python - 读取highpiexl图像并使用GrabCut获取片段

Question

当我从https://github.com/fengxianghu/GrabCut-1读取代码为grabcut_opencv.py 的图片时，发生以下情况:
1.第一次无法读取图片
2.鼠标事件不响应

我尝试了以下

1:将cv.namedwindow()的默认值设置为1，但是它不起作用

cv.namedWindow('output', 1)  
cv.namedWindow('input', 1)

将namedwindow()移入while循环是没有用的

     img = cv.imread(filename)
     img2 = img.copy()                               # a copy of original image
     mask = np.zeros(img.shape[:2],dtype = np.uint8) # mask initialized to PR_BG
     output = np.zeros(img.shape,np.uint8)           # output image to be shown

    print(" Instructions: \n")
    print(" Draw a rectangle around the object using right mouse button \n")

while(1):
    cv.namedWindow('output', 1)
    cv.namedWindow('input', 1)

    cv.setMouseCallback('input', onmouse)
    cv.moveWindow('input', img.shape[1] + 10, 90)

    cv.imshow('output',output)

    cv.imshow('input',img)

你有什么考虑
我的照片也附上了

Answer 1

我想我解决了这个难题:

删除行:

cv.moveWindow('input',img.shape[1]+10,90)

上面的代码将输入图像放置在输出图像的正确尺寸上。
由于您输入的图像很大，因此 input窗口的位置在屏幕外部，因此不可见。

您也可以在读取图像后缩小图像尺寸。
例:
在 img = cv.imread(filename)之后，调整图像大小:

img = cv.resize(img, (img.shape[1]//8, img.shape[0]//8), interpolation=cv.INTER_AREA)

更新:

您可以在每个轴上将图像缩小1/8倍(例如)。

显示较低分辨率的图像，并在较低分辨率的图像上进行选择。

在全分辨率图像上应用GrabCut算法。

这是 grabcut_opencv.py的修改版本:

#!/usr/bin/env python
'''
===============================================================================
Interactive Image Segmentation using GrabCut algorithm.

This sample shows interactive image segmentation using grabcut algorithm.

USAGE:
    python grabcut.py <filename>

README FIRST:
    Two windows will show up, one for input and one for output.

    At first, in input window, draw a rectangle around the object using
mouse right button. Then press 'n' to segment the object (once or a few times)
For any finer touch-ups, you can press any of the keys below and draw lines on
the areas you want. Then again press 'n' for updating the output.

Key '0' - To select areas of sure background
Key '1' - To select areas of sure foreground
Key '2' - To select areas of probable background
Key '3' - To select areas of probable foreground

Key 'n' - To update the segmentation
Key 'r' - To reset the setup
Key 's' - To save the results
===============================================================================
'''

# Python 2/3 compatibility
from __future__ import print_function

import numpy as np
import cv2 as cv
import sys

BLUE = [255,0,0]        # rectangle color
RED = [0,0,255]         # PR BG
GREEN = [0,255,0]       # PR FG
BLACK = [0,0,0]         # sure BG
WHITE = [255,255,255]   # sure FG

DRAW_BG = {'color' : BLACK, 'val' : 0}
DRAW_FG = {'color' : WHITE, 'val' : 1}
DRAW_PR_FG = {'color' : GREEN, 'val' : 3}
DRAW_PR_BG = {'color' : RED, 'val' : 2}

# setting up flags
rect = (0,0,1,1)
drawing = False         # flag for drawing curves
rectangle = False       # flag for drawing rect
rect_over = False       # flag to check if rect drawn
rect_or_mask = 100      # flag for selecting rect or mask mode
value = DRAW_FG         # drawing initialized to FG
thickness = 3           # brush thickness

def onmouse(event,x,y,flags,param):
    global img,img2,drawing,value,mask,rectangle,rect,rect_or_mask,ix,iy,rect_over
    global shrunk_img, shrunk_img2, shrunk_output

    # Draw Rectangle
    if event == cv.EVENT_RBUTTONDOWN:
        rectangle = True
        ix,iy = x,y

    elif event == cv.EVENT_MOUSEMOVE:
        if rectangle == True:
            shrunk_img = shrunk_img2.copy() #img = img2.copy()
            # Draw the rectangle on the shrunk image.
            cv.rectangle(shrunk_img, (ix,iy), (x,y), BLUE, 2) #cv.rectangle(img,(ix,iy),(x,y),BLUE,2)
            # Multiply coordinates by 8 because the selection was performed on the shrunk image
            rect = (min(ix*8,x*8),min(iy*8,y*8),abs(ix*8-x*8),abs(iy*8-y*8)) #rect = (min(ix,x),min(iy,y),abs(ix-x),abs(iy-y))
            rect_or_mask = 0

    elif event == cv.EVENT_RBUTTONUP:
        rectangle = False
        rect_over = True
        cv.rectangle(shrunk_img, (ix,iy), (x,y), BLUE, 2) #cv.rectangle(img,(ix,iy),(x,y),BLUE,2)

