Ranking convolutional neural network constructing method and image processing method and apparatus thereof

An image processing method, comprising:

• receiving an input hazy image;
• determining, by using a ranking convolutional neural network, a feature vector for a current pixel of the input hazy image, wherein the ranking convolutional neural network comprises a ranking layer, a convolution layer, a downsampling layer and a fully-connecting layer, the ranking layer is configured to sort an output of a previous layer of the ranking layer, generate an output of the ranking layer according to the sorted output, and output the output of the ranking layer to a next layer of the ranking layer;
• inputting the feature vector for the current pixel into a random forest regression model to obtain a haziness for the current pixel;
• and
• determining a clear image corresponding to the input hazy image according to the haziness and ambient light information.

A ranking convolutional neural network constructing apparatus, wherein the ranking convolutional neural network comprises a ranking layer, a convolution layer, a downsampling layer, and a fully-connecting layer, and the ranking layer is configured to sort an output of a previous layer of the ranking layer, generate an output of the ranking layer according to the sorted output, and output the output of the ranking layer to a next layer of the ranking layer, the apparatus comprising:

• a receiving module configured to receive an input feature image which is represented by a two dimensional matrix;
• a processing module configured to perform a ranking operation, a convolution operation, a downsampling operation and a fully-connecting operation to the input feature image, according to a preset order of the ranking layer, the convolution layer, the downsampling layer and the fully-connecting layer in the ranking convolutional neural network to obtain an output feature corresponding to the input feature image, wherein the output feature is a feature vector, the ranking operation is performed in the ranking layer, the convolution operation is performed in the convolution layer, the downsampling operation is performed in the downsampling layer, and the fully-connecting operation is performed in the fully-connecting layer;
• and
• an outputting module configured to output the output feature.