簡(jiǎn)介
在這篇文章中我將介紹如何寫一個(gè)簡(jiǎn)短(200行)的 Python 腳本,來自動(dòng)地將一幅圖片的臉替換為另一幅圖片的臉。
這個(gè)過程分四步:
檢測(cè)臉部標(biāo)記。
旋轉(zhuǎn)、縮放、平移和第二張圖片,以配合第一步。
調(diào)整第二張圖片的色彩平衡,以適配第一張圖片。
把第二張圖像的特性混合在第一張圖像中。
公眾號(hào)后臺(tái)回復(fù):“換臉”,獲取程序完整代碼。
1.使用dlib提取面部標(biāo)記
該腳本使用dlib的 Python 綁定來提取面部標(biāo)記:
Dlib 實(shí)現(xiàn)了 Vahid Kazemi 和 Josephine Sullivan 的《使用回歸樹一毫秒臉部對(duì)準(zhǔn)》論文中的算法。算法本身非常復(fù)雜,但dlib接口使用起來非常簡(jiǎn)單:
PREDICTOR_PATH ="/home/matt/dlib-18.16/shape_predictor_68_face_landmarks.
dat"detector = dlib.get_frontal_face_detector()predictor = dlib.
shape_predictor(PREDICTOR_PATH)defget_landmarks(im):
rects = detector(im,1) iflen(rects) >1:
raiseTooManyFaces iflen(rects) ==0:
raiseNoFaces returnnumpy.matrix([[p.x, p.
y]forpinpredictor(im, rects[0]).parts()])
get_landmarks()函數(shù)將一個(gè)圖像轉(zhuǎn)化成numpy數(shù)組,并返回一個(gè)68×2元素矩陣,輸入圖像的每個(gè)特征點(diǎn)對(duì)應(yīng)每行的一個(gè)x,y坐標(biāo)。
特征提取器(predictor)需要一個(gè)粗糙的邊界框作為算法輸入,由一個(gè)傳統(tǒng)的能返回一個(gè)矩形列表的人臉檢測(cè)器(detector)提供,其每個(gè)矩形列表在圖像中對(duì)應(yīng)一個(gè)臉。
2.用 Procrustes 分析調(diào)整臉部
現(xiàn)在我們已經(jīng)有了兩個(gè)標(biāo)記矩陣,每行有一組坐標(biāo)對(duì)應(yīng)一個(gè)特定的面部特征(如第30行的坐標(biāo)對(duì)應(yīng)于鼻頭)。我們現(xiàn)在要解決如何旋轉(zhuǎn)、翻譯和縮放第一個(gè)向量,使它們盡可能適配第二個(gè)向量的點(diǎn)。一個(gè)想法是可以用相同的變換在第一個(gè)圖像上覆蓋第二個(gè)圖像。
將這個(gè)問題數(shù)學(xué)化,尋找T,s和R,使得下面這個(gè)表達(dá)式:
結(jié)果最小,其中R是個(gè)2×2正交矩陣,s是標(biāo)量,T是二維向量,pi和qi是上面標(biāo)記矩陣的行。
事實(shí)證明,這類問題可以用“常規(guī) Procrustes 分析法”解決:
deftransformation_from_points(points1, points2):
points1 = points1.astype(numpy.float64)
points2 = points2.astype(numpy.float64)
c1 = numpy.mean(points1, axis=0)
c2 = numpy.mean(points2, axis=0)
points1 -= c1
points2 -= c2
s1 = numpy.std(points1)
s2 = numpy.std(points2)
points1 /= s1
points2 /= s2
U, S, Vt = numpy.linalg.svd(points1.T *
points2)
R = (U * Vt).T
returnnumpy.vstack([numpy.hstack(((s2 / s1) * R,
c2.T - (s2 / s1) * R * c1.T)),
numpy.matrix([0.,0.,1.])])