        # Multiply coordinates by 8 because the selection was performed on the shrunk image
        rect = (min(ix*8,x*8),min(iy*8,y*8),abs(ix*8-x*8),abs(iy*8-y*8)) #rect = (min(ix,x),min(iy,y),abs(ix-x),abs(iy-y))
        rect_or_mask = 0
        print(" Now press the key 'n' a few times until no further change \n")

    # draw touchup curves

    if event == cv.EVENT_LBUTTONDOWN:
        if rect_over == False:
            print("first draw rectangle \n")
        else:
            drawing = True
            cv.circle(img,(x,y),thickness,value['color'],-1)
            cv.circle(mask,(x,y),thickness,value['val'],-1)

    elif event == cv.EVENT_MOUSEMOVE:
        if drawing == True:
            cv.circle(img,(x,y),thickness,value['color'],-1)
            cv.circle(mask,(x,y),thickness,value['val'],-1)

    elif event == cv.EVENT_LBUTTONUP:
        if drawing == True:
            drawing = False
            cv.circle(img,(x,y),thickness,value['color'],-1)
            cv.circle(mask,(x,y),thickness,value['val'],-1)

if __name__ == '__main__':

    # print documentation
    print(__doc__)

    # Loading images
    if len(sys.argv) == 2:
        filename = sys.argv[1] # for drawing purposes
    else:
        print("No input image given, so loading default image, messi5.jpg \n")
        print("Correct Usage: python grabcut.py <filename> \n")
        filename = 'messi5.jpg'

    img = cv.imread(filename)

    #img = cv.resize(img, (img.shape[1]//8, img.shape[0]//8), interpolation=cv.INTER_AREA)

    img2 = img.copy()                               # a copy of original image
    mask = np.zeros(img.shape[:2],dtype = np.uint8) # mask initialized to PR_BG
    output = np.zeros(img.shape, np.uint8)           # output image to be shown

    # Shrink the image by a factor of 8 in each axis.
    shrunk_img = cv.resize(img, (img.shape[1]//8, img.shape[0]//8), interpolation=cv.INTER_AREA)
    shrunk_img2 = shrunk_img.copy()


    # input and output windows
    cv.namedWindow('output')
    cv.namedWindow('input')
    cv.setMouseCallback('input',onmouse)
    cv.moveWindow('input',shrunk_img.shape[1]+10,90) #cv.moveWindow('input',img.shape[1]+10,90)

    print(" Instructions: \n")
    print(" Draw a rectangle around the object using right mouse button \n")

    while(1):
        # Shrink the image by a factor of 8 in each axis before showing:
        shrunk_output = cv.resize(output, (output.shape[1]//8, output.shape[0]//8), interpolation=cv.INTER_AREA)
        #shrunk_img = cv.resize(img, (img.shape[1]//8, img.shape[0]//8), interpolation=cv.INTER_AREA)

        # Show shrunk images, instead of full resolution images
        cv.imshow('output', shrunk_output)
        cv.imshow('input', shrunk_img)
        k = cv.waitKey(1)

        # key bindings
        if k == 27:         # esc to exit
            break
        elif k == ord('0'): # BG drawing
            print(" mark background regions with left mouse button \n")
            value = DRAW_BG
        elif k == ord('1'): # FG drawing
            print(" mark foreground regions with left mouse button \n")
            value = DRAW_FG
        elif k == ord('2'): # PR_BG drawing
            value = DRAW_PR_BG
        elif k == ord('3'): # PR_FG drawing
            value = DRAW_PR_FG
        elif k == ord('s'): # save image
            bar = np.zeros((img.shape[0],5,3),np.uint8)
            res = np.hstack((img2,bar,img,bar,output))
            cv.imwrite('grabcut_output.png',res)
            print(" Result saved as image \n")
        elif k == ord('r'): # reset everything
            print("resetting \n")
            rect = (0,0,1,1)
            drawing = False
            rectangle = False
            rect_or_mask = 100
            rect_over = False
            value = DRAW_FG
            img = img2.copy()
            mask = np.zeros(img.shape[:2],dtype = np.uint8) # mask initialized to PR_BG
            output = np.zeros(img.shape,np.uint8)           # output image to be shown
        elif k == ord('n'): # segment the image
            print(""" For finer touchups, mark foreground and background after pressing keys 0-3
            and again press 'n' \n""")
            print(rect)
            if (rect_or_mask == 0):         # grabcut with rect
                bgdmodel = np.zeros((1,65),np.float64)
                fgdmodel = np.zeros((1,65),np.float64)
                cv.grabCut(img2,mask,rect,bgdmodel,fgdmodel,1,cv.GC_INIT_WITH_RECT)
                rect_or_mask = 1
            elif rect_or_mask == 1:         # grabcut with mask
                bgdmodel = np.zeros((1,65),np.float64)
                fgdmodel = np.zeros((1,65),np.float64)
                cv.grabCut(img2,mask,rect,bgdmodel,fgdmodel,1,cv.GC_INIT_WITH_MASK)

        mask2 = np.where((mask==1) + (mask==3),255,0).astype('uint8')
        output = cv.bitwise_and(img2,img2,mask=mask2)

    cv.destroyAllWindows()

注意:
我很有可能错过了很少的案例(当从小分辨率图像转换为全分辨率然后返回时)。