opencv︱图片与视频的读入、显示、写出、放缩与基本绘图函数介绍

import numpy as np
import cv2

 # Load an color image in grayscale
img = cv2.imread('messi5.jpg',0)

cv2.imdecode(np.fromfile(img_name_1, dtype=np.uint8), -1)

cv2.imshow('image',img)
cv2.waitKey(0)
cv2.destroyAllWindows()

cv2.imwrite('messigray.png',img)

cv2.imencode('.jpg', edges)[1].tofile('/../../1.jpg')

  image=cv2.imread('test.jpg')
  res=cv2.resize(image,(32,32),interpolation=cv2.INTER_CUBIC)
  cv2.imshow('iker',res)
  cv2.imshow('image',image)
  cv2.waitKey(0)
  cv2.destoryAllWindows()

import numpy as np
 import cv2

img = cv2.imread('messi5.jpg',0)
cv2.imshow('image',img)
1k = cv2.waitKey(0)

if k == 27: 
	# wait for ESC key to exit
	cv2.destroyAllWindows()
elif k == ord('s'): 
	# wait for 's' key to save and exit
	 cv2.imwrite('messigray.png',img)
	 cv2.destroyAllWindows()

import numpy as np
import cv2
from matplotlib import pyplot as plt

img = cv2.imread('messi5.jpg',0)
plt.imshow(img, cmap = 'gray', interpolation = 'bicubic')
plt.xticks([]), plt.yticks([]) 
	 # to hide tick values on X and Y axis
plt.show()

import numpy as np
import cv2

cap = cv2.VideoCapture(0)

 while(True):
 # Capture frame-by-frame
	 ret, frame = cap.read()

 # Our operations on the frame come here
	 gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)

 # Display the resulting frame
	 cv2.imshow('frame',gray)
	 if cv2.waitKey(1) & 0xFF == ord('q'):
 break

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

import numpy as np
import cv2

cap = cv2.VideoCapture(0)

# Define the codec and create VideoWriter object
fourcc = cv2.VideoWriter_fourcc(*'XVID')
out = cv2.VideoWriter('output.avi',fourcc, 20.0, (640,480))

while(cap.isOpened()):
	ret, frame = cap.read()
	if ret==True:
		frame = cv2.flip(frame,0)
# write the flipped frame
		out.write(frame)

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

# Release everything if job is finished
cap.release()
out.release()
cv2.destroyAllWindows()

import numpy as np
import cv2

cap = cv2.VideoCapture(0)

# Define the codec and create VideoWriter object
fourcc = cv2.cv.FOURCC(*'XVID')
out = cv2.VideoWriter('output.avi',fourcc, 20.0, (640,480))

while(cap.isOpened()):
	ret, frame = cap.read()
	if ret==True:
		frame = cv2.flip(frame,0)

		# write the flipped frame
		out.write(frame)

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

# Release everything if job is finished
cap.release()
out.release()
cv2.destroyAllWindows()

import numpy as np
import cv2

# Create a black image
img=np.zeros((512,512,3), np.uint8)

# Draw a diagonal blue line with thickness of 5 px
cv2.line(img,(0,0),(511,511),(255,0,0),5)

cv2.rectangle(img,(384,0),(510,128),(0,255,0),3)

cv2.circle(img,(447,63), 63, (0,0,255), -1)

cv2.ellipse(img,(256,256),(100,50),0,0,180,255,-1)

pts=np.array([[10,5],[20,30],[70,20],[50,10]], np.int32)
pts=pts.reshape((-1,1,2))
# 这里 reshape 的第一个参数为-1, 表明这一维的长度是根据后面的维度的计算出来的。

font=cv2.FONT_HERSHEY_SIMPLEX
cv2.putText(img,'OpenCV',(10,500), font, 4,(255,255,255),2)

import cv2
img = cv2.imread('img/image.png')
print img.shape
# (640, 640, 3)
print img.size
# 1228800
print img.dtype
# uint8
# 在debug的时候，dtype很重要

__main__:2: RuntimeWarning: overflow encountered in ubyte_scalars

 val = img[y1_, x1_] - img[y2_, x2_]

val = int(img[y1_, x1_]) - int(img[y2_, x2_])

# 参数输入
output_dir='/home/ubuntu/keras/matt/frcnn/output'
output_path= os.path.join(output_dir, '')                       # 输入图片存放位置
output_video_file = '/home/ubuntu/keras/matt/frcnn/output6.avi' # 输入视频保存位置以及视频名称
save_to_video(output_video_file,25)                                   

# 函数生成器
def get_file_names(search_path):
	for (dirpath, _, filenames) in os.walk(search_path):
		for filename in filenames:
			yield filename#os.path.join(dirpath, filename)
# yield 把值迭代进去，存进入，然后可以for 迭代出来
# [/home/ubuntu/keras/matt/frcnn/output/]

# 保存函数
def save_to_video(output_path,output_video_file,frame_rate):
    list_files = sorted(get_file_names(output_path), key=lambda var:[int(x) if x.isdigit() else x for x in re.findall(r'[^0-9]|[0-9]+', var)])
    # 拿一张图片确认宽高
    img0 = cv2.imread(os.path.join(output_path,'0.jpg'))
	height , width , layers =  img0.shape
	# 视频保存初始化 VideoWriter
    fourcc = cv2.cv.CV_FOURCC(*'mp4v')
    videowriter = cv2.VideoWriter(output_video_file,fourcc, frame_rate, (width,height))
    # 核心，保存的东西
    for f in list_files:
        print("saving..." + f)
        img = cv2.imread(os.path.join(output_path, f))
        videowriter.write(img)
    videowriter.release()
    cv2.destroyAllWindows()

fourcc = cv2.cv.CV_FOURCC(*'mp4v')
# fourcc = cv2.VideoWriter_fourcc(*'mp4v')
#fourcc = cv2.cv.CV_FOURCC(*'XVID')

import cv2
from matplotlib import pyplot as plt

# 读入
img = cv2.imdecode(np.fromfile('..\\1.jpg',dtype = np.uint8),1)

# 写出
cv2.imwrite("..\\1.jpg",img, [int(cv2.IMWRITE_JPEG_QUALITY), 100] )
cv2.imencode('.jpg', edges)[1].tofile('/../../1.jpg')

