HED算法中检测大颗粒旁小颗粒的另一种方法

Question

​

​

我在我的项目中的主要任务是检测在土壤颗粒图像中遇到的多边形的属性，我使用HED算法来检测图像中颗粒的边界，因为它在检测边界方面非常智能，并且不受图像中的噪声的影响，并且它基于opencv库中的深度神经网络但是我在拍摄大颗粒旁边的小颗粒图像时遇到了问题，如下图所示，因为它完美地检测出较大的颗粒，并且在很大程度上忽略了小颗粒，我不知道如何解决这个问题，因为它影响了我从图像分析中获得的结果。我的主要问题是，是否有一种方法可以提高算法的效率，以便有效地检测这两个颗粒。Find还附上了使用的HED算法。我使用的是佳能600D，所以我不怀疑图像质量的效率。

​

​

该算法使用了HED

# USAGE
# python detect_edges_image.py --edge-detector hed_model --image images/guitar.jpg

# import the necessary packages
import argparse
import cv2
import os
import easygui

path = easygui.fileopenbox()
print(path)
hdir = os.path.dirname(path)
print(hdir)
hfilename = os.path.basename(path)
print(hfilename)
hname = os.path.splitext(hfilename)[0]
print(hname)
houtname = hname+"_out.jpg"
print(houtname)
hout = os.path.sep.join([hdir,houtname])
print(hout)

# # construct the argument parser and parse the arguments
# ap = argparse.ArgumentParser()
# ap.add_argument("-d", "--edge-detector", type=str, required=True,
#   help="path to OpenCV's deep learning edge detector")
# ap.add_argument("-i", "--image", type=str, required=True,
#   help="path to input image")
# args = vars(ap.parse_args())

class CropLayer(object):
    def __init__(self, params, blobs):
        # initialize our starting and ending (x, y)-coordinates of
        # the crop
        self.startX = 0
        self.startY = 0
        self.endX = 0
        self.endY = 0

    def getMemoryShapes(self, inputs):
        # the crop layer will receive two inputs -- we need to crop
        # the first input blob to match the shape of the second one,
        # keeping the batch size and number of channels
        (inputShape, targetShape) = (inputs[0], inputs[1])
        (batchSize, numChannels) = (inputShape[0], inputShape[1])
        (H, W) = (targetShape[2], targetShape[3])

        # compute the starting and ending crop coordinates
        self.startX = int((inputShape[3] - targetShape[3]) / 2)
        self.startY = int((inputShape[2] - targetShape[2]) / 2)
        self.endX = self.startX + W
        self.endY = self.startY + H

        # return the shape of the volume (we'll perform the actual
        # crop during the forward pass
        return [[batchSize, numChannels, H, W]]

    def forward(self, inputs):
        # use the derived (x, y)-coordinates to perform the crop
        return [inputs[0][:, :, self.startY:self.endY,
                self.startX:self.endX]]

# load our serialized edge detector from disk
print("[INFO] loading edge detector...")

fpath = os.path.abspath(__file__)
fdir =  os.path.dirname(fpath)
print(fdir)
protoPath = os.path.sep.join([fdir,"hed_model", "deploy.prototxt"])
print(protoPath)
modelPath =  os.path.sep.join([fdir,"hed_model","hed_pretrained_bsds.caffemodel"])
print(modelPath)

net = cv2.dnn.readNetFromCaffe(protoPath, modelPath)

# register our new layer with the model
cv2.dnn_registerLayer("Crop", CropLayer)

# load the input image and grab its dimensions
image = cv2.imread('PATH')
# image = cv2.pyrMeanShiftFiltering(image1,10,20)
(H, W) = image.shape[:2]
# print(image.shape[:2])
# image.shape[:2] =(H*3, W*3)ho
# image = cv2.resize(image,0.5)

# convert the image to grayscale, blur it, and perform Canny
# edge detection
print("[INFO] performing Canny edge detection...")
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
blurred = cv2.GaussianBlur(gray, (5, 5), 0)
# blurred = cv2.addWeighted(gray,1.5,blurred,-0.5,0)
canny = cv2.Canny(blurred,30, 150)