代碼實(shí)現(xiàn)了這幾步:
1.將輸入矩陣轉(zhuǎn)換為浮點(diǎn)數(shù)。這是后續(xù)操作的基礎(chǔ)。
2.每一個(gè)點(diǎn)集減去它的矩心。一旦為點(diǎn)集找到了一個(gè)最佳的縮放和旋轉(zhuǎn)方法,這兩個(gè)矩心c1和c2就可以用來找到完整的解決方案。
3.同樣,每一個(gè)點(diǎn)集除以它的標(biāo)準(zhǔn)偏差。這會(huì)消除組件縮放偏差的問題。
4.使用奇異值分解計(jì)算旋轉(zhuǎn)部分??梢栽诰S基百科上看到關(guān)于解決正交 Procrustes 問題的細(xì)節(jié)。
5.利用仿射變換矩陣返回完整的轉(zhuǎn)化。
其結(jié)果可以插入 OpenCV 的cv2.warpAffine函數(shù),將圖像二映射到圖像一:
def warp_im(im, M, dshape):
output_im = numpy.zeros(dshape, dtype=im.dtype) cv2.warpAffine(im,
M[:2],
(dshape[1], dshape[0]),
dst=output_im,
borderMode=cv2.BORDER_TRANSPARENT,
flags=cv2.WARP_INVERSE_MAP) returnoutput_im
對(duì)齊結(jié)果如下:
3.校正第二張圖像的顏色
如果我們?cè)噲D直接覆蓋面部特征,很快會(huì)看到這個(gè)問題:
這個(gè)問題是兩幅圖像之間不同的膚色和光線造成了覆蓋區(qū)域的邊緣不連續(xù)。我們?cè)囍拚?/p>
COLOUR_CORRECT_BLUR_FRAC =0.6LEFT_EYE_POINTS = list(range(42,48))RIGHT_EYE_POINTS = list(range(36,42))def correct_colours(im1, im2, landmarks1):
blur_amount = COLOUR_CORRECT_BLUR_FRAC * numpy.linalg.norm(
numpy.mean(landmarks1[LEFT_EYE_POINTS], axis=0) -
numpy.mean(landmarks1[RIGHT_EYE_POINTS], axis=0))
blur_amount =int(blur_amount) ifblur_amount %2==0:
blur_amount +=1 im1_blur = cv2.GaussianBlur(im1, (blur_amount, blur_amount),0)
im2_blur = cv2.GaussianBlur(im2, (blur_amount, blur_amount),0)
# Avoid divide-by-zero errors. im2_blur +=128* (im2_blur <=1.0)?
return(im2.astype(numpy.float64) * im1_blur.astype(numpy.float64)
/
im2_blur.astype(numpy.float64))
結(jié)果如下:
此函數(shù)試圖改變 im2 的顏色來適配 im1。它通過用 im2 除以 im2 的高斯模糊值,然后乘以im1的高斯模糊值。這里的想法是用RGB縮放校色,但并不是用所有圖像的整體常數(shù)比例因子,每個(gè)像素都有自己的局部比例因子。
用這種方法兩圖像之間光線的差異只能在某種程度上被修正。例如,如果圖像1是從一側(cè)照亮,但圖像2是被均勻照亮的,色彩校正后圖像2也會(huì)出現(xiàn)未照亮一側(cè)暗一些的問題。
也就是說,這是一個(gè)相當(dāng)簡(jiǎn)陋的辦法,而且解決問題的關(guān)鍵是一個(gè)適當(dāng)?shù)母咚购撕瘮?shù)大小。如果太小,第一個(gè)圖像的面部特征將顯示在第二個(gè)圖像中。過大,內(nèi)核之外區(qū)域像素被覆蓋,并發(fā)生變色。這里的內(nèi)核用了一個(gè)0.6 *的瞳孔距離。
4.把第二張圖像的特征混合在第一張圖像中
用一個(gè)遮罩來選擇圖像2和圖像1的哪些部分應(yīng)該是最終顯示的圖像:
值為1(顯示為白色)的地方為圖像2應(yīng)該顯示出的區(qū)域,值為0(顯示為黑色)的地方為圖像1應(yīng)該顯示出的區(qū)域。值在0和1之間為圖像1和圖像2的混合區(qū)域。
這是生成上圖的代碼:
LEFT_EYE_POINTS = list(range(42,48))RIGHT_EYE_POINTS = list(range(36,42))
LEFT_BROW_POINTS = list(range(22,27))RIGHT_BROW_POINTS = list(range(17,22))
NOSE_POINTS = list(range(27,35))MOUTH_POINTS = list(range(48,61))
OVERLAY_POINTS = [ LEFT_EYE_POINTS + RIGHT_EYE_POINTS + LEFT_BROW_POINTS + RIGHT_BROW_POINTS,
NOSE_POINTS + MOUTH_POINTS,]FEATHER_AMOUNT =11def draw_convex_hull(im, points, color):
