我应该使用什么样的参数来查找和裁剪图像中的对象？

Question

我是深度学习的新手，并尝试实现用于图像聚类的 ML 算法。问题是我无法使用 OpenCV 在 Python 中裁剪图像中的对象。 这是我实现的代码，如果对象的颜色与背景非常不同（以 RGB 值表示），它适用于某些对象，但它不适用于 ML 算法所需的图像。我应该拥有/更改什么样的参数？有什么建议吗？

import cv2
import numpy as np
from PIL import Image
import tkinter as tk
from tkinter import filedialog as fd
from tkinter import*
import random
#!/usr/bin/python
from PIL import Image
import sys


myFile = 'Path' + '/crop.png'
nr_of_im = 1
q = 0
r = 0
x_list = []
y_list = []
img = cv2.imread(myFile, cv2.IMREAD_UNCHANGED)

ret, thresh = cv2.threshold(cv2.cvtColor(img.copy(), cv2.COLOR_BGR2GRAY) , 30, 255, cv2.THRESH_BINARY)
contours, hier = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
for contour in contours:
    print("len",len(contours))
    if cv2.contourArea(contour) > 80:
        x, y, w, h = cv2.boundingRect(contour)
        q = w
        r = h       
        x_list.append(x)
        y_list.append(y)
        font = cv2.FONT_HERSHEY_SIMPLEX
        ROI = img[y-10:y+10+h, x-10:x+10+w]
        ROI = cv2.resize(ROI,(300,300))
        file_all = "/images/%d.jpg"%nr_of_im
        nr_of_im += 1
        cv2.imwrite(file_all,ROI)

图像中有21个物体，但轮廓的长度返回1。图像看起来像这样

crop.png：

Answer 1

您的阈值太低，对我产生的图像是全白的。你需要提高你的门槛。始终查看您的阈值，以确保它按您期望的方式工作。您以后可以随时删除查看。

以下适用于我使用阈值为 97 的 Otsu 阈值。我得到 21 个轮廓。

输入：

import cv2
import numpy as np

# read image
img = cv2.imread('blocks.jpg')

# convert to grayscale
gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)

# threshold
ret, thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY+cv2.THRESH_OTSU)
print(ret)

# apply morphology fill and separate large regions and remove small ones
kernel = cv2.getStructuringElement(cv2.MORPH_RECT , (9,9))
morph = cv2.morphologyEx(thresh, cv2.MORPH_CLOSE, kernel)
kernel = cv2.getStructuringElement(cv2.MORPH_RECT , (15,15))
morph = cv2.morphologyEx(morph, cv2.MORPH_OPEN, kernel)

# get contours
result = img.copy()
contours = cv2.findContours(morph, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
contours = contours[0] if len(contours) == 2 else contours[1]

# get count of contours
print(len(contours))

# draw bounding boxes on contours
for cntr in contours:
    x,y,w,h = cv2.boundingRect(cntr)
    cv2.rectangle(result, (x, y), (x+w, y+h), (0, 0, 255), 2)
    #print("x,y,w,h:",x,y,w,h)
    
# save results
cv2.imwrite("blocks_thresh.jpg", thresh)
cv2.imwrite("blocks_morphology.jpg", morph)
cv2.imwrite("blocks_bboxes.jpg", result)

# show thresh and result    
cv2.imshow("thresh", thresh)
cv2.imshow("morph", morph)
cv2.imshow("result", result)
cv2.waitKey(0)
cv2.destroyAllWindows()

阈值图像：

形态清洁图像：

由轮廓生成的边界框：