# construct a blob out of the input image for the Holistically-Nested
# Edge Detector

# cc = cv2.cvtColor(canny, cv2.COLOR_GRAY2BGR)
# image = image+cc

# mean = (104.00698793, 116.66876762, 122.67891434),

blob = cv2.dnn.blobFromImage(image, scalefactor=1.0, size=(W, H),
                             # mean=(110,95,95),
                             mean=(104.00698793, 116.66876762, 122.67891434),
                            # mean=(104, 116, 122),
                            #  mean=(150, 120, 130),
                            #  mean=(145, 147, 180),
                             swapRB= False, crop=False)
print( blob)
cv2.waitKey(0)
# set the blob as the input to the network and perform a forward pass
# to compute the edges
print("[INFO] performing holistically-nested edge detection...")
net.setInput(blob)
hed = net.forward()
hed = cv2.resize(hed[0, 0], (W, H))
hed = (255 * hed).astype("uint8")

# show the output edge detection results for Canny and
# Holistically-Nested Edge Detection
cv2.imshow("Input", image)
cv2.imshow("Canny", canny)
cv2.imshow("HED", hed)
cv2.imwrite(hout, hed)

cv2.waitKey(0)

我发现cv2.dnn.blobFromImage()函数中的平均值在算法中非常有效。

Answer 1

另一种方法是使用已经实现为cv2.connectedComponentsWithStats的connected component labeling，而不是使用HED算法。我们可以使用它来分离对象，并将像素簇标记为单独的分段。

二值图像

​

​

import cv2
import numpy as np

# Load image, grayscale, Gaussian Blur, Otsu's threshold
image = cv2.imread('1.jpg')
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
blur = cv2.GaussianBlur(gray, (3,3), 0)
thresh = cv2.threshold(blur, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)[1]

利用连通分量标记生成伪彩色图像

​

​

# Perform connected component labeling
n_labels, labels, stats, centroids = cv2.connectedComponentsWithStats(thresh, connectivity=4)

# Create false color image and color background black
colors = np.random.randint(0, 255, size=(n_labels, 3), dtype=np.uint8)
colors[0] = [0, 0, 0]  # for cosmetic reason we want the background black
false_colors = colors[labels]

现在我们有了分割的像素簇，我们可以找到每个标记对象的质心。此信息已包含在从cv2.connectedComponentsWithStats返回的centroid变量中

​

​

# Obtain centroids
false_colors_centroid = false_colors.copy()
for centroid in centroids:
    cv2.drawMarker(false_colors_centroid, (int(centroid[0]), int(centroid[1])),
                   color=(255, 255, 255), markerType=cv2.MARKER_CROSS)

有很多质心。我们可以使用轮廓区域进行过滤，通过使用stats中包含的信息来仅保留较大的对象。

​

​

# Only keep larger objects by filtering using area
MIN_AREA = 50
false_color_centroid_filter = false_colors.copy()
for i, centroid in enumerate(centroids[1:], start=1):
    area = stats[i, 4]
    if area > MIN_AREA:
        cv2.drawMarker(false_color_centroid_filter, (int(centroid[0]), int(centroid[1])),
                       color=(255, 255, 255), markerType=cv2.MARKER_CROSS)

完整代码

import cv2
import numpy as np

# Load image, grayscale, Gaussian Blur, Otsu's threshold
image = cv2.imread('1.jpg')
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
blur = cv2.GaussianBlur(gray, (3,3), 0)
thresh = cv2.threshold(blur, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)[1]

# Perform connected component labeling
n_labels, labels, stats, centroids = cv2.connectedComponentsWithStats(thresh, connectivity=4)

# Create false color image and color background black
colors = np.random.randint(0, 255, size=(n_labels, 3), dtype=np.uint8)
colors[0] = [0, 0, 0]  # for cosmetic reason we want the background black
false_colors = colors[labels]

# Obtain centroids
false_colors_centroid = false_colors.copy()
for centroid in centroids:
    cv2.drawMarker(false_colors_centroid, (int(centroid[0]), int(centroid[1])),
                   color=(255, 255, 255), markerType=cv2.MARKER_CROSS)

# Only keep larger objects by filtering using area
MIN_AREA = 50
false_color_centroid_filter = false_colors.copy()
for i, centroid in enumerate(centroids[1:], start=1):
    area = stats[i, 4]
    if area > MIN_AREA:
        cv2.drawMarker(false_color_centroid_filter, (int(centroid[0]), int(centroid[1])),
                       color=(255, 255, 255), markerType=cv2.MARKER_CROSS)

cv2.imshow('binary', thresh)
cv2.imshow('false_colors', false_colors)
cv2.imshow('false_colors_centroids', false_colors_centroid)
cv2.imshow('false_color_centroid_filter', false_color_centroid_filter)
cv2.waitKey()