def extract_chars():
# construct the argument parser and parse the arguments
ap = argparse.ArgumentParser()
ap.add_argument("-i", "--image", required=True, help="Path to the image")
args = vars(ap.parse_args())
# load the image and define the window width and height
image = cv2.imread(args["image"])
(winW, winH) = (192, 192)
# loop over the image pyramid
for resized in pyramid(image, scale=1.5):
# loop over the sliding window for each layer of the pyramid
for (x, y, window) in sliding_window(resized,
stepSize=32,
windowSize=(winW, winH)):
# if the window does not meet our desired window size, ignore it
if window.shape[0] != winH or window.shape[1] != winW:
continue
import pytesseract
#print(pytesseract.image_to_string(window))
with open('extracted_info.txt', 'a') as info_file:
info_file.write(
pytesseract.image_to_string(window).encode('utf-8') + '\n')
info_file.write('#\n')
clone = resized.copy()
cv2.rectangle(clone, (x, y), (x + winW, y + winH), (0, 255, 0), 2)
cv2.imshow("Window", clone)
cv2.waitKey(1)
time.sleep(0.025)
img_path = '/Users/nihaar/Documents/4yp/4yp/code/sliding-window/img_sweep39_normalised.mat'
# load the image and define the window width and height
# image = cv2.imread(args["image"])
neg_mat1 = scio.loadmat(img_path)
image = neg_mat1['imgnormali']
(winW, winH) = (36, 36)
# angle = (0,45,90,135)
# image = image[:,:,1]
# image = image/128
ori = orientations(image)
detections = np.empty((0,2))
for i in ori:
# loop over the image pyramid
for resized in pyramid(i, scale=1.5):
# loop over the sliding window for each layer of the pyramid
for (x, y, window) in sliding_window(resized, stepSize=10, windowSize=(winW, winH)):
# if the window does not meet our desired window size, ignore it
if window.shape[0] != winH or window.shape[1] != winW:
continue
# THIS IS WHERE YOU WOULD PROCESS YOUR WINDOW, SUCH AS APPLYING A
# MACHINE LEARNING CLASSIFIER TO CLASSIFY THE CONTENTS OF THE
# WINDOW
# x_test1 =
# loaded_model = cPickle.load(open('~/svm-classifier.pkl', 'rb'))
# y_score = loaded_model.decision_function(x_test1)
window = np.reshape(window,[1,36,36,1])
# window = np.reshape(window,[-1,1681])
from pyimagesearch.helpers import sliding_window
import argparse
import time
import cv2
# construct the argument parser and parse the arguments
ap = argparse.ArgumentParser()
ap.add_argument("-i", "--image", required=True, help="Path to the image")
args = vars(ap.parse_args())
# load the image and define the window width and height
image = cv2.imread(args["image"])
(winW, winH) = (128, 128)
# loop over the image pyramid
for resized in pyramid(image, scale=1.5):
# loop over the sliding window for each layer of the pyramid
for (x, y, window) in sliding_window(resized,
stepSize=32,
windowSize=(winW, winH)):
# if the window does not meet our desired window size, ignore it
if window.shape[0] != winH or window.shape[1] != winW:
continue
# THIS IS WHERE YOU WOULD PROCESS YOUR WINDOW, SUCH AS APPLYING A
# MACHINE LEARNING CLASSIFIER TO CLASSIFY THE CONTENTS OF THE
# WINDOW
# since we do not have a classifier, we'll just draw the window
clone = resized.copy()
cv2.rectangle(clone, (x, y), (x + winW, y + winH), (0, 255, 0), 2)
# 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(imag, (startX, startY), (endX, endY), (0, 255, 0), 2)
# show the output image
cv2.imshow("Text Detection", imag)
cv2.waitKey(0)
#time.sleep(1)
for resized in pyramid(image,scale=2):
for (x,y,window) in sliding_window(resized, stepSize=32, windowSize=(winW,winH)):
if window.shape[0] != winH or window.shape[1]!= winW:
continue
east(window)
clone = resized.copy()
cv2.rectangle(clone, (x,y), (x + winW, y + winH), (0,255,0), 2)
cv2.imshow("window", clone)
time.sleep(0.025)
ap.add_argument("-i", "--image", required=True, help="Path to the image")
args = vars(ap.parse_args())
stepSize = 0
# load the image and define the window width and height
image = cv2.imread(args["image"], cv2.IMREAD_GRAYSCALE)
img = np.asarray(image)
#p = img.shape
#print (p)
# imread loads the image
(winW, winH) = (80, 80)
#Sliding window size
# loop over the image pyramid
for a in range(0, 2):
for b in range(0, 2):
for resized in pyramid(image):
# loop over the sliding window for each layer of the pyramid
for (x, y, window) in sliding_window(resized,
stepSize=24,
windowSize=(winW, winH)):
# if the window does not meet our desired window size, ignore it
# or check for the boundary conditions step2 and check if the pixel is grey or not step1 and then
#calculate the ratio.
if window.shape[0] != winH or window.shape[1] != winW:
continue
#stepSize=stepSize-10
#winW = winW - 20
#winH = winH - 20
'''
Classifier for images that are required, is to be inserted here.
Like for tick marks and comments that ae to be detected.
# construct the argument parser and parse the arguments
ap = argparse.ArgumentParser()
ap.add_argument("-i", "--image", required=True, help="Path to the image")
ap.add_argument("-s",
"--scale",
type=float,
default=1.5,
help="scale factor size")
args = vars(ap.parse_args())
# load the image
image = cv2.imread(args["image"])
# METHOD #1: No smooth, just scaling.
# loop over the image pyramid
for (i, resized) in enumerate(pyramid(image, scale=args["scale"])):
# show the resized image
cv2.imshow("Layer {}".format(i + 1), resized)
cv2.waitKey(0)
# close all windows
cv2.destroyAllWindows()
# METHOD #2: Resizing + Gaussian smoothing.
for (i, resized) in enumerate(pyramid_gaussian(image, downscale=2)):
# if the image is too small, break from the loop
if resized.shape[0] < 30 or resized.shape[1] < 30:
break
# show the resized image
cv2.imshow("Layer {}".format(i + 1), resized)
#from pyima/Users/Owner/Downloads/sliding-windowgesearch.helpers import sliding_window
import argparse
import time
import cv2
# construct the argument parser and parse the arguments
ap = argparse.ArgumentParser()
ap.add_argument("-i", "--image", required=True, help="Path to the image")
args = vars(ap.parse_args())
# load the image and define the window width and height
image = cv2.imread(args["image"])
(winW, winH) = (128, 128)
# loop over the image pyramid
for resized in pyramid(image, scale=1.5):
# loop over the sliding window for each layer of the pyramid
for (x, y, window) in sliding_window(resized, stepSize=32, windowSize=(winW, winH)):
# if the window does not meet our desired window size, ignore it
if window.shape[0] != winH or window.shape[1] != winW:
continue
# THIS IS WHERE YOU WOULD PROCESS YOUR WINDOW, SUCH AS APPLYING A
# MACHINE LEARNING CLASSIFIER TO CLASSIFY THE CONTENTS OF THE
# WINDOW
# since we do not have a classifier, we'll just draw the window
clone = resized.copy()
cv2.rectangle(clone, (x, y), (x + winW, y + winH), (0, 255, 0), 2)
cv2.imshow("Window", clone)
cv2.waitKey(1)