从轮廓删除背景

时间:2020-05-26 07:05:13

标签: python opencv

我在去除不需要的轮廓时遇到了一些问题。

具有检测到的轮廓的图像:

enter image description here

我不希望该图像显示以下轮廓(蓝色标记的区域):

enter image description here

但是我似乎无法摆脱它们。 我的代码:

img = cv2.imread(img_path)

edges = cv2.Canny(img, 240, 240)
#cv2.imshow('', edges)


thresh = cv2.threshold(edges,150, 255,cv2.THRESH_BINARY_INV)[1]
cnts, h = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)

# Show and Write Threshold Image
#cv2.imshow('thresh', thresh)
#cv2.imwrite('Thresholded_labeled_image.jpg', thresh)

# Find and Draw Contours
contours, h = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
img_contours = cv2.drawContours(thresh, contours, -1, (0,255,0), 3)
cv2.imshow('contours', img_contours)

# Remove Noise
kernel = np.ones((5,5),np.float32)/25
dst = cv2.filter2D(img_contours,-1,kernel)

plt.subplot(121),plt.imshow(img_contours),plt.title('Image_Contours')
plt.xticks([]), plt.yticks([])
plt.subplot(122),plt.imshow(dst),plt.title('Averaging')
plt.xticks([]), plt.yticks([])
plt.show()

我尝试了形态学:

kernel = np.ones((5,5),np.uint8)
closing = cv2.morphologyEx(edges, cv2.MORPH_CLOSE, kernel)
cv2.imshow('closing', closing)

我尝试更改内核的大小,但仍然无法正常工作。我仍然看到那些多余的轮廓。

有什么我想做的吗?

编辑1:使用boundingRect

kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (4,2))
dilate = cv2.dilate(thresh, kernel, iterations=2)

# Find contours, highlight text areas, and extract ROIs
cnts = cv2.findContours(dilate, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]

ROI_number = 0
ROI_images = []
for c in cnts:
    area = cv2.contourArea(c)
    print("Area is: ", area)
    x,y,w,h = cv2.boundingRect(c)
    print("Height: ", h)
    if area > 100 and 0<h<300:
        cv2.rectangle(image, (x, y), (x + w, y + h), (0, 255, 0), 3)
        ROI = img[y:y+h, x:x+w]
        # cv2.imwrite('ROI_{}.png'.format(ROI_number), ROI)
        ROI_number += 1
        ROI_images.append(ROI)

输出:

enter image description here

1 个答案:

答案 0 :(得分:1)

这就是你的做法。您必须根据需要编辑以下代码。

import cv2
import numpy as np
img = cv2.imread('try.png')
img_res = img.copy()
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
ret,thresh = cv2.threshold(gray,127,255,1)
contours,h = cv2.findContours(thresh,1,2)
# area_list = []
for cnt in contours:
        area = cv2.contourArea(cnt)
        x,y,w,h = cv2.boundingRect(cnt)
#         print(area,w,h)
        if area<5200:

            img[y:y+h, x:x+w] = (255,255,255)
            cv2.rectangle(img_res, (x, y), (x + w, y + h), (0, 255, 0), 3)

原始图片

try.png:

(这里我已将其加载为RGB图像,您必须修改代码以找出轮廓)

enter image description here

要删除的轮廓

img_res:

enter image description here

最终结果

img:

enter image description here