【Ubuntu】【Python】dlibを用いて顔器官検出

今のところdlibにはあって、OpenCVには無い顔器官検出。

とりあえず、無理やり色付けしたけど、もっとスマートな方法があるはず。
というか、リファレンスをしっかり読み込んでいないだけだと思いますが。。。

動画は以下。
顔を出すのは恥ずかしいので顔検出を用いて隠しております。
youtu.be

ソースコードは以下。
動作させるには、pyファイルと同じディレクトリに顔器官の学習済みデータを
配置する必要があります。
→shape_predictor_68_face_landmarks.dat（http://dlib.net/files/shape_predictor_68_face_landmarks.dat.bz2）

#!/usr/bin/env python
# -*- coding: utf-8 -*-

'''
face_landmark_detector.py.

Usage:
  face_landmark_detector.py [<video source>] [<resize rate>] [<privacy mask>]
'''

import sys
import dlib
import cv2
import time
import copy

try:
    fn = sys.argv[1]
    if fn.isdigit() == True:
        fn = int(fn)
except:
    fn = 0

try:
    resize_rate = sys.argv[2]
    resize_rate = int(resize_rate)
except:
    resize_rate = 1

try:
    privacy_mask = sys.argv[3]
    privacy_mask = int(privacy_mask)
except:
    privacy_mask = 0

predictor_path = "./shape_predictor_68_face_landmarks.dat"

detector = dlib.get_frontal_face_detector()
predictor = dlib.shape_predictor(predictor_path)

video_input = cv2.VideoCapture(fn)

while(video_input.isOpened() == True):
    ret, frame = video_input.read()
    temp_frame = copy.deepcopy(frame)

    # 処理負荷軽減のための対象フレーム縮小（引数指定時）
    height, width = frame.shape[:2]
    temp_frame = cv2.resize(frame, (int(width/resize_rate), int(height/resize_rate)))

    # 顔検出
    start = time.time()
    dets = detector(temp_frame, 1)
    elapsed_time = time.time() - start
    print ("detector processing time:{0}".format(elapsed_time)) + "[sec]"

    for k, d in enumerate(dets):
        print("Detection {}: Left: {} Top: {} Right: {} Bottom: {}".format(
            k, d.left(), d.top(), d.right(), d.bottom()))

        # 顔器官検出
        start = time.time()
        shape = predictor(temp_frame, d)
        elapsed_time = time.time() - start
        print ("predictor processing time:{0}".format(elapsed_time)) + "[sec]"

        # 描画
        rect_offset = 20
        if privacy_mask == 1:
            cv2.rectangle(frame, (int(d.left() * resize_rate) - rect_offset, int(d.top() * resize_rate) - rect_offset), \
                (int(d.right() * resize_rate) + rect_offset, int(d.bottom() * resize_rate) + rect_offset), (255, 255, 255), -1)

        for shape_point_count in range(shape.num_parts):
            shape_point = shape.part(shape_point_count)
            if shape_point_count < 17: # [0-16]:輪郭
                cv2.circle(frame, (int(shape_point.x * resize_rate), int(shape_point.y * resize_rate)), 2, (0, 0, 255), -1)
            elif shape_point_count < 22: # [17-21]眉（右）
                cv2.circle(frame, (int(shape_point.x * resize_rate), int(shape_point.y * resize_rate)), 2, (0, 255, 0), -1)
            elif shape_point_count < 27: # [22-26]眉（左）
                cv2.circle(frame, (int(shape_point.x * resize_rate), int(shape_point.y * resize_rate)), 2, (255, 0, 0), -1)
            elif shape_point_count < 31: # [27-30]鼻背
                cv2.circle(frame, (int(shape_point.x * resize_rate), int(shape_point.y * resize_rate)), 2, (0, 255, 255), -1)
            elif shape_point_count < 36: # [31-35]鼻翼、鼻尖
                cv2.circle(frame, (int(shape_point.x * resize_rate), int(shape_point.y * resize_rate)), 2, (255, 255, 0), -1)
            elif shape_point_count < 42: # [36-4142目47）
                cv2.circle(frame, (int(shape_point.x * resize_rate), int(shape_point.y * resize_rate)), 2, (255, 0, 255), -1)
            elif shape_point_count < 48: # [42-47]目（左）
                cv2.circle(frame, (int(shape_point.x * resize_rate), int(shape_point.y * resize_rate)), 2, (0, 0, 128), -1)
            elif shape_point_count < 55: # [48-54]上唇（上側輪郭）
                cv2.circle(frame, (int(shape_point.x * resize_rate), int(shape_point.y * resize_rate)), 2, (0, 128, 0), -1)
            elif shape_point_count < 60: # [54-59]下唇（下側輪郭）
                cv2.circle(frame, (int(shape_point.x * resize_rate), int(shape_point.y * resize_rate)), 2, (128, 0, 0), -1)
            elif shape_point_count < 65: # [60-64]上唇（下側輪郭）
                cv2.circle(frame, (int(shape_point.x * resize_rate), int(shape_point.y * resize_rate)), 2, (0, 128, 255), -1)
            elif shape_point_count < 68: # [65-67]下唇（上側輪郭）
                cv2.circle(frame, (int(shape_point.x * resize_rate), int(shape_point.y * resize_rate)), 2, (128, 255, 0), -1)

    cv2.imshow('face landmark detector', frame)

    c = cv2.waitKey(50) & 0xFF

    if c==27: # ESC
        break

video_input.release()
cv2.destroyAllWindows()

以上。