Python OpenCV:魔方解算器颜色提取

2022-01-09 00:00:00 python opencv computer-vision image-processing image

问题描述

说明:

我正在使用 Python & 解决魔方问题.开放式简历.为此，我试图提取立方体的所有颜色(单个立方体块)，然后应用适当的算法(我设计的，没有问题).

问题:

假设如果我提取了立方体的所有颜色，我如何定位提取的立方体的位置?我怎么知道它是在上中下层还是角落中边缘?

我做了什么:

这里我刚刚提取了黄色.

颜色提取后:

原图

守则

将 numpy 导入为 np导入简历2从 cv2 导入 *im = cv2.imread('v123.bmp')im = cv2.bilateralFilter(im,9,75,75)im = cv2.fastNlMeansDenoisingColored(im,None,10,10,7,21)hsv_img = cv2.cvtColor(im, cv2.COLOR_BGR2HSV) # HSV图像COLOR_MIN = np.array([20, 100, 100],np.uint8) # HSV 颜色代码上下界COLOR_MAX = np.array([30, 255, 255],np.uint8) # 黄色frame_threshed = cv2.inRange(hsv_img, COLOR_MIN, COLOR_MAX) # 阈值图像imgray = frame_threshedret,thresh = cv2.threshold(frame_threshed,127,255,0)轮廓，层次结构 = cv2.findContours(thresh,cv2.RETR_TREE,cv2.CHAIN_APPROX_SIMPLE)打印类型(轮廓)对于轮廓中的cnt:x,y,w,h = cv2.boundingRect(cnt)打印 x，打印 ycv2.rectangle(im,(x,y),(x+w,y+h),(0,255,0),2)cv2.imshow("显示",im)cv2.imwrite("提取的.jpg", im)cv2.waitKey()cv2.destroyAllWindows()

请就如何定位小方块的位置提出一些建议.这里发现了 4 个黄色立方体:右上角、中心、右边缘、左下角.我如何识别这些位置，例如:通过为每个位置分配数字(这里:3、4、5、7)

感谢任何帮助/想法 :) 谢谢.

P.S.:OpenCV 新手 :)

解决方案

这里有一个简单的方法:

将图片转换为 HSV 格式

使用颜色阈值检测具有从上到下或从下到上对轮廓进行排序.接下来，我们取每行 3 个正方形，并从左到右或从右到左对这一行进行排序.这是排序的可视化(从上到下，左)或(从下到上，右)

现在我们已经对轮廓进行了排序，我们只需将矩形绘制到我们的图像上.这是结果

从左到右和从上到下(左)、从右到左和从上到下

从左到右和从下到上(左)，从右到左和从下到上

导入 cv2将 numpy 导入为 np从 imutils 导入轮廓图像 = cv2.imread('1.png')原始 = image.copy()图像 = cv2.cvtColor(图像，cv2.COLOR_BGR2HSV)掩码 = np.zeros(image.shape，dtype=np.uint8)颜色 = {'灰色': ([76, 0, 41], [179, 255, 70]), # 灰色'蓝色': ([69, 120, 100], [179, 255, 255]), # 蓝色'黄色': ([21, 110, 117], [45, 255, 255]), # 黄色'橙色': ([0, 110, 125], [17, 255, 255]) # 橙色}# 找到正方形的颜色阈值open_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (7,7))close_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (5,5))对于颜色，(lower,upper) 在 colors.items() 中:较低 = np.array(较低，dtype=np.uint8)上= np.array(上，dtype=np.uint8)color_mask = cv2.inRange(图像，下，上)color_mask = cv2.morphologyEx(color_mask, cv2.MORPH_OPEN, open_kernel, 迭代次数=1)color_mask = cv2.morphologyEx(color_mask, cv2.MORPH_CLOSE, close_kernel, 迭代次数=5)color_mask = cv2.merge([color_mask, color_mask, color_mask])mask = cv2.bitwise_or(mask, color_mask)灰色 = cv2.cvtColor(掩码，cv2.COLOR_BGR2GRAY)cnts = cv2.findContours(灰色，cv2.RETR_EXTERNAL，cv2.CHAIN_APPROX_SIMPLE)cnts = cnts[0] 如果 len(cnts) == 2 否则 cnts[1]# 从上到下或从下到上对所有轮廓进行排序(cnts, _) = contours.sort_contours(cnts, method=从上到下")# 取每行 3 并从左到右或从右到左排序立方体行 = []行 = []对于枚举(cnts，1)中的(i，c):row.append(c)如果我 % 3 == 0:(cnts, _) = contours.sort_contours(row, method=从左到右")cube_rows.append(cnts)行 = []# 绘制文字数字 = 0对于 cube_rows 中的行:对于 c 行:x,y,w,h = cv2.boundingRect(c)cv2.rectangle(原始, (x, y), (x + w, y + h), (36,255,12), 2)cv2.putText(原始，#{}".format(数字 + 1)，(x，y - 5)，cv2.FONT_HERSHEY_SIMPLEX，0.7，(255,255,255)，2)数字 += 1cv2.imshow('掩码', 掩码)cv2.imwrite('mask.png', 掩码)cv2.imshow('原创', 原创)cv2.waitKey()

Description:

I am working on solving rubiks cube using Python & OpenCV. For this purpose I am trying to extract all the colors of the cubies(individual cube pieces) and then applying appropriate algorithm(which I've designed, no issues there).

