倾斜头检测失败了，但在现场流中成功

Question

我正在研究一个项目，需要从图像中检测到面部并将其存储到目录以进行进一步使用。 我正在使用openCV（haar_cascade_classifier） 它仅检测到直头。为了检测倾斜的头。我尝试了音调版本haar_cascade.但是问题仅在实时视频中检测到面。如果我运行web camera并使用haar_cascade_classifier_atl2.xml文件检测。它检测到倾斜的头部，但是如果我从图像目录中运行循环并传递图像以检测面部，则不会检测到相同的角度。意味着在视频中检测到，而不是从图像（相同角度）中检测到的。 这是代码，

import cv2
from math import sin, cos, radians
import time
import fnmatch
import os

total_number_of_frame = 0
framedirectory = "D:/finalpaper/extractedframes"
number_of_extracted_frames = len(fnmatch.filter(os.listdir('D:/finalpaper/extractedframes'), '*.png'))
print(number_of_extracted_frames)
face = cv2.CascadeClassifier(cv2.data.haarcascades + "haarcascade_frontalface_alt2.xml")

settings = {
    'scaleFactor': 1.3,
    'minNeighbors': 3,
    'minSize': (50, 50)
}

def rotate_image(image, angle):
    if angle == 0: return image
    height, width = image.shape[:2]
    rot_mat = cv2.getRotationMatrix2D((width/2, height/2), angle, 0.9)
    result = cv2.warpAffine(image, rot_mat, (width, height), flags=cv2.INTER_LINEAR)
    return result

def rotate_point(pos, img, angle):
    if angle == 0: return pos
    x = pos[0] - img.shape[1]*0.4
    y = pos[1] - img.shape[0]*0.4
    newx = x*cos(radians(angle)) + y*sin(radians(angle)) + img.shape[1]*0.4
    newy = -x*sin(radians(angle)) + y*cos(radians(angle)) + img.shape[0]*0.4
    return int(newx), int(newy), pos[2], pos[3]

for i in range(number_of_extracted_frames):
    framenumber = str(i)+".png"
    #joining path to directory
    filepath = os.path.join(framedirectory,framenumber)
    frame = cv2.imread(filepath)
    for angle in [0, -25, 25]:
        rimg = rotate_image(frame, angle)
        detected = face.detectMultiScale(rimg, **settings)
        if len(detected):
            detected = [rotate_point(detected[-1], frame, -angle)]
        break

     # Make a copy as we don't want to draw on the original image:
    for x, y, w, h in detected[-1:]:
        cv2.rectangle(frame, (x, y), (x+w, y+h), (255,0,0), 2)


    cv2.imshow("frame",frame)
    cv2.waitKey(700)

如果我使用的代码与Web摄像机一起运行，则它会检测到面部，但是如果我使用的循环未检测到倾斜头。