說明
這篇要說明安裝 tesseract 這個套件的一些步驟，這個套件主要在做文字的偵測跟辨識，目前想用於偵測影像中的文字並視為雜訊而去除，所以安裝這個套件
不過因為本身使用 Pycharm 當作IDE，可是好像在安裝的過程中無法以平常的方式直接安裝，所以參考網路的作法
屬於Python 安裝套件的基本方式再修正一些步驟，基本的流程是直接下載套件包，然後引入環境變數，之後再用 pip 來裝
但這邊前面兩個步驟相同，最後pip 的方式則省略
操作流程
下載EXE
先到 下載地址，下載與電腦本身要相符，否則會安裝失敗，例如電腦為64位元則安裝W64
下載成功會有下載好的 exe檔案
EXE 安裝
依照圖片中的說明安裝，大部分都是按下一步，其中有一個多國語言要打勾，還有實際安裝的路徑要記錄下來，等下環境變數會用到
設定環境變數
因為安裝的時間會有點久，可以先來設定環境變數
依照圖片的方式設定，在3的時候 在Path 新增剛剛記錄下來的路徑
因為參考其他作者提供的方法在系統變數下，如果有 Path，也加入
加入系統變數設定新資料夾
在系統變數下，新增一個變數名稱為TESSDATA_PREFIX，變數值為剛剛記錄下來的路徑加上/tessdata
安裝完成
Demo偵測文字
Code
# Import required modules
import cv2 as cv
import math
import argparse
import numpy as np
import cv2
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
# Load network
net = cv.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")
# Read frame
frame = cv.imread("./images/car_wash.jpg")
# 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 = cv.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()
label = 'Inference time: %.2f ms' % (t * 1000.0 / cv.getTickFrequency())
# Get scores and geometry
scores = output[0]
geometry = output[1]
[boxes, confidences] = decode(scores, geometry, confThreshold)
# Apply NMS
indices = cv.dnn.NMSBoxesRotated(boxes, confidences, confThreshold, nmsThreshold)
for i in indices:
# get 4 corners of the rotated rect
vertices = cv.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])
print(j)
cv.line(frame, p1, p2, (0, 255, 0), 2, cv.LINE_AA)
# print(p1,p2)
if j == 0:
x = (int(p1[0]), int(p1[1]))
if j == 2:
y = (int(p1[0]), int(p1[1]))
print(y)
#cv2.rectangle(frame, x, y, (0, 0, 0), -1)
# Put efficiency information
# cv.putText(frame, label, (0, 15), cv.FONT_HERSHEY_SIMPLEX, 0.5, (0, 0, 255))
# Display the frame
cv2.namedWindow('result', cv2.WINDOW_NORMAL)
cv2.resizeWindow("result", 640, 480)
cv.imshow("result", frame)
cv.waitKey(0)
留言
張貼留言