points = cv2.convexHull(points)
cv2.fillConvexPoly(im, points, color=color)def get_face_mask(im, landmarks):
im = numpy.zeros(im.shape[:2], dtype=numpy.float64)
forgroup in OVERLAY_POINTS:
draw_convex_hull(im,
landmarks[group],
color=1) im = numpy.array([im, im, im]).transpose((1,2,0))
im = (cv2.GaussianBlur(im, (FEATHER_AMOUNT, FEATHER_AMOUNT),0) >0) *1.0
im = cv2.GaussianBlur(im, (FEATHER_AMOUNT, FEATHER_AMOUNT),0)
returnimmask = get_face_mask(im2, landmarks2)warped_mask = warp_im(mask, M,
im1.shape)combined_mask = numpy.max([get_face_mask(im1, landmarks1),
warped_mask],
axis=0)
我們把上述過程分解:
get_face_mask()的定義是為一張圖像和一個(gè)標(biāo)記矩陣生成一個(gè)遮罩,它畫出了兩個(gè)白色的凸多邊形:一個(gè)是眼睛周圍的區(qū)域,一個(gè)是鼻子和嘴部周圍的區(qū)域。之后它由11個(gè)像素向遮罩的邊緣外部羽化擴(kuò)展,可以幫助隱藏任何不連續(xù)的區(qū)域。
這樣一個(gè)遮罩同時(shí)為這兩個(gè)圖像生成,使用與步驟2中相同的轉(zhuǎn)換,可以使圖像2的遮罩轉(zhuǎn)化為圖像1的坐標(biāo)空間。
之后,通過一個(gè)element-wise最大值,這兩個(gè)遮罩結(jié)合成一個(gè)。結(jié)合這兩個(gè)遮罩是為了確保圖像1被掩蓋,而顯現(xiàn)出圖像2的特性。
最后,使用遮罩得到最終的圖像:
output_im= im1 * (1.0- combined_mask) + warped_corrected_im2 * combined_mask
完整代碼(link):
import cv2import dlibimport numpyimport sysPREDICTOR_PATH ="/home/matt/dlib-18.16/shape_predictor_68_face_landmarks.
dat"SCALE_FACTOR =1FEATHER_AMOUNT =11FACE_POINTS =list(range(17,68))MOUTH_POINTS =list(range(48,61))
RIGHT_BROW_POINTS =list(range(17,22))LEFT_BROW_POINTS =list(range(22,27))
RIGHT_EYE_POINTS =list(range(36,42))LEFT_EYE_POINTS =list(range(42,48))NOSE_POINTS =list(range(27,35))JAW_POINTS =list(range(0,17))#
Points usedtolineupthe images.ALIGN_POINTS = (LEFT_BROW_POINTS + RIGHT_EYE_POINTS + LEFT_EYE_POINTS +
RIGHT_BROW_POINTS + NOSE_POINTS + MOUTH_POINTS)#
Points from the second imagetooverlayonthefirst.
The convex hull of each# element willbeoverlaid.
OVERLAY_POINTS = [ LEFT_EYE_POINTS + RIGHT_EYE_POINTS + LEFT_BROW_POINTS + RIGHT_BROW_POINTS, NOSE_POINTS + MOUTH_POINTS,]
# Amount of blurtouse during colour correction,asafraction of the#
pupillary distance.COLOUR_CORRECT_BLUR_FRAC =0.6detector = dlib.get_frontal_face_detector()predictor = dlib.
shape_predictor(PREDICTOR_PATH)class TooManyFaces(Exception):
passclass NoFaces(Exception):
passdef get_landmarks(im):
rects = detector(im,1) iflen(rects) >1:
raise TooManyFaces iflen(rects) ==0:
raise NoFaces returnnumpy.matrix([[p.x,p.y]forpin predictor(im, rects[0]).
