Merge branch 'it16076662' into 'master'

It16076662 H.T.M.D Samaranayake

See merge request !9

Identify and segmentate the brain tumor-backend/main.py

+from flask import Flask,render_template,request
+from keras.models import Sequential,Model
+from keras.layers import Dense,Activation,Flatten,Dropout
+from keras.layers import Conv2D,MaxPooling2D,UpSampling2D,Input
+import keras.backend as K
+import numpy as np
+
+import cv2
+
+app=Flask(__name__)
+
+def load_autoencoder_model():
+
+	input_img = Input(shape=(256, 256, 1))
+
+	x = Conv2D(32, (3, 3), activation='relu', padding='same')(input_img)
+	x = MaxPooling2D((2, 2), padding='same')(x)
+	x = Conv2D(32, (3, 3), activation='relu', padding='same')(x)
+	encoded = MaxPooling2D((2, 2), padding='same')(x)
+
+	x = Conv2D(32, (3, 3), activation='relu', padding='same')(encoded)
+	x = UpSampling2D((2, 2))(x)
+	x = Conv2D(32, (3, 3), activation='relu', padding='same')(x)
+	x = UpSampling2D((2, 2))(x)
+	decoded = Conv2D(1, (3, 3), activation='sigmoid', padding='same')(x)
+	autoencoder = Model(input_img, decoded)
+	autoencoder.load_weights('autoencorders_noise_removal.h5')
+	autoencoder.compile(optimizer='adam', loss='binary_crossentropy')
+
+	return autoencoder
+
+def load_brain_tumor_detect_model():
+
+	
+	K.clear_session()
+	model=Sequential()
+	model.add(Conv2D(256,(3,3),input_shape=(50,50,1)))
+	model.add(Activation('relu'))
+	model.add(MaxPooling2D(pool_size=(2,2)))
+    #The first CNN layer followed by Relu and MaxPooling layers
+	model.add(Conv2D(128,(3,3)))
+	model.add(Activation('relu'))
+	model.add(MaxPooling2D(pool_size=(2,2)))
+    #The second convolution layer followed by Relu and MaxPooling layers
+	model.add(Flatten())
+    #Flatten layer to stack the output convolutions from second convolution layer
+	model.add(Dense(64,activation='relu'))
+    #Dense layer of 64 neurons
+	model.add(Dense(2,activation='softmax'))
+    #The Final layer with two outputs for two categories
+	model.compile(loss='categorical_crossentropy',optimizer='adam',metrics=['accuracy'])
+    
+   # model.load_weights('cat&dogs_v1.h5')
+   
+	model.load_weights('braintumordata_v1.h5')
+
+	return model
+
+@app.route('/')
+def index():
+
+	return render_template('brainTumorIdentification.html')
+count=0
+@app.route('/brain_tumor_detect',methods=['GET', 'POST'])
+def brain_tumor_detect():
+	global count
+	count=count+1
+	category={0:'No',1:'Yes '}
+
+	model=load_brain_tumor_detect_model()
+	autoencoder_model=load_autoencoder_model()
+
+	file = request.files['myFile']
+	file_name=file.filename
+	file.save(file_name)
+
+	imgori=cv2.imread(file_name)
+	img=imgori
+	gray=cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
+	resized=cv2.resize(gray,(50,50))
+	normalized=resized/255.0
+	reshaped=np.reshape(normalized,(1,50,50,1))
+	
+	result=model.predict(reshaped)
+	label=np.argmax(result,axis=1)[0]
+	prob =np.max(result,axis=1)[0]
+	prob=round(prob,2)*100
+
+
+	encoder_resized = cv2.resize(gray, (256, 256))
+	encoder_normalized = encoder_resized / 255.0
+	encoder_reshaped = np.reshape(encoder_normalized, (1, 256, 256, 1))
+
+	encoder_result = autoencoder_model.predict(encoder_reshaped)
+	#print(encoder_result.shape,np.max(encoder_result))
+
+	img[:50,:]=[0,255,0]
+    
+	cv2.putText(img,str(category[label]),(10,40),cv2.FONT_HERSHEY_SIMPLEX,1,(255,255,255),2)
+	cv2.putText(img,str(prob),(200,40),cv2.FONT_HERSHEY_SIMPLEX,1,(255,255,255),2)
+
+	cv2.imwrite('static/tumor_detect'+str(count)+'.jpg',img)
+	path1="static/tumor_detect"+str(count)+".jpg"
+	
+	frame=imgori
+	gray=cv2.cvtColor(frame,cv2.COLOR_BGR2GRAY)
+	
+	ret,thresh=cv2.threshold(gray,168,255,cv2.THRESH_BINARY)
+	contours, hierarchy = cv2.findContours(thresh, cv2.RETR_TREE,cv2.CHAIN_APPROX_SIMPLE)
+	
+	#print('no. contours:',len(contours))
+	
+	for cnt in contours:
+	#cv2.drawContours(frame, [cnt], 0, (0,255,255), 3)
+		area=cv2.contourArea(cnt)
+		#print(area)
+		if(area>500):
+			x,y,w,h = cv2.boundingRect(cnt)
+			img = cv2.rectangle(frame,(x,y),(x+w,y+h),(0,255,0),2)
+			cv2.drawContours(frame, [cnt], 0, (0,0,255), 1)
+			cv2.imwrite('static/tumor_segment'+str(count)+'.jpg',frame)
+			
+	path2="static/tumor_segment"+str(count)+".jpg"
+	path3='static/autoencoder' + str(count) + '.jpg'
+
+	encoder_pixel_max=np.max(encoder_result)
+	cv2.imwrite('static/autoencoder' + str(count) + '.jpg', encoder_result.reshape(256,256)*255/encoder_pixel_max)
+	return render_template('brainTumorIdentification.html',path1=path1,path2=path2,path3=path3)
+
+app.run(debug=True)