django init

.gitignore

@@ -0,0 +1,2 @@
+.gitignore
+/node_modules

bibrecognition/bibrecognition/asgi.py

@@ -0,0 +1,16 @@
+"""
+ASGI config for bibrecognition project.
+
+It exposes the ASGI callable as a module-level variable named ``application``.
+
+For more information on this file, see
+https://docs.djangoproject.com/en/3.0/howto/deployment/asgi/
+"""
+
+import os
+
+from django.core.asgi import get_asgi_application
+
+os.environ.setdefault('DJANGO_SETTINGS_MODULE', 'bibrecognition.settings')
+
+application = get_asgi_application()

bibrecognition/bibrecognition/settings.py

@@ -0,0 +1,120 @@
+"""
+Django settings for bibrecognition project.
+
+Generated by 'django-admin startproject' using Django 3.0.2.
+
+For more information on this file, see
+https://docs.djangoproject.com/en/3.0/topics/settings/
+
+For the full list of settings and their values, see
+https://docs.djangoproject.com/en/3.0/ref/settings/
+"""
+
+import os
+
+# Build paths inside the project like this: os.path.join(BASE_DIR, ...)
+BASE_DIR = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
+
+
+# Quick-start development settings - unsuitable for production
+# See https://docs.djangoproject.com/en/3.0/howto/deployment/checklist/
+
+# SECURITY WARNING: keep the secret key used in production secret!
+SECRET_KEY = '__q^s(i^&vo%n&ybt0i&nk09(=9mt6^9#!l(v3_gjtfca^bp-8'
+
+# SECURITY WARNING: don't run with debug turned on in production!
+DEBUG = True
+
+ALLOWED_HOSTS = []
+
+
+# Application definition
+
+INSTALLED_APPS = [
+    'django.contrib.admin',
+    'django.contrib.auth',
+    'django.contrib.contenttypes',
+    'django.contrib.sessions',
+    'django.contrib.messages',
+    'django.contrib.staticfiles',
+]
+
+MIDDLEWARE = [
+    'django.middleware.security.SecurityMiddleware',
+    'django.contrib.sessions.middleware.SessionMiddleware',
+    'django.middleware.common.CommonMiddleware',
+    'django.middleware.csrf.CsrfViewMiddleware',
+    'django.contrib.auth.middleware.AuthenticationMiddleware',
+    'django.contrib.messages.middleware.MessageMiddleware',
+    'django.middleware.clickjacking.XFrameOptionsMiddleware',
+]
+
+ROOT_URLCONF = 'bibrecognition.urls'
+
+TEMPLATES = [
+    {
+        'BACKEND': 'django.template.backends.django.DjangoTemplates',
+        'DIRS': [],
+        'APP_DIRS': True,
+        'OPTIONS': {
+            'context_processors': [
+                'django.template.context_processors.debug',
+                'django.template.context_processors.request',
+                'django.contrib.auth.context_processors.auth',
+                'django.contrib.messages.context_processors.messages',
+            ],
+        },
+    },
+]
+
+WSGI_APPLICATION = 'bibrecognition.wsgi.application'
+
+
+# Database
+# https://docs.djangoproject.com/en/3.0/ref/settings/#databases
+
+DATABASES = {
+    'default': {
+        'ENGINE': 'django.db.backends.sqlite3',
+        'NAME': os.path.join(BASE_DIR, 'db.sqlite3'),
+    }
+}
+
+
+# Password validation
+# https://docs.djangoproject.com/en/3.0/ref/settings/#auth-password-validators
+
+AUTH_PASSWORD_VALIDATORS = [
+    {
+        'NAME': 'django.contrib.auth.password_validation.UserAttributeSimilarityValidator',
+    },
+    {
+        'NAME': 'django.contrib.auth.password_validation.MinimumLengthValidator',
+    },
+    {
+        'NAME': 'django.contrib.auth.password_validation.CommonPasswordValidator',
+    },
+    {
+        'NAME': 'django.contrib.auth.password_validation.NumericPasswordValidator',
+    },
+]
+
+
+# Internationalization
+# https://docs.djangoproject.com/en/3.0/topics/i18n/
+
+LANGUAGE_CODE = 'en-us'
+
+TIME_ZONE = 'UTC'
+
+USE_I18N = True
+
+USE_L10N = True
+
+USE_TZ = True
+
+
+# Static files (CSS, JavaScript, Images)
+# https://docs.djangoproject.com/en/3.0/howto/static-files/
+
+STATIC_URL = '/static/'

