, tipy),
(bx + nx * arrow_half, by + ny * arrow_half),
(bx - nx * arrow_half, by - ny * arrow_half)], fill=color)
def _text_size(draw, text, font):
bbox = draw.textbbox((0, 0), text, font=font)
return bbox[2] - bbox[0], bbox[3] - bbox[1]
_LINE_NAMES = {
"hair_top": "头顶",
"hairline": "发际线",
"brow_center": "眉心",
"nose_bottom": "鼻翼下缘",
"chin_tip": "下巴尖",
}
def _grow_outward(start_col, fg_band, direction, limit):
"""从 start_col 沿 direction(+1 右 / -1 左) 在前景带 fg_band 内逐列外扩。
用于回收被误标成「头发」的外耳轮廓:耳朵被头发遮挡时,外耳轮廓那一圈常被
分割并入头发类,故耳朵掩膜外缘会偏内。这里把外缘沿紧邻的前景(耳∪发)向外
延伸,最多 limit 列;一旦下一列无前景(背景间隙)立即停止,绝不窜到分离的
那缕头发上。返回外扩后的列号。
"""
w = fg_band.shape[1]
c = int(start_col)
for _ in range(int(limit)):
nc = c + direction
if not (0 <= nc < w) or not fg_band[:, nc].any():
break
c = nc
return c
def _ear_edges_from_mask(ear_mask, hair_mask, y0, y1, left_cheek_x, right_cheek_x,
face_center_x):
"""从耳朵分割掩膜取人头最左/最右 x(仅在脸纵向范围 [y0,y1] 内统计)。
左线 = 脸中线左侧耳朵像素的最左列;右线 = 右侧耳朵像素的最右列;再沿紧邻的
前景(耳∪发)按脸宽自适应外扩,回收被误标成头发的外耳轮廓(见 _grow_outward)。
某侧耳朵不可见(被头发/侧脸遮挡 → 掩膜为空),或外缘未越过对应脸颊线(非真实
头宽边缘)时该侧返回 None —— 即「看不到耳朵就不画这条线」。
"""
if ear_mask is None:
return None, None
m = np.asarray(ear_mask)
if m.ndim == 3:
m = m[..., 0]
m = m > 0
h = m.shape[0]
y0 = max(0, int(y0)); y1 = min(h - 1, int(y1))
if y1 <= y0:
return None, None
ear_band = m[y0:y1 + 1]
cols = np.where(ear_band.any(axis=0))[0]
if cols.size == 0:
return None, None
# 前景带 = 耳∪发(外耳轮廓常被误标为发),外扩上限按脸宽自适应
fg_band = ear_band
if hair_mask is not None:
hm = np.asarray(hair_mask)
if hm.ndim == 3:
hm = hm[..., 0]
fg_band = ear_band | (hm[y0:y1 + 1] > 0)
grow = max(2, round(max(1.0, right_cheek_x - left_cheek_x) * 0.045))
left_cols = cols[cols < face_center_x]
right_cols = cols[cols > face_center_x]
# 左/右耳外缘(外扩后),且必须在对应脸颊线外侧(否则视为残缺/噪声,只保留脸颊线)
head_l = head_r = None
if right_cols.size:
edge = _grow_outward(right_cols.max(), fg_band, +1, grow)
head_r = float(edge) if edge >= right_cheek_x else None
if left_cols.size:
edge = _grow_outward(left_cols.min(), fg_band, -1, grow)
head_l = float(edge) if edge <= left_cheek_x else None
return head_l, head_r
def create_annotated_image(image_bgr, measure_result, ear_mask=None, hair_mask=None,
variant="v1"):
"""生成标注图层 PNG(透明底 RGBA,尺寸同原图)。返回 PIL.Image。
布局(对齐 img1.png 版本5):
- 纵向竖线:人头最左 + 七眼 6 点 + 人头最右,切 7 段(七眼)。人头最左/最右
取自耳朵分割掩膜的外缘(方案 B,BiSeNet 类 7/8);耳朵不可见(被头发/侧脸
遮挡 → 掩膜空)或无掩膜时省略该侧端线,只画对应脸颊线。
- 横向 5 条分界线:头顶/发际线/眉心/鼻翼下缘/下巴尖,右侧标名。
- 四庭(顶/上/中/下庭)在左侧:名 + 数值(带 cm) + 百分比三行换行,竖向虚线双箭头。
- 七眼段宽上下交替(上 3 / 下 4):数值(带 cm) 上、百分比(占头宽比)下,横向虚线双箭头。
variant="v6"(接口6):去掉头顶横线与顶庭(只画发际线/眉心/鼻翼下缘/下巴尖 4 条
横线 + 上/中/下庭),竖线纵向范围改为发际线→下巴尖,且不画人头最左/最右端线
(仅七眼 6 点 5 段,不取头部端)。
"""
h, w = image_bgr.shape[:2]
v = measure_result.vertical
pc = measure_result.px_per_cm
# --- 自适应尺寸:字号/线宽/虚线/箭头按短边缩放 ---
s = min(w, h)
font_size = max(9, round(s * 0.020)) # 字号上调一档
line_w = max(1, round(s * 0.0022))
dash_len = max(4, round(s * 0.008))
gap_len = max(2, round(dash_len * 0.7)) # 虚线更稠密(间隙<划线)
arrow_size = max(2, round(s * 0.0045)) # 箭头更小
pad = max(4, round(s * 0.012)) # 文字与线的间距
line_h = font_size + max(2, round(font_size * 0.18))
