python通过EAST文本检测器使用OpenCV检测图像中的文

2021-02-20 本文已影响0人水煮鱼又失败了

1 场景

在python环境下，使用EAST文本检测器使用OpenCV检测自然场景图像中的文本。

即通过算法，检测标识出来自然图像中的文字区域。

可以检测图像中的文字区域和视频中的文字区域。

之后可以截取文字区域图像，再通过OCR算法，检测出文字的内容。

检测效果如下：

1.png

2 官网

（1）英文官方地址

https://www.pyimagesearch.com/2018/08/20/opencv-text-detection-east-text-detector/

（2）中文译文地址

https://segmentfault.com/a/1190000018622750

（3）源码地址（百度网盘）

链接：https://pan.baidu.com/s/1DlWXraYRqCsg5WJ-B3te8w
提取码：cmcn

源码项目结构：

.
├── images
│   ├── car_wash.png
│   ├── lebron_james.jpg
│   └── sign.jpg
├── frozen_east_text_detection.pb
├── text_detection.py
└── text_detection_video.py

3 依赖

（1）CV2

pip install opencv-python

（2）numpy

pip install numpy

（3）argparse

pip install argparse

4 代码

4.1 识别图片

（1）识别代码text_detection.py

# USAGE
# python text_detection.py --image images/lebron_james.jpg --east frozen_east_text_detection.pb

# import the necessary packages
from imutils.object_detection import non_max_suppression
import numpy as np
import argparse
import time
import cv2

# 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
image = cv2.imread(args["image"])
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)

（2）使用

python text_detection.py --image images/car_wash.png --east frozen_east_text_detection.pb

结果如下：

2.png

4.2 识别视频

（1）识别代码text_detection_video.py

# USAGE
# python text_detection_video.py --east frozen_east_text_detection.pb

# import the necessary packages
from imutils.video import VideoStream
from imutils.video import FPS
from imutils.object_detection import non_max_suppression
import numpy as np
import argparse
import imutils
import time
import cv2

def decode_predictions(scores, geometry):
    # 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])

    # return a tuple of the bounding boxes and associated confidences
    return (rects, confidences)

# construct the argument parser and parse the arguments
ap = argparse.ArgumentParser()
ap.add_argument("-east", "--east", type=str, required=True,
    help="path to input EAST text detector")
ap.add_argument("-v", "--video", type=str,
    help="path to optinal input video file")
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())

# initialize the original frame dimensions, new frame dimensions,
# and ratio between the dimensions
(W, H) = (None, None)
(newW, newH) = (args["width"], args["height"])
(rW, rH) = (None, None)

# 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"])

# if a video path was not supplied, grab the reference to the web cam
if not args.get("video", False):
    print("[INFO] starting video stream...")
    vs = VideoStream(src=0).start()
    time.sleep(1.0)

# otherwise, grab a reference to the video file
else:
    vs = cv2.VideoCapture(args["video"])

# start the FPS throughput estimator
fps = FPS().start()

# loop over frames from the video stream
while True:
    # grab the current frame, then handle if we are using a
    # VideoStream or VideoCapture object
    frame = vs.read()
    frame = frame[1] if args.get("video", False) else frame

    # check to see if we have reached the end of the stream
    if frame is None:
        break

    # resize the frame, maintaining the aspect ratio
    frame = imutils.resize(frame, width=1000)
    orig = frame.copy()

    # if our frame dimensions are None, we still need to compute the
    # ratio of old frame dimensions to new frame dimensions
    if W is None or H is None:
        (H, W) = frame.shape[:2]
        rW = W / float(newW)
        rH = H / float(newH)

    # resize the frame, this time ignoring aspect ratio
    frame = cv2.resize(frame, (newW, newH))

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

    # decode the predictions, then  apply non-maxima suppression to
    # suppress weak, overlapping bounding boxes
    (rects, confidences) = decode_predictions(scores, geometry)
    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 frame
        cv2.rectangle(orig, (startX, startY), (endX, endY), (0, 255, 0), 2)

    # update the FPS counter
    fps.update()

    # show the output frame
    cv2.imshow("Text Detection", orig)
    key = cv2.waitKey(1) & 0xFF

    # if the `q` key was pressed, break from the loop
    if key == ord("q"):
        break

# stop the timer and display FPS information
fps.stop()
print("[INFO] elasped time: {:.2f}".format(fps.elapsed()))
print("[INFO] approx. FPS: {:.2f}".format(fps.fps()))

# if we are using a webcam, release the pointer
if not args.get("video", False):
    vs.stop()

# otherwise, release the file pointer
else:
    vs.release()

# close all windows
cv2.destroyAllWindows()