Create app.py

app.py

@@ -0,0 +1,136 @@
+# remove warning message
+import json
+import os
+from typing import final
+os.environ['TF_CPP_MIN_LOG_LEVEL'] = '3'
+
+# required library
+import cv2
+import numpy as np
+import matplotlib.pyplot as plt
+import matplotlib.gridspec as gridspec
+from local_utils import detect_lp, getPath
+from os.path import splitext,basename
+from keras.models import model_from_json
+from keras.preprocessing.image import load_img, img_to_array
+from keras.applications.mobilenet_v2 import preprocess_input
+from sklearn.preprocessing import LabelEncoder
+import glob
+import gradio as gr
+from transfer import load_model
+
+def sort_contours(cnts,reverse = False):
+    i = 0
+    boundingBoxes = [cv2.boundingRect(c) for c in cnts]
+    (cnts, boundingBoxes) = zip(*sorted(zip(cnts, boundingBoxes),
+                                        key=lambda b: b[1][i], reverse=reverse))
+    return cnts
+
+def predict_from_model(image,model,labels):
+    image = cv2.resize(image,(80,80))
+    image = np.stack((image,)*3, axis=-1)
+    prediction = labels.inverse_transform([np.argmax(model.predict(image[np.newaxis,:]))])
+    return prediction
+
+def classify(img,resize=False,Dmax=650, Dmin = 270):
+    wpod_net_path = "wpod-net.json"
+    wpod_net = load_model(wpod_net_path)
+    ##preprocess_image
+    #img = cv2.imread(image_path)
+    img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
+    img = img / 255
+    if resize:
+        img = cv2.resize(img, (224,224))
+
+    ##get_plate
+    vehicle = img
+    ratio = float(max(vehicle.shape[:2])) / min(vehicle.shape[:2])
+    side = int(ratio * Dmin)
+    bound_dim = min(side, Dmax)
+    _ , LpImg, _, cor = detect_lp(wpod_net, vehicle, bound_dim, lp_threshold=0.5)
+
+    
+
+    if (len(LpImg)): #check if there is at least one license image
+    # Scales, calculates absolute values, and converts the result to 8-bit.
+        plate_image = cv2.convertScaleAbs(LpImg[0], alpha=(255.0))
+        
+        # convert to grayscale and blur the image
+        gray = cv2.cvtColor(plate_image, cv2.COLOR_BGR2GRAY)
+        blur = cv2.GaussianBlur(gray,(7,7),0)
+        
+        # Applied inversed thresh_binary 
+        binary = cv2.threshold(blur, 180, 255,
+                            cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)[1]
+        
+        kernel3 = cv2.getStructuringElement(cv2.MORPH_RECT, (3, 3))
+        thre_mor = cv2.morphologyEx(binary, cv2.MORPH_DILATE, kernel3)
+
+  
+    cont, _  = cv2.findContours(binary, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
+
+    test_roi = plate_image.copy()
+    crop_characters = []
+    digit_w, digit_h = 30, 60
+
+    for c in sort_contours(cont):
+        (x, y, w, h) = cv2.boundingRect(c)
+        ratio = h/w
+        if 1<=ratio<=3.5: # Only select contour with defined ratio
+            if h/plate_image.shape[0]>=0.5: # Select contour which has the height larger than 50% of the plate
+                # Draw bounding box arroung digit number
+                cv2.rectangle(test_roi, (x, y), (x + w, y + h), (0, 255,0), 2)
+
+                # Sperate number and gibe prediction
+                curr_num = thre_mor[y:y+h,x:x+w]
+                curr_num = cv2.resize(curr_num, dsize=(digit_w, digit_h))
+                _, curr_num = cv2.threshold(curr_num, 220, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)
+                crop_characters.append(curr_num)
+
+    #print("Detect {} letters...".format(len(crop_characters)))
+    # Load model architecture, weight and labels
+    json_file = open('MobileNets_character_recognition.json', 'r')
+    loaded_model_json = json_file.read()
+    json_file.close()
+    model = model_from_json(loaded_model_json)
+    model.load_weights("License_character_recognition_weight.h5")
+
+    labels = LabelEncoder()
+    labels.classes_ = np.load('license_character_classes.npy')
+
+    #fig = plt.figure(figsize=(15,3))
+    #cols = len(crop_characters)
+    #grid = gridspec.GridSpec(ncols=cols,nrows=1,figure=fig)
+
+    final_string = ''
+    for i,character in enumerate(crop_characters):
+        #fig.add_subplot(grid[i])
+        title = np.array2string(predict_from_model(character,model,labels))
+        #plt.title('{}'.format(title.strip("'[]"),fontsize=20))
+        final_string+=title.strip("'[]")
+        #plt.axis(False)
+        #plt.imshow(character,cmap='gray')
+
+    try:
+        cols = len(crop_characters)
+    except ValueError:
+        return "No Plate Detected"
+    else:
+        if len(crop_characters) == 0:
+            return "No Plate Detected"
+        else: 
+            return final_string
+        
+    
+
+
+gr.Interface(fn=classify, 
+            inputs=gr.inputs.Image(), 
+            outputs="text",
+            title = "Plate Number Recognition",
+            examples = ['29Z5550.jpeg', 'germany_car_plate.jpg', 'india_car_plate.jpg', 'turkey_car_plate.jpg', 'vietnam_car_rectangle_plate.jpg'],
+            description="Automaticall Recognize the symbols contained in the number plates of a motor vehicle when read from an image provided. It will help the authorities to automatically detect motor vehicle that will violate number-coding scheme.",
+            allow_flagging="never").launch(inbrowser=True)
+
+#classify("C:/Users/JomerJuan/Documents/Deep Learning/Plate Number Recognition/Plate_examples/germany_car_plate.jpg",resize=False,Dmax=650, Dmin = 270)
+