xsl
a1d458eb20
- face_mesh_landmarks.py: 加常量 LEFT_POSITION=21 / RIGHT_POSITION=251
- measure.py: MeasureResult 收 landmarks/宽高, to_response 顶层输出两点(原图像素 {x,y}, 与 landmarks 同格式)
- measure_face 透传 landmarks(签名不变, 6处调用零改动); __init__ 用 None 默认值守卫向后兼容
- 三接口自动生效: 接口1/6 在 data 顶层, 接口5 在 face_measure 对象里(复用同一 to_response)
- 实测坐标左右镜像合理, 44 个现有测试全过无回归
272 lines
11 KiB
Python
272 lines
11 KiB
Python
"""四庭七眼测量核心：纵向定位（方案 B 主 / 方案 A 兜底）+ 七眼 + 厘米换算。
|
||
|
||
整合：
|
||
- estimate_vertical_landmarks：方案 A，按三庭比例推算上/顶庭（兜底）。
|
||
- 决策逻辑：优先方案 B（分割发际线/头顶），合理性校验不过则回退方案 A。
|
||
- measure_seven_eyes：眼宽/脸宽/两眼间距实测。
|
||
- measure_face：主入口，产出结构化结果 MeasureResult（含 to_response）。
|
||
|
||
详见技术方案 §4 / §5。本模块不依赖 torch，可在纯几何环境单独运行。
|
||
"""
|
||
from face_analysis.calibration import (
|
||
estimate_scale_factor, normalized_to_pixel, pixel_distance, _lm_list,
|
||
)
|
||
from face_analysis.face_mesh_landmarks import (
|
||
GLABELLA_9, GLABELLA_151, NOSE_BOTTOM, CHIN_TIP,
|
||
LEFT_EYE_OUTER, LEFT_EYE_INNER, RIGHT_EYE_INNER, RIGHT_EYE_OUTER,
|
||
LEFT_CHEEK, RIGHT_CHEEK, LEFT_POSITION, RIGHT_POSITION,
|
||
)
|
||
from face_analysis.hair_segmenter import locate_hairline_by_segmentation
|
||
|
||
# 方案 A 推算比例常量（顶:上:中:下 = 0.22:0.25:0.28:0.25），见技术方案 §4.2
|
||
_UPPER_RATIO = 0.25 / 0.265 # 上庭 ÷ 中下庭均值
|
||
_TOP_RATIO = 0.22 / 0.28 # 顶庭 ÷ 中庭（≈ 0.786）
|
||
|
||
|
||
def _brow_center(lm, w, h):
|
||
"""眉心 = 索引 9 / 151 中点。"""
|
||
g9 = normalized_to_pixel(lm[GLABELLA_9], w, h)
|
||
g151 = normalized_to_pixel(lm[GLABELLA_151], w, h)
|
||
return (g9[0] + g151[0]) / 2, (g9[1] + g151[1]) / 2
|
||
|
||
|
||
def estimate_vertical_landmarks(landmarks, image_width, image_height):
|
||
"""方案 A（兜底）：实测中/下庭，按比例推算上/顶庭。
|
||
|
||
返回 5 个纵向点像素坐标 + 各段像素高度。注意其循环论证局限：
|
||
上/顶庭为估算值，不反映真实脸型（详见技术方案 §4.1）。
|
||
"""
|
||
lm = _lm_list(landmarks)
|
||
w, h = image_width, image_height
|
||
|
||
brow_x, brow_y = _brow_center(lm, w, h)
|
||
nose_bottom = normalized_to_pixel(lm[NOSE_BOTTOM], w, h)
|
||
chin_tip = normalized_to_pixel(lm[CHIN_TIP], w, h)
|
||
|
||
middle_court_px = abs(brow_y - nose_bottom[1]) # 眉心 → 鼻翼下缘
|
||
lower_court_px = abs(nose_bottom[1] - chin_tip[1]) # 鼻翼下缘 → 下巴尖
|
||
|
||
one_unit_px = (middle_court_px + lower_court_px) / 2 # 一等份 ≈ 中/下庭均值
|
||
upper_court_px = one_unit_px * _UPPER_RATIO
|
||
top_court_px = one_unit_px * _TOP_RATIO
|
||
|
||
hairline_y = brow_y - upper_court_px
|
||
hair_top_y = hairline_y - top_court_px
|
||
|
||
return {
|
||
"hair_top": (brow_x, hair_top_y),
|
||
"hairline": (brow_x, hairline_y),
|
||
"brow_center": (brow_x, brow_y),
|
||
"nose_bottom": (nose_bottom[0], nose_bottom[1]),
|
||
"chin_tip": (chin_tip[0], chin_tip[1]),
|
||
"top_court_px": top_court_px,
|
||
"upper_court_px": upper_court_px,
|
||
"middle_court_px": middle_court_px,
|
||
"lower_court_px": lower_court_px,
|
||
}
|
||
|
||
|
||
def _vertical_from_segmentation(lm, w, h, hair_mask):
|
||
"""方案 B：用分割得到的发际线/头顶替换方案 A 的上/顶庭。
|
||
|
||
成功且通过合理性校验返回 vertical dict，否则返回 None。
|
||
"""
|
||
res = locate_hairline_by_segmentation(hair_mask, _brow_center(lm, w, h)[0], h)
|
||
if res is None:
|
||
return None
|
||
hairline_y, hair_top_y = res
|
||
|
||
brow_x, brow_y = _brow_center(lm, w, h)
|
||
nose_bottom = normalized_to_pixel(lm[NOSE_BOTTOM], w, h)
|
||
chin_tip = normalized_to_pixel(lm[CHIN_TIP], w, h)
|
||
|
||
middle_court_px = abs(brow_y - nose_bottom[1])
|
||
lower_court_px = abs(nose_bottom[1] - chin_tip[1])
|
||
upper_court_px = brow_y - hairline_y # 发际线 → 眉心
