Face detection with Python + OpenCV (rotation invariant)

Face detection while rotating the image I haven't adjusted the best angle If necessary, refer to the following

Simple face detection API with Heroku + OpenCV

I want you to rotate the filter instead of the input image and detect it automatically ...

Fitting point

It may be natural for people who are accustomed to image processing, but since I have hardly done it, I am quite addicted to it.

The order may be different when acquiring and specifying the height and width of the image.

--shape… height (rows), width (columns) --Slice by index ... [Lower height (y): Upper limit height (y + h), Lower limit width (x): Upper limit width (x + w)] --OpenCV coordinate specification (center point, etc.) ... (horizontal (x), vertical (y))

The coordinate system of the display has a downward y-axis, but the angle is counterclockwise, so when the normal y-axis is converted to an upward coordinate system, it rotates clockwise.

code

`face_rotate_detect.py`


# -*- coding: utf-8 -*-

from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

import cv2, os, sys, imghdr, shutil, math
import numpy as np

CWD = os.getcwd()
DIR_ORIGIN = CWD + '/images/'
DIR_DESTINATION = CWD + '/faces/'

classifier = cv2.CascadeClassifier('{python_dir}/{classifier_dir}/haarcascade_frontalface_alt2.xml'.format(
    python_dir = os.path.split(sys.executable)[0],
    classifier_dir = '../share/OpenCV/haarcascades',
))

def getFaces(path_full):
    results = []
    image = cv2.imread(path_full)
    gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
    rows, cols, colors = image.shape
    center = tuple(np.array([cols, rows]))
    # get rotations
    for angle in range(-90, 91, 5):
        radian = np.deg2rad(angle)
        output_height = int(np.absolute(cols * np.sin(radian)) + np.absolute(rows * np.cos(radian)))
        output_width = int(np.absolute(cols * np.cos(radian)) + np.absolute(rows * np.sin(radian)))
        output_size = tuple(np.array([output_width, output_height]))
        # rotate
        Matrix = cv2.getRotationMatrix2D(center, degree, 1.0)
        # translate
        Matrix[0, 2] += (output_width - width) * 0.5
        Matrix[1, 2] += (output_height - height) * 0.5
        # warp affine
        rotated = cv2.warpAffine(gray, Matrix, output_size, flags = cv2.INTER_LINEAR)
        # detect faces
        faces = classifier.detectMultiScale(rotated)
        if len(faces):
            rotated_color = cv2.warpAffine(image, Matrix, output_size, flags = cv2.INTER_LINEAR)
            for x, y, w, h in faces:
                results.append(rotated_color[y : y + h, x : x + w])
    return results

def saveFaces(faces):
    global count

    for face in faces:
        cv2.imwrite(
            '{dir_destination}{count}.jpg'.format(dir_destination = DIR_DESTINATION, count = count),
            face,
            [cv2.IMWRITE_JPEG_QUALITY, 100]
        )
        count += 1

count = 1
for path, subdirs, files in os.walk(DIR_ORIGIN):
    for name in files:
        path_full = os.path.join(path, name)
        if imghdr.what(path_full) in ['jpeg']:
            saveFaces(getFaces(path_full))
            print(path_full)