buf = np.zeros((h, w, 4), dtype=np.uint8)
# 发际线弃用(hairline_discarded):保留头顶横线,去掉发际线横线,
# 也不标顶/上庭(缺发际线作边界,算不出)。横线 = 头顶/眉心/鼻翼下缘/下巴尖。
if getattr(measure_result, "hairline_discarded", False):
order = ["hair_top", "brow_center", "nose_bottom", "chin_tip"]
elif variant == "v6":
order = ["hairline", "brow_center", "nose_bottom", "chin_tip"]
else:
order = ["hair_top", "hairline", "brow_center", "nose_bottom", "chin_tip"]
ys = [v[name][1] for name in order]
pts = measure_result.eyes["points"]
seven_keys = ["left_cheek", "left_outer", "left_inner",
"right_inner", "right_outer", "right_cheek"]
base_xs = [pts[k][0] for k in seven_keys]
if variant == "v6":
xs = sorted(base_xs) # 接口6:仅七眼 6 点,不画人头最左/最右端线
else:
# 人头最左/最右:取自耳朵分割掩膜外缘(方案B,类7/8),脸纵向范围内统计。
# 看不到耳朵(被头发/侧脸遮挡 → 掩膜空)或外缘未越过脸颊线则省略该侧端线。
lcx, rcx = pts["left_cheek"][0], pts["right_cheek"][0]
head_l, head_r = _ear_edges_from_mask(
ear_mask, hair_mask, ys[0], ys[-1], lcx, rcx, (lcx + rcx) / 2)
head_xs = [x for x in (head_l, head_r) if x is not None]
xs = sorted(base_xs + head_xs) # 自左向右(6 或 7/8 点)
# 人脸/人头包围盒
fx0, fx1 = xs[0], xs[-1]
fy0, fy1 = ys[0], ys[-1]
face_cx = (fx0 + fx1) / 2
over = max(6, round(s * 0.030)) # 线超出包围盒的长度(参考图风格)
face_half = (fx1 - fx0) / 2 + over # 横线超出最外侧竖线一点
# 竖线纵向范围:v6 = 发际线→下巴尖(不超出);v1(含发际线弃用)= 头顶→下巴尖并两端超出一点
v_top = fy0 if variant == "v6" else fy0 - over
v_bot = fy1 if variant == "v6" else fy1 + over
# --- 1. 横向分界线(渐变,覆盖头宽并超出一点) ---
for cy in ys:
draw_gradient_horizontal_line(buf, face_cx, cy, half_length=face_half, width=line_w)
# --- 2. 纵向竖线(渐变,覆盖 v_top→v_bot ---
for vx in xs:
draw_gradient_vertical_line(buf, vx, v_top, v_bot, width=line_w)
canvas = Image.fromarray(buf, mode="RGBA")
draw = ImageDraw.Draw(canvas)
font = _load_font(font_size)
# --- 3a. 横线右侧:线名(头顶/发际线/眉心/鼻翼下缘/下巴尖),文字纵向居中对齐到线 ---
name_x = fx1 + over + pad # 移到横线右端外侧一点(往右)
for i, name in enumerate(order):
text = _LINE_NAMES[name]
tw, _ = _text_size(draw, text, font)
x = min(name_x, w - 2 - tw) # 右侧越界时回收
# anchor="lm"x 为左、y 为竖直中点 → 文字中线正好压在横线上(与线对齐)
draw.text((x, ys[i]), text, fill=LINE_COLOR, font=font, anchor="lm")
# --- 3b. 左侧四庭:名 + 数值两行(无 cm)+ 竖向虚线双箭头 ---
# court_start:庭段在 order 里的起始索引。发际线弃用时 order 首位是头顶(无下界发际线,
# 顶/上庭不标),中庭从眉心开始 → 跳过 order[0]。
if getattr(measure_result, "hairline_discarded", False):
court_cm = [measure_result.middle_cm, measure_result.lower_cm]
court_name = ["中庭", "下庭"]
n_court = 2
court_start = 1
elif variant == "v6":
court_cm = [measure_result.upper_cm, measure_result.middle_cm, measure_result.lower_cm]
court_name = ["上庭", "中庭", "下庭"]
n_court = 3
court_start = 0
else:
court_cm = [measure_result.top_cm, measure_result.upper_cm,
measure_result.middle_cm, measure_result.lower_cm]
court_name = ["顶庭", "上庭", "中庭", "下庭"]
n_court = 4
court_start = 0
arrow_x = max(arrow_size + 1, fx0 - pad) # 竖箭头所在 x(脸左侧,贴近最左竖线)
court_total = sum(court_cm) or 1.0 # 各庭占比分母 = 四庭(v6 三庭)之和
for i in range(n_court):
y_a, y_b = ys[court_start + i], ys[court_start + i + 1]
# 竖向虚线双箭头,覆盖该庭高度(略收一点避免压到横线)
inset = min(arrow_size, (y_b - y_a) * 0.12)