bibrecognition/bibrecognition/urls.py

@@ -0,0 +1,21 @@
+"""bibrecognition URL Configuration
+
+The `urlpatterns` list routes URLs to views. For more information please see:
+    https://docs.djangoproject.com/en/3.0/topics/http/urls/
+Examples:
+Function views
+    1. Add an import:  from my_app import views
+    2. Add a URL to urlpatterns:  path('', views.home, name='home')
+Class-based views
+    1. Add an import:  from other_app.views import Home
+    2. Add a URL to urlpatterns:  path('', Home.as_view(), name='home')
+Including another URLconf
+    1. Import the include() function: from django.urls import include, path
+    2. Add a URL to urlpatterns:  path('blog/', include('blog.urls'))
+"""
+from django.contrib import admin
+from django.urls import path
+
+urlpatterns = [
+    path('admin/', admin.site.urls),
+]

bibrecognition/bibrecognition/wsgi.py

@@ -0,0 +1,16 @@
+"""
+WSGI config for bibrecognition project.
+
+It exposes the WSGI callable as a module-level variable named ``application``.
+
+For more information on this file, see
+https://docs.djangoproject.com/en/3.0/howto/deployment/wsgi/
+"""
+
+import os
+
+from django.core.wsgi import get_wsgi_application
+
+os.environ.setdefault('DJANGO_SETTINGS_MODULE', 'bibrecognition.settings')
+
+application = get_wsgi_application()

bibrecognition/manage.py

@@ -0,0 +1,21 @@
+#!/usr/bin/env python
+"""Django's command-line utility for administrative tasks."""
+import os
+import sys
+
+
+def main():
+    os.environ.setdefault('DJANGO_SETTINGS_MODULE', 'bibrecognition.settings')
+    try:
+        from django.core.management import execute_from_command_line
+    except ImportError as exc:
+        raise ImportError(
+            "Couldn't import Django. Are you sure it's installed and "
+            "available on your PYTHONPATH environment variable? Did you "
+            "forget to activate a virtual environment?"
+        ) from exc
+    execute_from_command_line(sys.argv)
+
+
+if __name__ == '__main__':
+    main()

main.py

@@ -3,172 +3,188 @@ try:
 except ImportError:
     import Image
 from cv2 import cv2
-import pytesseract 
+import pytesseract
+import argparse
 import numpy as np
 from imutils.object_detection import non_max_suppression
 
 
 pytesseract.pytesseract.tesseract_cmd = r'C:\Program Files\Tesseract-OCR\tesseract.exe'
-faceCascade = cv2.CascadeClassifier('haarcascade/haarcascade_frontalface_default.xml')
-
-def findText(img, i):
-    # @TODO
-    # make ROI from found texts and return a array of imgs. Then try recon text by pytesseract
-    image = img
-    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) = (320, 320)
-    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('./EAST/frozen_east_text_detection.pb')
-
-    # 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)
-    net.setInput(blob)
-    (scores, geometry) = net.forward(layerNames)
-
-    # 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] < 0.5:
-                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_"+str(i), orig)
+faceCascade = cv2.CascadeClassifier(
+    'haarcascade/haarcascade_frontalface_default.xml')
 
 
-# MAIN PROGRAM
+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 = []
 
-image = cv2.imread('imgs/bib_01.jpg')
-gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
+	# 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]
 
-faces = faceCascade.detectMultiScale(
-    gray,
-    scaleFactor=1.1,
-    minNeighbors=5,
-    minSize=(30, 30)
-)
+		# 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
 
-faceNumber = len(faces)
-# print('znaleziono '+str(faceNumber)+' twarzy \n')
-ROI = [0] * faceNumber
+			# 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)
 
-for (x, y, w, h) in faces:
-    cv2.rectangle(image, (x, y), (x+w, y+h), (0, 255, 0), 2)
+			# 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)
 
-i = 0
-for (x, y, w, h) in faces:
-    x = int( x - (3*w/4) )
-    y = int(y + 1.5*h)
-    w = int(2.5*w)
-    h = int(3.5*h)
-    if x < 0:
-        x = 1
-    # cv2.rectangle(image, (x, y), (x+w, y+h), (0, 0, 255), 2)
-    # print('y = '+str(y)+', y+h = '+str(y+h)+', x = '+str(x)+', x+w = '+str(x+w)+'\n')
-    crop_img = image[y:y+h, x:x+w]
-    ROI[i] = crop_img
-    # cv2.imshow("cropped_"+str(i), crop_img[i])
-    i = i + 1
+			# use the geometry volume to derive the width and height
+			# of the bounding box
+			h = xData0[x] + xData2[x]
+			w = xData1[x] + xData3[x]
 