|
||
top_court_px = hairline_y - hair_top_y # 头顶 → 发际线
|
||
|
||
# 合理性校验：发际线在眉心上方、头顶在发际线上方、各庭为正
|
||
if not (hair_top_y < hairline_y < brow_y):
|
||
return None
|
||
if upper_court_px <= 0 or top_court_px <= 0:
|
||
return None
|
||
if middle_court_px <= 0 or lower_court_px <= 0:
|
||
return None
|
||
|
||
return {
|
||
"hair_top": (brow_x, float(hair_top_y)),
|
||
"hairline": (brow_x, float(hairline_y)),
|
||
"brow_center": (brow_x, brow_y),
|
||
"nose_bottom": (nose_bottom[0], nose_bottom[1]),
|
||
"chin_tip": (chin_tip[0], chin_tip[1]),
|
||
"top_court_px": top_court_px,
|
||
"upper_court_px": upper_court_px,
|
||
"middle_court_px": middle_court_px,
|
||
"lower_court_px": lower_court_px,
|
||
}
|
||
|
||
|
||
def decide_vertical(landmarks, image_width, image_height, hair_mask):
|
||
"""纵向定位决策：方案 B 优先，失败回退方案 A。
|
||
|
||
返回 (vertical_dict, hairline_source)，source ∈ {"segmentation","estimated"}。
|
||
"""
|
||
lm = _lm_list(landmarks)
|
||
vb = _vertical_from_segmentation(lm, image_width, image_height, hair_mask)
|
||
if vb is not None:
|
||
return vb, "segmentation"
|
||
return estimate_vertical_landmarks(landmarks, image_width, image_height), "estimated"
|
||
|
||
|
||
def measure_seven_eyes(landmarks, image_width, image_height):
|
||
"""七眼：眼宽（左右均值）、脸宽、两眼间距（像素）。"""
|
||
lm = _lm_list(landmarks)
|
||
w, h = image_width, image_height
|
||
left_outer = normalized_to_pixel(lm[LEFT_EYE_OUTER], w, h)
|
||
left_inner = normalized_to_pixel(lm[LEFT_EYE_INNER], w, h)
|
||
right_inner = normalized_to_pixel(lm[RIGHT_EYE_INNER], w, h)
|
||
right_outer = normalized_to_pixel(lm[RIGHT_EYE_OUTER], w, h)
|
||
left_cheek = normalized_to_pixel(lm[LEFT_CHEEK], w, h)
|
||
right_cheek = normalized_to_pixel(lm[RIGHT_CHEEK], w, h)
|
||
|
||
left_eye = pixel_distance(left_outer, left_inner)
|
||
right_eye = pixel_distance(right_inner, right_outer)
|
||
return {
|
||
"eye_width_px": (left_eye + right_eye) / 2,
|
||
"face_width_px": pixel_distance(left_cheek, right_cheek),
|
||
"inter_eye_distance_px": pixel_distance(left_inner, right_inner),
|
||
# 标注图用的横向点像素坐标（不进 to_response）
|
||
"points": {
|
||
"left_outer": left_outer, "left_inner": left_inner,
|
||
"right_inner": right_inner, "right_outer": right_outer,
|
||
"left_cheek": left_cheek, "right_cheek": right_cheek,
|
||
},
|
||
}
|
||
|
||
|
||
class MeasureResult:
|
||
"""测量结果，提供 to_response() 输出与接口文档同构的 data 字段。"""
|
||
|
||
def __init__(self, vertical, eyes, px_per_cm, hairline_source, head_pose,
|
||
landmarks=None, image_width=None, image_height=None):
|
||
self.vertical = vertical
|
||
self.eyes = eyes
|
||
self.px_per_cm = px_per_cm
|
||
self.hairline_source = hairline_source
|
||
self.head_pose = head_pose # (yaw, pitch, roll) 或 None
|
||
# 原始 mediapipe 点集 + 图像尺寸，供 to_response 输出 21/251 号定位点
|
||
self.landmarks = landmarks
|
||
self.w = image_width
|
||
self.h = image_height
|
||
|
||
# 各庭厘米
|
||
self.top_cm = vertical["top_court_px"] / px_per_cm
|
||
self.upper_cm = vertical["upper_court_px"] / px_per_cm
|
||
self.middle_cm = vertical["middle_court_px"] / px_per_cm
|
||
self.lower_cm = vertical["lower_court_px"] / px_per_cm
|
||
self.face_total_cm = self.top_cm + self.upper_cm + self.middle_cm + self.lower_cm
|
||
|
||
# 七眼厘米
|
||
self.eye_width_cm = eyes["eye_width_px"] / px_per_cm
|
||
self.face_width_cm = eyes["face_width_px"] / px_per_cm
|
||
self.inter_eye_cm = eyes["inter_eye_distance_px"] / px_per_cm
|
||
|
||
def to_response(self):
|
||
