markdown
#說明
前兩篇皆與這個相關,會寫三篇的原因也是因為在尋找這個問題解答的同時,有搜尋到這樣的三種方法,所以就把他們都記錄下來,這一篇的方法為,偵測文字,所以用已經訓練好的model,去辨識圖片中的文字部分,找到圖片後用方框框起來,這裡有示範一個框成藍色的版本,方便確認真的找到文字,另外實際用的時候直接採用黑色的框就可以了,不過目前用這個方法有遇到一個問題是,如果文字為傾斜的,就無法去偵測出來
#操作流程
##Code
```
import math
import argparse
import os
import cv2
ImgPath = './old'
OutputPath = './new'
parser = argparse.ArgumentParser(
description='Use this script to run text detection deep learning networks using OpenCV.')
# Input argument
parser.add_argument('--input',
help='Path to input image or video file. Skip this argument to capture frames from a camera.')
# Model argument
parser.add_argument('--model', default="./model/frozen_east_text_detection.pb",
help='Path to a binary .pb file of model contains trained weights.'
)
# Width argument
parser.add_argument('--width', type=int, default=320,
help='Preprocess input image by resizing to a specific width. It should be multiple by 32.'
)
# Height argument
parser.add_argument('--height', type=int, default=320,
help='Preprocess input image by resizing to a specific height. It should be multiple by 32.'
)
# Confidence threshold
parser.add_argument('--thr', type=float, default=0.5,
help='Confidence threshold.'
)
# Non-maximum suppression threshold
parser.add_argument('--nms', type=float, default=0.4,
help='Non-maximum suppression threshold.'
)
args = parser.parse_args()
############ Utility functions ############
def decode(scores, geometry, scoreThresh):
detections = []
confidences = []
############ CHECK DIMENSIONS AND SHAPES OF geometry AND scores ############
assert len(scores.shape) == 4, "Incorrect dimensions of scores"
assert len(geometry.shape) == 4, "Incorrect dimensions of geometry"
assert scores.shape[0] == 1, "Invalid dimensions of scores"
assert geometry.shape[0] == 1, "Invalid dimensions of geometry"
assert scores.shape[1] == 1, "Invalid dimensions of scores"
assert geometry.shape[1] == 5, "Invalid dimensions of geometry"
assert scores.shape[2] == geometry.shape[2], "Invalid dimensions of scores and geometry"
assert scores.shape[3] == geometry.shape[3], "Invalid dimensions of scores and geometry"
height = scores.shape[2]
width = scores.shape[3]
for y in range(0, height):
# Extract data from scores
scoresData = scores[0][0][y]
x0_data = geometry[0][0][y]
x1_data = geometry[0][1][y]
x2_data = geometry[0][2][y]
x3_data = geometry[0][3][y]
anglesData = geometry[0][4][y]
for x in range(0, width):
score = scoresData[x]
# If score is lower than threshold score, move to next x
if (score < scoreThresh):
continue
# Calculate offset
offsetX = x * 4.0
offsetY = y * 4.0
angle = anglesData[x]
# Calculate cos and sin of angle
cosA = math.cos(angle)
sinA = math.sin(angle)
h = x0_data[x] + x2_data[x]
w = x1_data[x] + x3_data[x]
# Calculate offset
offset = (
[offsetX + cosA * x1_data[x] + sinA * x2_data[x], offsetY - sinA * x1_data[x] + cosA * x2_data[x]])
# Find points for rectangle
p1 = (-sinA * h + offset[0], -cosA * h + offset[1])
p3 = (-cosA * w + offset[0], sinA * w + offset[1])
center = (0.5 * (p1[0] + p3[0]), 0.5 * (p1[1] + p3[1]))
detections.append((center, (w, h), -1 * angle * 180.0 / math.pi))
confidences.append(float(score))
# Return detections and confidences
return [detections, confidences]
if __name__ == "__main__":
# Read and store arguments
confThreshold = args.thr
nmsThreshold = args.nms
inpWidth = args.width
inpHeight = args.height
model = args.model