# 画框
plt.imshow(cv2.rectangle(img,(187,176),(241,205),(0,255,0),3), cmap = 'gray', interpolation = 'bicubic')

# 写文字
plt.text(187,176, 'words')   # plt的方式
cv2.putText(img,'words',(187,176) ,0, 1,(255,255,255),2)  #cv2的方式
        # 添加文字，1.2表示字体大小，（0,40）是初始的位置，(255,255,255)表示颜色，2表示粗细

# 
import cv2
import freetype as ft2

import freetype
face = freetype.Face("Vera.ttf")


img = cv2.imread('pic/lena.jpg')
line = '你好,我是 lena'

color = (0, 255, 0)  # Green
pos = (3, 3)
text_size = 24

# ft = put_chinese_text('wqy-zenhei.ttc')
ft = ft2.put_chinese_text('msyh.ttf')
image = ft.draw_text(img, pos, line, text_size, color)

from matplotlib import pyplot as plt
import matplotlib
from PIL import Image, ImageDraw, ImageFont
# 显示中文 plt
fnt = "...\\msyh.ttc"
fnt = ImageFont.truetype(fnt, 20)

img = Image.open('..\\1.jpg')
draw = ImageDraw.Draw(img)
draw.rectangle((187,176,241,205), outline=(255, 255, 255, 30))
draw.text((187,176),'你好',(0,0,0), font=fnt)
img.save("..\\t1.jpg")

from matplotlib import pyplot as plt
import cv2
img = cv2.imread('images/images_all/005A5pE3gy1flekxbm2bpj30zk0qoqg2.jpg')
img = cv2.rectangle(img,(x_min,y_min),(x_max,y_max),(0,255,255),3)
plt.imshow(img)
# save
from scipy import misc
# numpy直接保存出来
misc.imsave('img.jpg', r_image)

get_colors_for_classes(2)
>>> [(0, 255, 255), (255, 0, 0)]

import colorsys
import random

import numpy as np
from PIL import Image, ImageDraw, ImageFont


def get_colors_for_classes(num_classes):
    """Return list of random colors for number of classes given."""
    # Use previously generated colors if num_classes is the same.
    if (hasattr(get_colors_for_classes, "colors") and
            len(get_colors_for_classes.colors) == num_classes):
        return get_colors_for_classes.colors

    hsv_tuples = [(x / num_classes, 1., 1.) for x in range(num_classes)]
    colors = list(map(lambda x: colorsys.hsv_to_rgb(*x), hsv_tuples))
    colors = list(
        map(lambda x: (int(x[0] * 255), int(x[1] * 255), int(x[2] * 255)),
            colors))
    random.seed(10101)  # Fixed seed for consistent colors across runs.
    random.shuffle(colors)  # Shuffle colors to decorrelate adjacent classes.
    random.seed(None)  # Reset seed to default.
    get_colors_for_classes.colors = colors  # Save colors for future calls.
    return colors


def draw_boxes(image, boxes, box_classes, class_names, scores=None,fnt ="msyh.ttc" ):
    """Draw bounding boxes on image.
    Draw bounding boxes with class name and optional box score on image.
    Args:
        image: An `array` of shape (width, height, 3) with values in [0, 1].
        boxes: An `array` of shape (num_boxes, 4) containing box corners as
            (y_min, x_min, y_max, x_max).
        box_classes: A `list` of indicies into `class_names`.
        class_names: A `list` of `string` class names.
        `scores`: A `list` of scores for each box.
    Returns:
        A copy of `image` modified with given bounding boxes.
    """
    #image = Image.fromarray(np.floor(image * 255 + 0.5).astype('uint8'))
	image = Image.fromarray(image)
	
    font = ImageFont.truetype(
        font=fnt,
        size=np.floor(3e-2 * image.size[1] + 0.5).astype('int32'))
    thickness = (image.size[0] + image.size[1]) // 300

    colors = get_colors_for_classes(len(class_names))

    for i, c in list(enumerate(box_classes)):
        box_class = class_names[c]
        box = boxes[i]
        if isinstance(scores, np.ndarray):
            score = scores[i]
            label = '{} {:.2f}'.format(box_class, score)
        else:
            label = '{}'.format(box_class)

        draw = ImageDraw.Draw(image)
        label_size = draw.textsize(label, font)

        top, left, bottom, right = box
        top = max(0, np.floor(top + 0.5).astype('int32'))
        left = max(0, np.floor(left + 0.5).astype('int32'))
        bottom = min(image.size[1], np.floor(bottom + 0.5).astype('int32'))
        right = min(image.size[0], np.floor(right + 0.5).astype('int32'))
        print(label, (left, top), (right, bottom))

        if top - label_size[1] >= 0:
            text_origin = np.array([left, top - label_size[1]])
        else:
            text_origin = np.array([left, top + 1])

        # My kingdom for a good redistributable image drawing library.
        for i in range(thickness):
            draw.rectangle(
                [left + i, top + i, right - i, bottom - i], outline=colors[c])
        draw.rectangle(
            [tuple(text_origin), tuple(text_origin + label_size)],
            fill=colors[c])
        draw.text(text_origin, label, fill=(0, 0, 0), font=font)
        del draw

    return np.array(image)