从色调饱和度直方图中检测皮肤 - OpenCV Python

时间:2013-05-15 09:35:31

标签: python opencv computer-vision histogram

我正在使用python中的一个小程序来估计单眼相机的2D图像指向手势的方向,而我正在使用OpenCV 2.3。 我知道这有点棘手,但我很有动力! :) 我的方法是使用面部检测来检测我确定皮肤很多的区域:

img = cv2.imread("/home/max/recordings/cameras/imageTEST.jpg",1)
img_hsv = cv2.cvtColor(img,cv2.COLOR_BGR2HSV)
hc1 = cv2.CascadeClassifier("/home/max/haarcascade_frontalface_alt.xml")
faces1 = hc1.detectMultiScale(img)
for (x,y,w,h) in faces1:
  cv2.rectangle(img, (x,y), (x+w,y+h), 255)
crop_img = img[y+2:y+w, x+2:x+h]

我真的想使用这种方法,因为我希望我的检测对光变化很稳健。然后我计算检测到的面部图像的色调饱和度直方图进行反投影:

roihist = cv2.calcHist([crop_img],[0,1], None, [180, 256], [0, 180, 0, 256] )
dst = cv2.calcBackProject([img],[0,1],roihist,[0,180,0,256],1)

最后,我可以用阈值对图片进行二值化,并跟踪头部和手部斑点以估计指向的方向。 我的代码没有问题但是没有检测到皮肤...... 我究竟做错了什么? 谢谢你的帮助!

最高

2 个答案:

答案 0 :(得分:0)

您是否尝试过使用YCbCr格式的Cr频道?当我以前使用肤色进行手部检测时,我对Cr运气不错。此外,还有this paper,它使用一种很好的方法来检测手部。但请记住,只要您使用肤色,检测就不适用于所有手,但可以针对给定用户或一群用户进行调整。

答案 1 :(得分:0)

我最近一直在研究网上可用的opencv示例(只是为了好玩的基本内容)。我已经从脸部识别(有趣的,但我喜欢的太黑的盒子)中移动到手动选择HSV空间中的roi,然后使用'camshift'来跟踪。我仍然得到我不理解的变量结果所以我还绘制了所有中间处理窗口,例如hsv图像和backproject图像,还绘制了窗口的直方图。突然之间一切都很清楚了 - 你可以确切地看到计算机正在尝试使用它。

这是我的python3.4,opencv3的工作代码。您可以手动选择皮肤。主要归功于我在网上找到的其他例子。

'cv2.calcBAckProject'功能可以很好地阈化皮肤特征。

hsv and backproject

import numpy as np
import cv2

roiPts = []
track_mode = False
termination = (cv2.TERM_CRITERIA_EPS | cv2.TERM_CRITERIA_COUNT, 10, 1)
roiBox = None
kernel = np.ones((5, 5), np.uint8)
frame_width_in_px = 640
number_of_histogram_elements=16

def selectROI(event, x,y,flags,param):
    global track_mode, roiPts

    if (event == cv2.EVENT_LBUTTONDOWN) and (len(roiPts)==4): #reselecting ROI points so take out of tracking mode and empty current roipoints
        roiPts=[]
        track_mode = False
    if (event==cv2.EVENT_LBUTTONDOWN) and (len(roiPts) < 4): #ROI point selection
        roiPts.append([x, y])

cap = cv2.VideoCapture(0)
cv2.namedWindow("frame")
cv2.setMouseCallback("frame", selectROI)

while True:
    ret, frame = cap.read()

    if len(roiPts)<=4 and len(roiPts)>0:
        for x,y in roiPts:
            cv2.circle(frame, (x,y), 4, (0, 255, 0), 1)  # draw small circle for each roi click

    if len(roiPts)==4 and track_mode==False: #initialize the camshift
        # convert the selected points to a box shape
        roiBox = np.array(roiPts, dtype=np.int32)
        s = roiBox.sum(axis=1)
        tl = roiBox[np.argmin(s)]
        br = roiBox[np.argmax(s)]

        #extract the roi from the image and calculate the histograme
        roi = frame[tl[1]:br[1], tl[0]:br[0]]
        roi = cv2.cvtColor(roi, cv2.COLOR_BGR2HSV) #
        roiHist = cv2.calcHist([roi], [0], None, [number_of_histogram_elements], [0, 180])
        roiHist = cv2.normalize(roiHist, roiHist, 0, 255, cv2.NORM_MINMAX)
        roiBox = (tl[0], tl[1], br[0], br[1])
        track_mode = True #ready for camshift

    if track_mode == True: #tracking mode
        hsv = cv2.cvtColor(frame, cv2.COLOR_BGR2HSV)
        backProj = cv2.calcBackProject([hsv], [0], roiHist, [0, 180], 1)
        #perfrom some noise reduction and smoothing
        erosion = cv2.erode(backProj, kernel, iterations=2)
        dilate = cv2.dilate(erosion, kernel, iterations=2)
        (r, roiBox) = cv2.CamShift(dilate, roiBox, termination) #this takes prev roiBox and calculates the new roiBox
        pts = np.int0(cv2.boxPoints(r))
        cv2.polylines(frame, [pts], True, (0, 255, 0), 2) #tracking box
        cv2.polylines(backProj, [pts], True, (0, 255, 0), 2) #tracking box
        cv2.polylines(dilate, [pts], True, (0, 255, 0), 2) #tracking box
        cv2.polylines(hsv, [pts], True, (0, 255, 0), 2) #tracking box

        # plot histogram polyline across the windows
        x = np.linspace(0,640,number_of_histogram_elements,dtype=np.int32)
        y = roiHist.flatten().astype(np.int32, copy=False)-255 #note frame height needs to be greater than 255 which is the max histo value
        y=np.absolute(y)
        pts2 = np.stack((x, y), axis=1)
        cv2.polylines(frame, [pts2], False, (0, 255, 0), 2)
        cv2.polylines(hsv, [pts2], False, (0, 255, 0), 2)

        cv2.imshow("backproject", backProj)
        cv2.imshow("dilate", dilate)
        cv2.imshow("hsv", hsv)

    cv2.imshow("frame", frame)

    if cv2.waitKey(1) & 0xFF == ord('q'):
        break

# When everything done, release the capture
cap.release()
cv2.destroyAllWindows()