total_px = (self.vertical["top_court_px"] + self.vertical["upper_court_px"]
|
||
+ self.vertical["middle_court_px"] + self.vertical["lower_court_px"])
|
||
fw_px = self.eyes["face_width_px"]
|
||
|
||
def pt(name):
|
||
x, y = self.vertical[name]
|
||
return {"x": int(round(x)), "y": int(round(y))}
|
||
|
||
data = {
|
||
"face_total_height_cm": round(self.face_total_cm, 2),
|
||
"four_courts": {
|
||
"top_court_cm": round(self.top_cm, 2),
|
||
"upper_court_cm": round(self.upper_cm, 2),
|
||
"middle_court_cm": round(self.middle_cm, 2),
|
||
"lower_court_cm": round(self.lower_cm, 2),
|
||
"ratios": {
|
||
"top_court": round(self.vertical["top_court_px"] / total_px, 3),
|
||
"upper_court": round(self.vertical["upper_court_px"] / total_px, 3),
|
||
"middle_court": round(self.vertical["middle_court_px"] / total_px, 3),
|
||
"lower_court": round(self.vertical["lower_court_px"] / total_px, 3),
|
||
},
|
||
},
|
||
"seven_eyes": {
|
||
"eye_width_cm": round(self.eye_width_cm, 2),
|
||
"face_width_cm": round(self.face_width_cm, 2),
|
||
"inter_eye_distance_cm": round(self.inter_eye_cm, 2),
|
||
"ratios": {
|
||
"eye_width": round(self.eyes["eye_width_px"] / fw_px, 3),
|
||
"inter_eye_distance": round(self.eyes["inter_eye_distance_px"] / fw_px, 3),
|
||
},
|
||
},
|
||
"landmarks": {
|
||
"hair_top": pt("hair_top"),
|
||
"hairline": pt("hairline"),
|
||
"brow_center": pt("brow_center"),
|
||
"nose_bottom": pt("nose_bottom"),
|
||
"chin_tip": pt("chin_tip"),
|
||
},
|
||
"hairline_source": self.hairline_source,
|
||
}
|
||
# left/right_position：mediapipe 21/251 号定位点（原图像素，与 landmarks 同坐标系）。
|
||
# landmarks 缺省（如测试直构 MeasureResult）时不输出，保持向后兼容。
|
||
if self.landmarks is not None and self.w and self.h:
|
||
lm = _lm_list(self.landmarks)
|
||
|
||
def _pt_lm(idx):
|
||
px, py = normalized_to_pixel(lm[idx], self.w, self.h)
|
||
return {"x": int(round(px)), "y": int(round(py))}
|
||
|
||
data["left_position"] = _pt_lm(LEFT_POSITION)
|
||
data["right_position"] = _pt_lm(RIGHT_POSITION)
|
||
if self.head_pose is not None:
|
||
yaw, pitch, roll = self.head_pose
|
||
data["head_pose"] = {
|
||
"yaw": round(yaw, 2), "pitch": round(pitch, 2), "roll": round(roll, 2),
|
||
}
|
||
return data
|
||
|
||
|
||
def measure_face(landmarks, hair_mask, image_width, image_height, head_pose=None):
|
||
"""主入口：纵向决策 + 七眼 + 尺度换算 → MeasureResult。"""
|
||
vertical, source = decide_vertical(landmarks, image_width, image_height, hair_mask)
|
||
eyes = measure_seven_eyes(landmarks, image_width, image_height)
|
||
px_per_cm = estimate_scale_factor(landmarks, image_width, image_height)
|
||
return MeasureResult(vertical, eyes, px_per_cm, source, head_pose,
|
||
landmarks, image_width, image_height)
|
||
|
||
|
||
if __name__ == "__main__":
|
||
import sys
|
||
import json
|
||
import cv2
|
||
from face_analysis.detector import detector
|
||
from face_analysis.pose import estimate_head_pose
|
||
|
||
path = sys.argv[1] if len(sys.argv) > 1 else "tests/fixtures/frontal.jpg"
|
||
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)
|
||
|
||
# 尝试分割（若 torch 不可用则走方案 A）
|
||
mask = None
|
||
try:
|
||
from face_analysis.hair_segmenter import get_segmenter
|
||
mask = get_segmenter().segment_hair(img)
|
||
except Exception as e: # noqa: BLE001
|
||
print(f"[warn] 分割不可用，回退方案 A：{e}")
|
||
|
||
pose = estimate_head_pose(lms, w, h)
|
||
result = measure_face(lms, mask, w, h, head_pose=pose)
|
||
print(json.dumps(result.to_response(), ensure_ascii=False, indent=2))
|