draw_dashed_line_with_arrows(
draw, arrow_x, y_a + inset, arrow_x, y_b - inset,
dash_len=dash_len, gap_len=gap_len, arrow_size=arrow_size, width=line_w)
# 名 + 数值(带 cm) + 百分比三行,右对齐到箭头左侧
name = court_name[i]
val = f"{court_cm[i]:.2f}cm"
pct = f"{court_cm[i] / court_total * 100:.1f}%"
nw, _ = _text_size(draw, name, font)
vw, _ = _text_size(draw, val, font)
pw, _ = _text_size(draw, pct, font)
label_right = arrow_x - pad
y_mid = (y_a + y_b) / 2
y_top = y_mid - 1.5 * line_h
draw.text((max(2, label_right - nw), y_top), name, fill=LINE_COLOR, font=font)
draw.text((max(2, label_right - vw), y_top + line_h), val, fill=LINE_COLOR, font=font)
draw.text((max(2, label_right - pw), y_top + 2 * line_h), pct, fill=LINE_COLOR, font=font)
# --- 4. 七眼每段宽度:上下交替(上 3 / 下 4),横向虚线双箭头 + 数值(带 cm) + 百分比 ---
# 每段两行:数值(带 cm) 上、百分比 下;百分比分母 = 整个头宽(七段之和)
txt_off = arrow_size + pad * 2
txt_block = 2 * line_h # 两行文字总高(数值 + 百分比)
y_arrow_top = max(txt_off + txt_block + 2, fy0 - pad - arrow_size)
y_arrow_bot = min(h - txt_off - txt_block - 2, fy1 + pad + arrow_size)
head_w = (xs[-1] - xs[0]) or 1.0 # 头宽(像素)= 百分比分母
for i in range(len(xs) - 1):
x_a, x_b = xs[i], xs[i + 1]
if x_b - x_a < 1:
continue
seg_cm = (x_b - x_a) / pc
seg_pct = (x_b - x_a) / head_w * 100
cx_seg = (x_a + x_b) / 2
val = f"{seg_cm:.2f}cm"
pct = f"{seg_pct:.1f}%"
vw, _ = _text_size(draw, val, font)
pw, _ = _text_size(draw, pct, font)
inset = min(arrow_size, (x_b - x_a) * 0.12)
on_top = (i % 2 == 1) # 奇数段在上 → 上 3 / 下 4
y_arrow = y_arrow_top if on_top else y_arrow_bot
draw_dashed_line_with_arrows(
draw, x_a + inset, y_arrow, x_b - inset, y_arrow,
dash_len=dash_len, gap_len=gap_len, arrow_size=arrow_size, width=line_w)
# 数值行在上、百分比行在下;on_top 时整块置于箭头上方,否则下方
text_top = (y_arrow - txt_off - txt_block) if on_top else (y_arrow + txt_off)
draw.text((cx_seg - vw / 2, text_top), val, fill=LINE_COLOR, font=font)
draw.text((cx_seg - pw / 2, text_top + line_h), pct, fill=LINE_COLOR, font=font)
return canvas
if __name__ == "__main__":
import sys
import time
import cv2
from face_analysis.detector import detector
from face_analysis.measure import measure_face
path = sys.argv[1] if len(sys.argv) > 1 else "tests/fixtures/frontal.jpg"
out = sys.argv[2] if len(sys.argv) > 2 else "tests/output/annotated.png"
img = cv2.imread(path)
if img is None:
print(f"无法读取图片: {path}")
sys.exit(1)
h, w = img.shape[:2]
lms = detector.detect(img)
if lms is None:
print("未检出人脸")
sys.exit(1)
mask = None
ears = None
try:
from face_analysis.hair_segmenter import get_segmenter
mask, ears = get_segmenter().segment_hair_and_ears(img)
except Exception as e: # noqa: BLE001
print(f"[warn] 分割不可用,回退方案 A:{e}")
result = measure_face(lms, mask, w, h)
t0 = time.time()
canvas = create_annotated_image(img, result, ear_mask=ears, hair_mask=mask)
dt = time.time() - t0
os.makedirs(os.path.dirname(out), exist_ok=True)
canvas.save(out)
arr = np.asarray(canvas)
print(f"saved {out} mode={canvas.mode} size={canvas.size} "
f"transparent={bool((arr[:,:,3]==0).any())} opaque={bool((arr[:,:,3]>0).any())} "
f"elapsed={dt*1000:.1f}ms")