parts()])def annotate_landmarks(im, landmarks): im=im.copy() foridx, point in enumerate(landmarks):
pos = (point[0,0], point[0,1])
cv2.putText(im, str(idx), pos,
fontFace=cv2.FONT_HERSHEY_SCRIPT_SIMPLEX,
fontScale=0.4,
color=(0,0,255))
cv2.circle(im, pos,3, color=(0,255,255)) returnimdef draw_convex_hull(im, points, color):
points = cv2.convexHull(points) cv2.fillConvexPoly(im, points, color=color)def get_face_mask(im, landmarks): im= numpy.zeros(im.shape[:2], dtype=numpy.float64) forgroup in OVERLAY_POINTS:
draw_convex_hull(im,
landmarks[group],
color=1) im= numpy.array([im,im,im]).transpose((1,2,0))
im= (cv2.GaussianBlur(im, (FEATHER_AMOUNT, FEATHER_AMOUNT),0) >0) *1.0 im= cv2.GaussianBlur(im, (FEATHER_AMOUNT, FEATHER_AMOUNT),0) returnimdef transformation_from_points(points1, points2):
""" Returnanaffine transformation [s * R | T] such that:
sum ||s*R*p1,i + T - p2,i||^2 isminimized. """
# Solve the procrustes problem by subtracting centroids, scaling by the
# standard deviation,andthen using the SVDtocalculate the rotation. See
# the followingformore details:
# https://en.wikipedia.org/wiki/Orthogonal_Procrustes_problem
points1 = points1.astype(numpy.float64)
points2 = points2.astype(numpy.float64)
c1 = numpy.mean(points1, axis=0)
c2 = numpy.mean(points2, axis=0)
points1 -= c1
points2 -= c2
s1 = numpy.std(points1)
s2 = numpy.std(points2)
points1 /= s1
points2 /= s2
U, S, Vt = numpy.linalg.svd(points1.T * points2)
# The R we seekisin fact the transpose of the one given by U * Vt.
This
#isbecause the above formulation assumes the matrix goesontheright
# (with row vectors) whereasour solution requires the matrixtobeonthe
#left(with column vectors).
R = (U * Vt).T returnnumpy.vstack([numpy.hstack(((s2 / s1) * R,
c2.T - (s2 / s1) * R * c1.T)),
numpy.matrix([0.,0.,1.])])def read_im_and_landmarks(fname):
im= cv2.imread(fname, cv2.IMREAD_COLOR) im= cv2.resize(im, (im.shape[1] * SCALE_FACTOR,
im.shape[0] * SCALE_FACTOR))
s = get_landmarks(im) returnim, sdef warp_im(im, M, dshape): output_im = numpy.zeros(dshape, dtype=im.dtype)
cv2.warpAffine(im,
M[:2],
(dshape[1], dshape[0]),
dst=output_im,
borderMode=cv2.BORDER_TRANSPARENT,
flags=cv2.WARP_INVERSE_MAP) returnoutput_imdef correct_colours(im1, im2, landmarks1):
blur_amount = COLOUR_CORRECT_BLUR_FRAC * numpy.linalg.norm(
numpy.mean(landmarks1[LEFT_EYE_POINTS], axis=0) -
numpy.mean(landmarks1[RIGHT_EYE_POINTS], axis=0))
blur_amount =int(blur_amount) ifblur_amount %2==0:
blur_amount +=1 im1_blur = cv2.GaussianBlur(im1, (blur_amount, blur_amount),0) im2_blur = cv2.GaussianBlur(im2, (blur_amount, blur_amount),0)
# Avoid divide-by-zero errors.
im2_blur +=128* (im2_blur <=1.0)? ?return(im2.astype(numpy.float64) * im1_blur.astype(numpy.float64) /? ? ? ? ? ? ? ? ? ? ? ? ? ?
im2_blur.astype(numpy.float64))im1, landmarks1 = read_im_and_landmarks(sys.argv[1])
im2, landmarks2 = read_im_and_landmarks(sys.argv[2])M = transformation_from_points(landmarks1[ALIGN_POINTS],
landmarks2[ALIGN_POINTS])mask = get_face_mask(im2, landmarks2)warped_mask = warp_im(mask, M, im1.shape)combined_mask = numpy.max([get_face_mask(im1, landmarks1), warped_mask],
axis=0)warped_im2 = warp_im(im2, M, im1.shape)warped_corrected_im2 = correct_colours(im1, warped_im2, landmarks1)output_im = im1 *
(1.0- combined_mask) + warped_corrected_im2 *
combined_maskcv2.imwrite('output.jpg', output_im)
-
圖像
+關(guān)注
關(guān)注
2文章
1078瀏覽量
40345 -
python
+關(guān)注
關(guān)注
54文章
4758瀏覽量
84289
原文標(biāo)題:如何用200行Python代碼做了一個(gè)換臉程序?
文章出處:【微信號(hào):WUKOOAI,微信公眾號(hào):悟空智能科技】歡迎添加關(guān)注!文章轉(zhuǎn)載請(qǐng)注明出處。
發(fā)布評(píng)論請(qǐng)先 登錄
相關(guān)推薦
評(píng)論