Computer Vision News - September 2018

Code and Implementation : Implementing the DnCNN network using the Keras software package will look as follows: • A first layer of 64 3x3 filters with ReLU activation. • Followed by 15 identical convolutional layers with batch normalization and ReLU activation. • With another 3x3 filter A pre-trained DnCNN network is now included in Matlab out-of-the-box -- you can just run: And test it using the following code: Research 7 Research Computer Vision News def DnCNN(): inpt = Input(shape=(None,None,1)) # 1st layer, Conv+relu x = Conv2D(filters=64, kernel_size=(3,3), strides=(1,1), adding='same')(inpt) x = Activation('relu')(x) # 15 layers, Conv+BN+relu for i in range(15): x = Conv2D(filters=64, kernel_size=(3,3), strides=(1,1), padding='same')(x) x = BatchNormalization(axis=-1, epsilon=1e-3)(x) x = Activation('relu')(x) # last layer, Conv x = Conv2D(filters=1, kernel_size=(3,3), strides=(1,1), padding='same')(x) x = Subtract()([inpt, x]) # input - noise model = Model(inputs=inpt, outputs=x) return model net = denoisingNetwork('DnCNN');

RkJQdWJsaXNoZXIy NTc3NzU=