Convolutional neural network demosaicing algorithm based on residual interpolation

Abstract

The invention belongs to the technical field of image processing, and particularly relates to a convolutional neural network demosaicing algorithm based on residual interpolation. To solve the problemin an existing image recovery method that recovery is not accurate enough in a slant edge area and the image overall resolution is low, an edge detection algorithm is firstly utilized to recover a green channel, then a residual interpolation method is adopted to recover a red plane and a blue plane, after a residual interpolation result is obtained, finally a convolutional neural network is adopted as a correction item to further improve a result image, a demosaicing result is used as input of the convolutional neural network, the residue between a corresponding full color image and the demosaicing result is used as a label of the convolutional neural network, and through training, the weight of the convolutional neural network is gradually corrected. According to the convolutional neuralnetwork demosaicing algorithm based on the residual interpolation, not only is the edge in the horizontal direction and the vertical direction detected, but also the detection of the edge in the slant direction is added, so that the image is more accurately recovered in the slant edge area, the image resolution is improved, and the obtained demosaiced image edge is clearer.

Description

technical field [0001] The invention belongs to the technical field of image processing, in particular to a convolutional neural network demosaicing algorithm based on residual interpolation. Background technique [0002] Single-sensor color imaging technology is widely used in the digital camera industry. In a single-sensor camera, a color filter array (CFA: Color Filter Array) is covered on the surface of the sensor, and each pixel only samples red and green. One of the three color components, blue and blue. If the full-color image is restored, the two lost color components need to be estimated. We call the process of estimating the lost color as demosaicing. The most widely used color image today is the image of the Bayer CFA model. In the Bayer CFA model, the green pixels are sampled according to the quincunx grid, and the red and blue pixels are sampled according to the rectangular grid. Among them, the green samples are red or blue double the sample size. So far, res...

AI Technical Summary

Problems solved by technology

However, these methods are equivalent to isotropic low-pass filtering, which will produce significant defects such as edge blur and zipper effect.

In response to this defect, an adaptive direction interpolation algorithm can be used to detect the direction of the horizontal and vertical edges using the gradient, and interpolate along the horizontal and vertical edge directions respectively, but this method will reduce the overall resolution of the image; The method based on the smooth transition criterion of hue interpolates according to the constant assumption of color difference (red-green, blue-green), but the obtained full-color image has a large interpolation error where the green component value changes abruptly.

The residual interpolation algorithm is used to improve on the basis of chromatic aberration interpolation. This method performs interpolation on the residual domain. Compared with the chromatic aberration domain, the residual domain is smoother and the interpolation accuracy is higher, but this method is not accurate enough in the recovery of the hypotenuse area.

Images