使用opencv删除任何图像的背景

Question

我一直在寻找一种技术来删除任何给定图像的背景.想法是检测面部并移除检测到的面部的背景.我完成了脸部.现在删除背景部分仍然存在.

我用过这段代码.

import cv2
import numpy as np

#== Parameters           
BLUR = 21
CANNY_THRESH_1 = 10
CANNY_THRESH_2 = 200
MASK_DILATE_ITER = 10
MASK_ERODE_ITER = 10
MASK_COLOR = (0.0,0.0,1.0) # In BGR format


#-- Read image
img = cv2.imread('SYxmp.jpg')
gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)

#-- Edge detection 
edges = cv2.Canny(gray, CANNY_THRESH_1, CANNY_THRESH_2)
edges = cv2.dilate(edges, None)
edges = cv2.erode(edges, None)

#-- Find contours in edges, sort by area 
contour_info = []
_, contours, _ = cv2.findContours(edges, cv2.RETR_LIST, cv2.CHAIN_APPROX_NONE)
for c in contours:
    contour_info.append((
        c,
        cv2.isContourConvex(c),
        cv2.contourArea(c),
    ))
contour_info = sorted(contour_info, key=lambda c: c[2], reverse=True)
max_contour = contour_info[0]

#-- Create empty mask, draw filled polygon on it corresponding to largest contour ----
# Mask is black, polygon is white
mask = np.zeros(edges.shape)
cv2.fillConvexPoly(mask, max_contour[0], (255))

#-- Smooth mask, then blur it
mask = cv2.dilate(mask, None, iterations=MASK_DILATE_ITER)
mask = cv2.erode(mask, None, iterations=MASK_ERODE_ITER)
mask = cv2.GaussianBlur(mask, (BLUR, BLUR), 0)
mask_stack = np.dstack([mask]*3)    # Create 3-channel alpha mask

#-- Blend masked img into MASK_COLOR background
mask_stack  = mask_stack.astype('float32') / 255.0         
img         = img.astype('float32') / 255.0    
masked = (mask_stack * img) + ((1-mask_stack) * MASK_COLOR)  
masked = (masked * 255).astype('uint8')                    

cv2.imshow('img', masked)                                   # Display
cv2.waitKey()
cv2.imwrite("WTF.jpg",masked)

但此代码仅适用于此图像

应该改变什么来使用不同图像的代码

Answer 1

局部最优解

# Original Code
CANNY_THRESH_2 = 200

# Change to
CANNY_THRESH_2 = 100

####### Change below worth to try but not necessary

# Original Code
mask = np.zeros(edges.shape)
cv2.fillConvexPoly(mask, max_contour[0], (255))

# Change to
for c in contour_info:
    cv2.fillConvexPoly(mask, c[0], (255))

效果

• 测试图像
  • 相似颜色的背景,头发和皮肤

• 原始输出
  • 原始输出

• 原始边缘

• 应用所有轮廓而不是具有相同边缘阈值的最大轮廓

  • 稍微好一些

  

• Canny Thresh 2设为100,应用所有轮廓

  • 好多了

• 更强的边缘

• Canny Thresh 2设为40,应用所有轮廓
  • 边缘开始变得不那么尖锐

推理

1. 程序行为

   该程序搜索边缘并构建轮廓.获取最大轮廓并识别为人脸.然后涂上面膜.

2. 问题

   处理背景和人脸之间的相似颜色并不容易.金色的头发和肤色使得很难找到原始阈值的正确边缘.

   最大轮廓意味着当图像像测试图像中的围巾一样具有强大的顶点时,很容易丢失某些区域的轨迹.但它实际上取决于人脸识别过程后的图像类型.