img_list = []
# Load network
net = cv2.dnn.readNet('./frozen_east_text_detection.pb')
# Create a new named window
kWinName = "EAST: An Efficient and Accurate Scene Text Detector"
outputLayers = []
outputLayers.append("feature_fusion/Conv_7/Sigmoid")
outputLayers.append("feature_fusion/concat_3")
def read_directory(directory_name):
path = directory_name
GrandpaPath = os.listdir(path)
for i in range(len(GrandpaPath)):
DadPath = os.listdir(path + '/' + GrandpaPath[i])
for j in range(len(DadPath)):
KidPath = os.listdir(path + '/' + GrandpaPath[i] + '/' + DadPath[j])
# print(KidPath)
KidName_path = str(path + '/' + GrandpaPath[i] + '/' + DadPath[j] + '/')
KidName = os.listdir(path + '/' + GrandpaPath[i] + '/' + DadPath[j])
# print(KidPath)
for k in range(len(KidPath)):
OldName = str(KidName_path + KidName[k])
NewName = str(KidName_path + KidName[k])
# print(OldName)
# print(NewName)
# print(NewName)
img_list.append(NewName)
# print(img_list)
return img_list
'''''
for root, dirs, files in os.walk(ImgPath):
for file in files:
if file.endswith(".jpg"):
img_list.append(str(os.path.join(root, file)))
return img_list
'''''
# ---------------------------------------------
'''''
name_of_img = []
for filename in os.listdir(r"./" + directory_name):
path = directory_name + "/" + filename
name_of_img.append(path)
return name_of_img
'''''
def detectwords(ImgPath):
print("start")
img_path = read_directory(ImgPath)
# print(img_path)
for k in range(len(img_path)):
frame = cv2.imread(img_path[k])
# frame = cv2.imread('./106_C_1/0000528/V110138349/C1_0000528_V110138349_0000.jpg')
# print(frame)
# Read frame
# frame = cv2.imread(ImgPath)
# print(ImgPath)
# Get frame height and width
height_ = frame.shape[0]
width_ = frame.shape[1]
rW = width_ / float(inpWidth)
rH = height_ / float(inpHeight)
# Create a 4D blob from frame.
blob = cv2.dnn.blobFromImage(frame, 1.0, (inpWidth, inpHeight), (123.68, 116.78, 103.94), True, False)
# Run the model
net.setInput(blob)
output = net.forward(outputLayers)
t, _ = net.getPerfProfile()
# Get scores and geometry
scores = output[0]
geometry = output[1]
[boxes, confidences] = decode(scores, geometry, confThreshold)
# Apply NMS
indices = cv2.dnn.NMSBoxesRotated(boxes, confidences, confThreshold, nmsThreshold)
for i in indices:
# get 4 corners of the rotated rect
vertices = cv2.boxPoints(boxes[i[0]])
# scale the bounding box coordinates based on the respective ratios
for j in range(4):
vertices[j][0] *= rW
vertices[j][1] *= rH
for j in range(4):
p1 = (vertices[j][0], vertices[j][1])
# p2 = (vertices[(j + 1) % 4][0], vertices[(j + 1) % 4][1])
# cv2.line(frame, p1, p2, (0, 255, 0), 2, cv2.LINE_AA)
if j == 0:
x = (int(p1[0]) - 50, int(p1[1]) + 50)
if j == 2:
y = (int(p1[0] + 50), int(p1[1]) - 50)
cv2.rectangle(frame, x, y, (255, 0, 0), -1)
# Display the frame
cv2.namedWindow('result', cv2.WINDOW_NORMAL)
cv2.resizeWindow("result", 640, 480)
cv2.imshow("result", frame)
cv2.waitKey(-1)
NewName = (img_path[k]).split('/')[-1]
print(NewName)
# NewName = img_path[i].split('/')[-1]
NewName = OutputPath + str(NewName)
import os
path = OutputPath
if not os.path.isdir(path):
os.mkdir(path)
cv2.imwrite(NewName, frame)
detectwords(ImgPath)
print("finish")
```
##引用package
- 參考 : href="https://github.com/oyyd/frozen_east_text_detection.pb
- 下載點 : https://drive.google.com/file/d/1uGoSKfWKU1h8O89s04Gr2JrI3iMB79I8/view?usp=sharing
##DEMO
留言
張貼留言