Image processing apparatus, image processing method, and program

Abstract

There is provided an image processing apparatus including: a prediction tap selection unit which selects a pixel which is a prediction tap used for prediction operation for acquiring a pixel value of a target pixel which is a target from a second image obtained by converting a first image, from the first image; a classification unit which classifies the target pixel to any class from a plurality of classes; a tap coefficient output unit which outputs a tap coefficient of a class of the target pixel from tap coefficients, acquired by learning to minimize an error between a result of the prediction operation using a student image corresponding to the first image and a teacher image corresponding to the second image; and an operation unit which acquires a pixel value of the target pixel by performing the prediction operation using the tap coefficient and the prediction tap.

Description

technical field [0001] The present invention relates to an image processing device, an image processing method and a program, and more particularly to an image processing device, an image processing method and a program capable of preventing image quality degradation. Background technique [0002] As the sharpness improvement processing for improving the sharpness of an image, there is classification adaptation processing or high-frequency emphasis processing. [0003] For example, an input image is converted into an output image with high image quality by an operation using a plurality of tap coefficients acquired by learning and pixel values ​​of a plurality of pixels of the input image (for example, see Japanese Unexamined Patent Application Publication No. 2000-308079 and Japanese Unexamined Patent Application Publication No. 2000-341705). [0004] In the classification adaptation process, the tap coefficients include negative values. Due to the presence of such negativ...

AI Technical Summary

Problems solved by technology

[0005] However, in the case where the pixel values ​​of the input image change sharply, circles occur on the output image due to the influence of negative tap coefficients, thereby degrading the image quality, such as a black abyss around the high-brightness portion of the output image. trace

Images