-i = 0
-for x in ROI:
-    findText(x, i)
-    # x = cv2.cvtColor(x,cv2.COLOR_BGR2GRAY)
-    # kernel = np.ones((1,1), np.uint8)
-    # x = cv2.dilate(x, kernel, iterations = 1)
-    # x = cv2.erode(x, kernel, iterations=1)
-    # x = cv2.adaptiveThreshold(x, 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C, cv2.THRESH_BINARY, 11, 2)
+			# 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)
 
-    # cv2.imshow("Text Detection_"+str(i), orig)
-    # cv2.imshow("cropped_"+str(i), x)
-    # cv2.imwrite("cropped_"+str(i)+"_thres.jpg", x)
-    # result = pytesseract.image_to_string(Image.open("cropped_"+str(i)+"_thres.jpg"))
-    # print(result)
-    i = i + 1
+			# add the bounding box coordinates and probability score
+			# to our respective lists
+			rects.append((startX, startY, endX, endY))
+			confidences.append(scoresData[x])
 
-cv2.imshow("Faces found", image)
-cv2.waitKey()
+	# return a tuple of the bounding boxes and associated confidences
+	return (rects, confidences)
 
-#print(pytesseract.image_to_string(Image.open('imgs/bib_01.jpg')))
+
+# 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="nearest multiple of 32 for resized width")
+ap.add_argument("-e", "--height", type=int, default=320,
+                help="nearest multiple of 32 for resized height")
+ap.add_argument("-p", "--padding", type=float, default=0.0,
+                help="amount of padding to add to each border of ROI")
+args = vars(ap.parse_args())
+
+# load the input image and grab the image dimensions
+image = cv2.imread(args["image"])
+orig = image.copy()
+(origH, origW) = 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 = origW / float(newW)
+rH = origH / 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)
+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)
+
+# initialize the list of results
+results = []
+
+# 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)
+
+	# in order to obtain a better OCR of the text we can potentially
+	# apply a bit of padding surrounding the bounding box -- here we
+	# are computing the deltas in both the x and y directions
+	dX = int((endX - startX) * args["padding"])
+	dY = int((endY - startY) * args["padding"])
+
+	# apply padding to each side of the bounding box, respectively
+	startX = max(0, startX - dX)
+	startY = max(0, startY - dY)
+	endX = min(origW, endX + (dX * 2))
+	endY = min(origH, endY + (dY * 2))
+
+	# extract the actual padded ROI
+	roi = orig[startY:endY, startX:endX]
+
+	# in order to apply Tesseract v4 to OCR text we must supply
+	# (1) a language, (2) an OEM flag of 4, indicating that the we
+	# wish to use the LSTM neural net model for OCR, and finally
+	# (3) an OEM value, in this case, 7 which implies that we are
+	# treating the ROI as a single line of text
+	config = ("-l eng --oem 1 --psm 7")
+	text = pytesseract.image_to_string(roi, config=config)
+
+	# add the bounding box coordinates and OCR'd text to the list
+	# of results
+	results.append(((startX, startY, endX, endY), text))
+
+# sort the results bounding box coordinates from top to bottom
+results = sorted(results, key=lambda r: r[0][1])
+
+# loop over the results
+for ((startX, startY, endX, endY), text) in results:
+	# display the text OCR'd by Tesseract
+	print("OCR TEXT")
+	print("========")
+	print("{}\n".format(text))
+
+	# strip out non-ASCII text so we can draw the text on the image
+	# using OpenCV, then draw the text and a bounding box surrounding
+	# the text region of the input image
+	text = "".join([c if ord(c) < 128 else "" for c in text]).strip()
+	output = orig.copy()
+	cv2.rectangle(output, (startX, startY), (endX, endY),
+               (0, 0, 255), 2)
+	cv2.putText(output, text, (startX, startY - 20),
+             cv2.FONT_HERSHEY_SIMPLEX, 1.2, (0, 0, 255), 3)
+
+	# show the output image
+	cv2.imshow("Text Detection", output)
+	cv2.waitKey(0)