私的AI研究会 > OpenCV3
「Python画像処理100 (Interface 2021年1月号)」CQ出版社刊 のサンプルコードを中心に検証をしてみる。
OpenVINO™ ツールキットをインストールした環境で検証する。
pi@raspberrypi:~ $ python3 Python 3.7.3 (default, Jul 25 2020, 13:03:44) [GCC 8.3.0] on linux Type "help", "copyright", "credits" or "license" for more information. >>> import cv2 >>> cv2.__version__ '4.5.1-openvino' >>> quit()
pi@raspberrypi:~ $ ls Bookshelf Desktop Documents Downloads Music Pictures Public Templates Videos build cq workspace
~cq $ vi matchtemplate.py
# -*- coding: utf-8 -*-
import cv2
import numpy as np
import time
def __main():
img = cv2.imread('image/IMG_1630_2.jpg')
temple = cv2.imread('image/IMG_1630_2_T.jpg')
h, w, _ = temple.shape
timeStart = time.time()
result = cv2.matchTemplate(image=img, templ=temple, method=cv2.TM_CCOEFF)
timeEnd = time.time()
print("{0} = {1}".format('CPU', (timeEnd - timeStart) * 1000) + "/ms")
# 配列内のグローバルな最小値と最大値を見つける minLoc=最も類似する座標 maxLoc=最も類似しない座標
minVal, maxVal, minLoc, maxLoc = cv2.minMaxLoc(result)
x, y = maxLoc
color = np.array([0., 255., 255.]) # BGR表記
cv2.rectangle(img=img, pt1=(x, y), pt2=(x + w, y + h), color=color, thickness=3)
cv2.imshow('Final result', img)
cv2.imshow('Template', temple)
cv2.waitKey(0)
cv2.destroyAllWindows()
return 0
if __name__ == '__main__':
print(cv2.__version__)
__main()
~cq $ vi multimatchtemplate.py
# -*- coding: utf-8 -*-
import cv2
import time
import numpy as np
def __main():
img = cv2.imread("image/IMG_1618_2.JPG")
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
temple = cv2.imread("image/IMG_1621_T.jpg")
temple = cv2.cvtColor(temple, cv2.COLOR_BGR2GRAY)
h1, w1 = temple.shape
timeStart = time.time()
# ここから処理を実行する
result = cv2.matchTemplate(gray, temple, cv2.TM_CCOEFF_NORMED)
threshold = 0.8
location = np.where(result >= threshold) # 条件を満たす要素のインデックス（位置）を返す。
for x, y in zip(*location[::-1]):
cv2.rectangle(img, pt1=(x, y), pt2=(x + w1, y + h1), color=(0, 255, 255), thickness=1)
timeEnd = time.time()
print("{0} = {1}".format('CPU', (timeEnd - timeStart) * 1000) + "/ms")
cv2.imshow('res.png', img)
cv2.imshow('template', temple)
cv2.waitKey(0)
cv2.destroyAllWindows()
if __name__ == '__main__':
print(cv2.__version__)
__main()
~cq $ vi cascade.py
# -*- coding: utf-8 -*-
"""
カスケード分類器
人物を探す
"""
import cv2
import time
def __main():
img = cv2.imread('image/DSCF0769.JPG')
img = getResize(img)
timeStart = time.time()
# ここから処理を実行する
img = getPeople(img)
timeEnd = time.time()
print("{0} = {1}".format('CPU', (timeEnd - timeStart) * 1000) + "/ms")
cv2.imshow('Final result', img)
cv2.waitKey(0)
cv2.destroyAllWindows()
def getPeople(img):
global cascade
gray = cv2.cvtColor(src=img, code=cv2.COLOR_BGR2GRAY)
bodyRect = cascade.detectMultiScale(image=gray, scaleFactor=1.01,minNeighbors=10)
for x, y, w, h in bodyRect:
cv2.rectangle(img=img, pt1=(x, y), pt2=(x + w, y + h), color=(0, 255, 255), thickness=3)
return img
def getResize(img):
basePixSize = 1280 # 縦横で大きい辺の変更したいサイズ
height = img.shape[0]
width = img.shape[1]
largeSize = max(height, width) # 大きい方の辺のサイズ
resizeRate = basePixSize / largeSize # 変更比率を計算
img = cv2.resize(img, (int(width * resizeRate), int(height * resizeRate)))
return img
if __name__ == '__main__':
print(cv2.__version__)
cascadeFile = 'haarcascade_fullbody.xml'
cascade = cv2.CascadeClassifier(cascadeFile)
__main()
~cq $ vi hog.py
# -*- coding: utf-8 -*-
"""
HoG特徴とSVM識別器
人物を探す
"""
import cv2
import time
def __main():
img = cv2.imread('image/DSCF0769.JPG')
img = getResize(img)
timeStart = time.time()
# ここから処理を実行する
img = getPeople(img)
timeEnd = time.time()
print("{0} = {1}".format('CPU', (timeEnd - timeStart) * 1000) + "/ms")
cv2.imshow('Final result', img)
cv2.waitKey(0)
cv2.destroyAllWindows()
# ここから実行する
def getPeople(img):
gray = cv2.cvtColor(src=img, code=cv2.COLOR_BGR2GRAY)
hog = cv2.HOGDescriptor()
hog.setSVMDetector(svmdetector=cv2.HOGDescriptor_getDefaultPeopleDetector())
# winStride(ウィンドウの移動量) padding(入力画像の周囲の拡張範囲)
human, _ = hog.detectMultiScale(img=gray, winStride=(10, 10), padding=(16, 16), scale=None)
for (x, y, w, h) in human:
cv2.rectangle(img, (x, y), (x + w, y + h), (0, 255, 255), 3)
return img
def getResize(img):
basePixSize = 1280 # 縦横で大きい辺の変更したいサイズ
height = img.shape[0]
width = img.shape[1]
largeSize = max(height, width) # 大きい方の辺のサイズ
resizeRate = basePixSize / largeSize # 変更比率を計算
img = cv2.resize(img, (int(width * resizeRate), int(height * resizeRate)))
return img
if __name__ == '__main__':
print(cv2.__version__)
__main()