$ pip install --upgrade imutils

# import the necessary packagesfrom imutils.object_detection importnon_max_suppressionimport numpy as npimport argparseimport timeimport cv2 # construct the argument parser and parse theargumentsap = argparse.ArgumentParser()ap.add_argument("-i","--image", type=str,           help="pathto input image")ap.add_argument("-east","--east", type=str,           help="pathto input EAST text detector")ap.add_argument("-c","--min-confidence", type=float, default=0.5,           help="minimumprobability required to inspect a region")ap.add_argument("-w","--width", type=int, default=320,           help="resizedimage width (should be multiple of 32)")ap.add_argument("-e","--height", type=int, default=320,           help="resizedimage height (should be multiple of 32)")args = vars(ap.parse_args())

# load the input image and grab the imagedimensionsimage = cv2.imread(args["image"])orig = image.copy()(H, W) = image.shape[:2] # set the new width and height and thendetermine the ratio in change# for both the width and height(newW, newH) = (args["width"],args["height"])rW = W / float(newW)rH = H / float(newH) # resize the image and grab the new image dimensionsimage = cv2.resize(image, (newW, newH))(H, W) = image.shape[:2]

# define the two output layer names for theEAST detector model that# we are interested -- the first is theoutput probabilities and the# second can be used to derive the boundingbox coordinates of textlayerNames = [           "feature_fusion/Conv_7/Sigmoid",           "feature_fusion/concat_3"]

# load the pre-trained EAST text detectorprint("[INFO] loading EAST textdetector...")net = cv2.dnn.readNet(args["east"]) # construct a blob from the image and thenperform a forward pass of# the model to obtain the two output layersetsblob = cv2.dnn.blobFromImage(image, 1.0, (W,H),           (123.68,116.78, 103.94), swapRB=True, crop=False)start = time.time()net.setInput(blob)(scores, geometry) = net.forward(layerNames)end = time.time() # show timing information on text predictionprint("[INFO] text detection took {:.6f}seconds".format(end - start))

# grab the number of rows and columns fromthe scores volume, then# initialize our set of bounding boxrectangles and corresponding# confidence scores(numRows, numCols) = scores.shape[2:4]rects = []confidences = [] # loop over the number of rowsfor 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           forx in range(0, numCols):                     #if our score does not have sufficient probability, ignore it                     ifscoresData[x] < args["min_confidence"]:                                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 suppressweak, overlapping bounding# boxesboxes = non_max_suppression(np.array(rects),probs=confidences) # loop over the bounding boxesfor (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 imagecv2.imshow("Text Detection", orig)cv2.waitKey(0)

$ python text_detection.py --imageimages/lebron_james.jpg            --eastfrozen_east_text_detection.pb[INFO] loading EAST text detector...[INFO] text detection took 0.142082 seconds

$ python text_detection.py --image images/car_wash.png           --eastfrozen_east_text_detection.pb[INFO] loading EAST text detector...[INFO] text detection took 0.142295 seconds

$ python text_detection.py --image images/sign.jpg           --eastfrozen_east_text_detection.pb[INFO] loading EAST text detector...[INFO] text detection took 0.141675 seconds