thresh = thresh[y:y + h, x:x + w]
#contours, hierarchy = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)[-2:]
ans = ''
(_, contours, _) = cv2.findContours(thresh.copy(), cv2.RETR_EXTERNAL,
cv2.CHAIN_APPROX_SIMPLE)
#print("length:{}".format(len(contours)))
if len(contours) > 0:
for c in contours:
if cv2.contourArea(c) > 400:
#contour = max(contours, key=cv2.contourArea)
cv2.drawContours(frame, contours, -1, (0, 255, 0), 2)
#print("Area:{}".format(cv2.contourArea(c)))
(x1, y1, w1, h1) = cv2.boundingRect(c)
roi = thresh[y1:y1 + h1, x1:x1 + w1]
roi = preprocess(roi, 28, 28)
roi = np.expand_dims(img_to_array(roi), axis=0)
pred = model.predict(roi)
pred = np.argmax(pred, axis=1) + 1
print("Pred:{}".format(str(pred)))
cv2.putText(frame, str(pred), (x1 - 5, y1 - 5),
cv2.FONT_HERSHEY_SIMPLEX, 0.7, (0, 0, 255), 2)
#cv2.rectangle(frame, (x1, y1), (x1+w1, y1+h1), (0,255,0),2)
cv2.rectangle(frame, (x, y), (x + w, y + h), (0, 255, 0), 2)
cv2.imshow('frame', frame)
cv2.imshow('thresh', thresh)
if cv2.waitKey(1) == 27:
break
cv2.destroyAllWindows()
import argparse
import cv2
import os
ap = argparse.ArgumentParser()
ap.add_argument("-d", "--dataset", required=True, help="path to input dataset")
ap.add_argument("-m", "--model", required=True, help="path to output model")
args = vars(ap.parse_args())
data = []
labels = []
for imagePath in paths.list_images(args["dataset"]):
image = cv2.imread(imagePath)
image = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
image = preprocess(image, 28, 28)
image = img_to_array(image)
data.append(image)
label = imagePath.split(os.path.sep)[-2]
labels.append(label)
data = np.array(data, dtype="float") / 255.0
labels = np.array(labels)
(trainX, testX, trainY, testY) = train_test_split(data,
labels,
test_size=0.25,
random_state=42)
lb = LabelBinarizer().fit(trainY)
trainY = lb.transform(trainY)
ap.add_argument("-d", "--dataset", required=True,
help="path to the input dataset")
ap.add_argument("-o", "--output", required=True,
help="path to output model")
args = vars(ap.parse_args())
# init data and labels
data = []
labels = []
# loop over the images in the dataset
for imagePath in paths.list_images(args["dataset"]):
# load the image, preprocess it and store it in data list
image = cv2.imread(imagePath)
image = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
image = preprocess(image, width=28, height=28)
image = img_to_array(image)
data.append(image)
# extract label from the image path and append to labels list
label = imagePath.split(os.path.sep)[-2]
labels.append(label)
# normalize the data
data = np.array(data, dtype="float") / 255.0
labels = np.array(labels)
# split the data into train/test
(trainX, testX, trainY, testY) = train_test_split(data, labels,
test_size=0.25)
def main(input_digit):
capture_digit("training_data/" + str(input_digit))
x, y, w, h = 0, 0, 300, 300
max_pics = 10
image_no = 0
blueUpper = np.array([140,255,255], dtype = "uint8")
blueLower = np.array([100,50,50], dtype = "uint8")
cap=cv2.VideoCapture(0)
if cap.isOpened():
ret,frame=cap.read()
else :
ret = False
while ret :
ret,frame=cap.read()
hsv= cv2.cvtColor(frame,cv2.COLOR_BGR2HSV)
# Thresholding Range
# # Threshold the HSV image to get only blue colors
blue=cv2.inRange(hsv,blueLower,blueUpper)
# Gaussian Blur
blur = cv2.GaussianBlur(blue, (3, 3), 0)
ret, thresh = cv2.threshold(blur, 175, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)
thresh = thresh[y:y + h, x:x + w]
#contours, hierarchy = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)[-2:]
ans=''
(_, contours, _) = cv2.findContours(thresh.copy(), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
#print("length:{}".format(len(contours)))
if len(contours) > 0:
for c in contours:
if cv2.contourArea(c)>200:
#contour = max(contours, key=cv2.contourArea)
cv2.drawContours(frame, contours, -1, (0, 255, 0), 2 )
#print("Area:{}".format(cv2.contourArea(c)))
(x1, y1, w1, h1) = cv2.boundingRect(c)
roi = thresh[y1:y1+h1, x1:x1+w1]
roi = preprocess(roi, 28, 28)
image_no+=1
cv2.imwrite("Training_Data/" + str(input_digit)+"/"+str(image_no)+ ".jpg",roi)
print("Image Count : {}".format(image_no))
cv2.rectangle(frame, (x1, y1), (x1+w1, y1+h1), (0,255,0),2)
cv2.rectangle(frame, (x, y), (x+w, y+h), (0, 255, 0), 2)
cv2.imshow('frame', frame)
cv2.imshow('thresh', thresh)
if image_no==1000:
break
if cv2.waitKey(1)==27:
break
cv2.destroyAllWindows()
cap.release()
cv2.CHAIN_APPROX_SIMPLE)[0]
cnts = sorted(cnts, key=cv2.contourArea, reverse=True)[:4]
cnts = contours.sort_contours(cnts)[0]
# init the output image as grayscale with 3 channels
output = cv2.merge([gray] * 3)
predictions = []
# loop over the contours
for c in cnts:
# compute the bounding box and extract the digits
(x, y, w, h) = cv2.boundingRect(c)
roi = gray[y - 5:y + h + 5, x - 5:x + w + 5]
# preprocess the roi and classify it
roi = preprocess(roi, width=28, height=28)
roi = np.expand_dims(img_to_array(roi), axis=0) / 255.0
pred = model.predict(roi).argmax(axis=1)[0] + 1
predictions.append(str(pred))
# draw prediction on image
cv2.rectangel(output, (x - 2, y - 2), (x + w + 4, y + h + 4),
(0, 255, 0), 1)
cv2.putText(output, str(pred), (x - 5, y - 5),
cv2.FONT_HERSHEY_SIMPLEX, 0.55, (0, 255, 0), 2)
# show the output image
print("[INFO] captcha: {}".format("".join(predictions)))
cv2.imshow("Output", output)
cv2.waitKey()