使用python和PIL对图像进行分割,以计算多个矩形对象的质心和旋转

Question

我使用python和PIL在640x480图像中找到各种矩形(和正方形)的质心和旋转,类似于这个

到目前为止,我的代码适用于图像中的单个矩形.

import Image, math

def find_centroid(im):
    width, height = im.size
    XX, YY, count = 0, 0, 0
    for x in xrange(0, width, 1):
        for y in xrange(0, height, 1):
            if im.getpixel((x, y)) == 0:
                XX += x
                YY += y
                count += 1
    return XX/count, YY/count

#Top Left Vertex
def find_vertex1(im):
    width, height = im.size
    for y in xrange(0, height, 1):
        for x in xrange (0, width, 1):
            if im.getpixel((x, y)) == 0:
                X1=x
                Y1=y
                return X1, Y1

#Bottom Left Vertex
def find_vertex2(im):
    width, height = im.size
    for x in xrange(0, width, 1):
        for y in xrange (height-1, 0, -1):
            if im.getpixel((x, y)) == 0:
                X2=x
                Y2=y
                return X2, Y2

#Top Right Vertex
def find_vertex3(im):
    width, height = im.size
    for x in xrange(width-1, 0, -1):
        for y in xrange (0, height, 1):
            if im.getpixel((x, y)) == 0:
                X3=x
                Y3=y
                return X3, Y3

#Bottom Right Vertex
def find_vertex4 (im):
    width, height = im.size
    for y in xrange(height-1, 0, -1):
        for x in xrange (width-1, 0, -1):
            if im.getpixel((x, y)) == 0:
                X4=x
                Y4=y
                return X4, Y4

def find_angle (V1, V2, direction):
    side1=math.sqrt(((V1[0]-V2[0])**2))
    side2=math.sqrt(((V1[1]-V2[1])**2))
    if direction == 0:
        return math.degrees(math.atan(side2/side1)), 'Clockwise'
    return 90-math.degrees(math.atan(side2/side1)), 'Counter Clockwise'

#Find direction of Rotation; 0 = CW, 1 = CCW
def find_direction (vertices, C):
    high=480
    for i in range (0,4):
        if vertices[i][1]<high:
            high = vertices[i][1]
            index = i
    if vertices[index][0]<C[0]:
        return 0
    return 1

def main():
    im = Image.open('hopperrotated2.png')
    im = im.convert('1') # convert image to black and white
    print 'Centroid ', find_centroid(im)
    print 'Top Left ', find_vertex1 (im)
    print 'Bottom Left ', find_vertex2 (im)
    print 'Top Right', find_vertex3 (im)
    print 'Bottom Right ', find_vertex4 (im)
    C = find_centroid (im)
    V1 = find_vertex1 (im)
    V2 = find_vertex3 (im)
    V3 = find_vertex2 (im)
    V4 = find_vertex4 (im)
    vertices = [V1,V2,V3,V4]
    direction = find_direction(vertices, C)
    print 'angle: ', find_angle(V1,V2,direction)

if __name__ == '__main__':
  main()

我遇到问题的地方是图像中有多个物体.

我知道PIL有一个find_edges方法,它只提供边缘的图像,但我不知道如何使用这个新的边缘图像将图像分割成单独的对象.

from PIL import Image, ImageFilter

im = Image.open('hopperrotated2.png')

im1 = im.filter(ImageFilter.FIND_EDGES)
im1 = im1.convert('1')
print im1
im1.save("EDGES.jpg")

如果我可以使用边缘将图像分割成单独的矩形,那么我可以在每个矩形上运行我的第一个代码来获得质心和旋转.

但更好的是能够使用边缘来计算每个矩形的旋转和质心,而无需向上分割图像.

非常感谢大家的帮助!

Answer 1

您需要在找到角落之前识别每个对象.您只需要对象的边框,因此您也可以减少初始输入.然后只需要跟踪每个不同的边界来找到你的角落,在你知道每个不同的边界后直接找到质心.

使用下面的代码,这里是你得到的(质心是红点,白色文本是以度为单位的旋转):

请注意,您的输入不是二进制,因此我使用了一个非常简单的阈值.此外,以下代码是实现此目的的最简单方法,任何体面的库中都有更快的方法.

import sys
import math
from PIL import Image, ImageOps, ImageDraw

orig = ImageOps.grayscale(Image.open(sys.argv[1]))
orig_bin = orig.point(lambda x: 0 if x < 128 else 255)
im = orig_bin.load()

border = Image.new('1', orig.size, 'white')
width, height = orig.size
bim = border.load()
# Keep only border points
for x in xrange(width):
    for y in xrange(height):
        if im[x, y] == 255:
            continue
        if im[x+1, y] or im[x-1, y] or im[x, y+1] or im[x, y-1]:
            bim[x, y] = 0
        else:
            bim[x, y] = 255

# Find each border (the trivial dummy way).
def follow_border(im, x, y, used):
    work = [(x, y)]
    border = []
    while work:
        x, y = work.pop()
        used.add((x, y))
        border.append((x, y))
        for dx, dy in ((1, 0), (-1, 0), (0, 1), (0, -1),
                (1, 1), (-1, -1), (1, -1), (-1, 1)):
            px, py = x + dx, y + dy
            if im[px, py] == 255 or (px, py) in used:
                continue
            work.append((px, py))

    return border

used = set()
border = []
for x in xrange(width):
    for y in xrange(height):
        if bim[x, y] == 255 or (x, y) in used:
            continue
        b = follow_border(bim, x, y, used)
        border.append(b)

# Find the corners and centroid of each rectangle.
rectangle = []
for b in border:
    xmin, xmax, ymin, ymax = width, 0, height, 0
    mean_x, mean_y = 0, 0
    b = sorted(b)
    top_left, bottom_right = b[0], b[-1]
    for x, y in b:
        mean_x += x
        mean_y += y
    centroid = (mean_x / float(len(b)), mean_y / float(len(b)))
    b = sorted(b, key=lambda x: x[1])
    curr = 0
    while b[curr][1] == b[curr + 1][1]:
        curr += 1
    top_right = b[curr]
    curr = len(b) - 1
    while b[curr][1] == b[curr - 1][1]:
        curr -= 1
    bottom_left = b[curr]

    rectangle.append([
        [top_left, top_right, bottom_right, bottom_left], centroid])


result = orig.convert('RGB')
draw = ImageDraw.Draw(result)
for corner, centroid in rectangle:
    draw.line(corner + [corner[0]], fill='red', width=2)
    cx, cy = centroid
    draw.ellipse((cx - 2, cy - 2, cx + 2, cy + 2), fill='red')
    rotation = math.atan2(corner[0][1] - corner[1][1],
            corner[1][0] - corner[0][0])
    rdeg = math.degrees(rotation)
    draw.text((cx + 10, cy), text='%.2f' % rdeg)

result.save(sys.argv[2])