The problem:

Suppose if I've extracted all the colors of the cubies, how I can locate the position of the extracted cubies? How will I know whether it is in top-middle-lower layer or whether its a corner-middle-edge piece?

What I've done:

Here I have just extracted yellow color.

After color extraction:

Original Image

The Code

import numpy as np
import cv2
from cv2 import *

im = cv2.imread('v123.bmp')
im = cv2.bilateralFilter(im,9,75,75)
im = cv2.fastNlMeansDenoisingColored(im,None,10,10,7,21)
hsv_img = cv2.cvtColor(im, cv2.COLOR_BGR2HSV)   # HSV image


COLOR_MIN = np.array([20, 100, 100],np.uint8)       # HSV color code lower and upper bounds
COLOR_MAX = np.array([30, 255, 255],np.uint8)       # color yellow 

frame_threshed = cv2.inRange(hsv_img, COLOR_MIN, COLOR_MAX)     # Thresholding image
imgray = frame_threshed
ret,thresh = cv2.threshold(frame_threshed,127,255,0)
contours, hierarchy = cv2.findContours(thresh,cv2.RETR_TREE,cv2.CHAIN_APPROX_SIMPLE)
print type(contours)
for cnt in contours:
    x,y,w,h = cv2.boundingRect(cnt)
    print x,
    print y
    cv2.rectangle(im,(x,y),(x+w,y+h),(0,255,0),2)
cv2.imshow("Show",im)
cv2.imwrite("extracted.jpg", im)
cv2.waitKey()
cv2.destroyAllWindows()

Please give some suggestions on how can I locate the positions of the cubies. Here 4 yellow cubies are spotted: top-right-corner, center, right-edge, bottom-left-corner. How can I identify these positions for eg: by assigning digits to each position (here: 3, 4, 5, 7)

Any help/idea is appreciated :) Thanks.

P.S.: OpenCV newbie :)

解决方案

Here's a simple approach:

Convert image to HSV format
Use color thresholding to detect the squares with cv2.inRange()
Perform morphological operations and draw squares onto a mask
Find contours on mask and sort from top-bottom or bottom-top
Take each row of three squares and sort from left-right or right-left

After converting to HSV format, we perform color thresholding using cv2.inRange() to detect the squares. We draw the detected squares onto a mask

From here we find contours on the mask and utilize imutils.contours.sort_contours() to sort the contours from top-to-bottom or bottom-to-top. Next we take each row of 3 squares and sort this row from left-to-right or right-to-left. Here's a visualization of the sorting (top-bottom, left) or (bottom-top, right)

Now that we have the contours sorted, we simply draw the rectangles onto our image. Here's the results

Left-to-right and top-to-bottom (left), right-to-left and top-to-bottom

Left-to-right and bottom-to-top (left), right-to-left and bottom-to-top

import cv2
import numpy as np
from imutils import contours

image = cv2.imread('1.png')
original = image.copy()
image = cv2.cvtColor(image, cv2.COLOR_BGR2HSV)
mask = np.zeros(image.shape, dtype=np.uint8)

colors = {
    'gray': ([76, 0, 41], [179, 255, 70]),        # Gray
    'blue': ([69, 120, 100], [179, 255, 255]),    # Blue
    'yellow': ([21, 110, 117], [45, 255, 255]),   # Yellow
    'orange': ([0, 110, 125], [17, 255, 255])     # Orange
    }

# Color threshold to find the squares
open_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (7,7))
close_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (5,5))
for color, (lower, upper) in colors.items():
    lower = np.array(lower, dtype=np.uint8)
    upper = np.array(upper, dtype=np.uint8)
    color_mask = cv2.inRange(image, lower, upper)
    color_mask = cv2.morphologyEx(color_mask, cv2.MORPH_OPEN, open_kernel, iterations=1)
    color_mask = cv2.morphologyEx(color_mask, cv2.MORPH_CLOSE, close_kernel, iterations=5)

    color_mask = cv2.merge([color_mask, color_mask, color_mask])
    mask = cv2.bitwise_or(mask, color_mask)

gray = cv2.cvtColor(mask, cv2.COLOR_BGR2GRAY)
cnts = cv2.findContours(gray, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
# Sort all contours from top-to-bottom or bottom-to-top
(cnts, _) = contours.sort_contours(cnts, method="top-to-bottom")

# Take each row of 3 and sort from left-to-right or right-to-left
cube_rows = []
row = []
for (i, c) in enumerate(cnts, 1):
    row.append(c)
    if i % 3 == 0:  
        (cnts, _) = contours.sort_contours(row, method="left-to-right")
        cube_rows.append(cnts)
        row = []

# Draw text
number = 0
for row in cube_rows:
    for c in row:
        x,y,w,h = cv2.boundingRect(c)
        cv2.rectangle(original, (x, y), (x + w, y + h), (36,255,12), 2)

        cv2.putText(original, "#{}".format(number + 1), (x,y - 5), cv2.FONT_HERSHEY_SIMPLEX, 0.7, (255,255,255), 2)
        number += 1

cv2.imshow('mask', mask)
cv2.imwrite('mask.png', mask)
cv2.imshow('original', original)
cv2.waitKey()

相关文章