在 Python 中加载 OpenCV EAST 文本检测器时出错

Question

我正在尝试使用 EAST 文本检测器来检测图像中的文本区域，但在加载预训练的 EAST 文本检测器时遇到问题。

以下是我的text_detection.py文件

from imutils.object_detection import non_max_suppression
import numpy as np
import argparse
import time
import cv2
import requests
import urllib

# construct the argument parser and parse the arguments
ap = argparse.ArgumentParser()
ap.add_argument("-i", "--image", type=str,help="path to input image")
ap.add_argument("-east", "--east", type=str,help="path to input EAST text detector")
ap.add_argument("-c", "--min-confidence", type=float, default=0.5,help="minimum probability required to inspect a region")
ap.add_argument("-w", "--width", type=int, default=320,help="resized image width (should be multiple of 32)")
ap.add_argument("-e", "--height", type=int, default=320,help="resized image height (should be multiple of 32)")
args = vars(ap.parse_args())

# load the input image and grab the image dimensions
req = urllib.request.urlopen('https://hips.hearstapps.com/ghk.h-cdn.co/assets/18/02/mandy-hale-inspirational-quote.jpg')
arr = np.asarray(bytearray(req.read()), dtype=np.uint8)
image = cv2.imdecode(arr, -1)
orig = image.copy()

(H, W) = image.shape[:2]

# set the new width and height and then determine the ratio in change
# for both the width and height
(newW, newH) = (args["width"], args["height"])
rW = W / float(newW)
rH = H / float(newH)

# resize the image and grab the new image dimensions
image = cv2.resize(image, (newW, newH))
(H, W) = image.shape[:2]

# define the two output layer names for the EAST detector model that
# we are interested -- the first is the output probabilities and the
# second can be used to derive the bounding box coordinates of text
layerNames = [
    "feature_fusion/Conv_7/Sigmoid",
    "feature_fusion/concat_3"]

# load the pre-trained EAST text detector
print("[INFO] loading EAST text detector...")
net = cv2.dnn.readNet(args["east"])

# construct a blob from the image and then perform a forward pass of
# the model to obtain the two output layer sets
blob = cv2.dnn.blobFromImage(image, 1.0, (W, H),
                             (123.68, 116.78, 103.94), swapRB=True, crop=False)
start = time.time()
net.setInput(blob)
(scores, geometry) = net.forward(layerNames)
end = time.time()

# show timing information on text prediction
print("[INFO] text detection took {:.6f} seconds".format(end - start))

# grab the number of rows and columns from the scores volume, then
# initialize our set of bounding box rectangles and corresponding
# confidence scores
(numRows, numCols) = scores.shape[2:4]
rects = []
confidences = []

# loop over the number of rows
for y in range(0, numRows):
    # extract the scores (probabilities), followed by the geometrical
    # data used to derive potential bounding box coordinates that
    # surround text
    scoresData = scores[0, 0, y]
    xData0 = geometry[0, 0, y]
    xData1 = geometry[0, 1, y]
    xData2 = geometry[0, 2, y]
    xData3 = geometry[0, 3, y]
    anglesData = geometry[0, 4, y]

# loop over the number of columns
for x in range(0, numCols):
    # if our score does not have sufficient probability, ignore it
    if scoresData[x] < args["min_confidence"]:
        continue

    # compute the offset factor as our resulting feature maps will
    # be 4x smaller than the input image
    (offsetX, offsetY) = (x * 4.0, y * 4.0)

    # extract the rotation angle for the prediction and then
    # compute the sin and cosine
    angle = anglesData[x]
    cos = np.cos(angle)
    sin = np.sin(angle)

    # use the geometry volume to derive the width and height of
    # the bounding box
    h = xData0[x] + xData2[x]
    w = xData1[x] + xData3[x]

    # compute both the starting and ending (x, y)-coordinates for
    # the text prediction bounding box
    endX = int(offsetX + (cos * xData1[x]) + (sin * xData2[x]))
    endY = int(offsetY - (sin * xData1[x]) + (cos * xData2[x]))
    startX = int(endX - w)
    startY = int(endY - h)

    # add the bounding box coordinates and probability score to
    # our respective lists
    rects.append((startX, startY, endX, endY))
    confidences.append(scoresData[x])

# apply non-maxima suppression to suppress weak, overlapping bounding
# boxes
boxes = non_max_suppression(np.array(rects), probs=confidences)

# loop over the bounding boxes
for (startX, startY, endX, endY) in boxes:
    # scale the bounding box coordinates based on the respective
    # ratios
    startX = int(startX * rW)
    startY = int(startY * rH)
    endX = int(endX * rW)
    endY = int(endY * rH)

    # draw the bounding box on the image
    cv2.rectangle(orig, (startX, startY), (endX, endY), (0, 255, 0), 2)

# show the output image
cv2.imshow("Text Detection", orig)
cv2.waitKey(0)

# apply non-maxima suppression to suppress weak, overlapping bounding
# boxes
boxes = non_max_suppression(np.array(rects), probs=confidences)

# loop over the bounding boxes
for (startX, startY, endX, endY) in boxes:
    # scale the bounding box coordinates based on the respective
    # ratios
    startX = int(startX * rW)
    startY = int(startY * rH)
    endX = int(endX * rW)
    endY = int(endY * rH)

    # draw the bounding box on the image
    cv2.rectangle(orig, (startX, startY), (endX, endY), (0, 255, 0), 2)

# show the output image
cv2.imshow("Text Detection", orig)
cv2.waitKey(0)

一个错误

net = cv2.dnn.readNet(args["east"]) cv2.error: OpenCV(3.4.3) C:\projects\opencv-python\opencv\modules\dnn\src\dnn.cpp:3443: error: (-2:Unspecified error) 无法确定文件的原始框架：在函数 'cv::dnn::experimental_dnn_34_v7::readNet'

在加载 EAST 文本检测器时显示

我正在使用 opencv-python 3.4.3.18。这个错误的原因是什么？跟Python版本有关系吗？

Answer 1

问题是我没有通过论点。要使用 PyCharm 传递参数，请在“运行”菜单 select "edit configurations" 上传递参数 --image ：输入图像的路径。 --east : EAST 场景文本检测器模型文件路径。 --min-confidence ：确定文本的概率阈值。 --width ：调整后的图像宽度 --height : 调整后的图像高度

Answer 2

如果有人用编译好的c++ sample program, you need to pass the arguments with the correct syntax to opencv's CommandLineParser:

./a.out --input=./path/to/image.jpg --model=frozen_east_text_detection.pb

在 Python 中加载 OpenCV EAST 文本检测器时出错

Error on loading OpenCV EAST text detector in Python

python

ocr

opencv

pycharm