Image Sharpness Enhancement via High-Frequency Component Translation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing image interpolation techniques result in blurry high-resolution images due to increased pixel count without adding sufficient details, and learning-based algorithms require significant memory and computational resources.
Innovation Solution
An image processing apparatus and method that includes a high-frequency component translating unit, a high-frequency component extracting unit, and a detail-gain generating unit to enhance image sharpness by extracting and translating high-frequency components, generating detail gains, and calculating a weighted superposition to produce a high-frequency component for the output image.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If image interpolation techniques are used to increase pixel count, then the number of pixels is increased, but the generated images become blurry and of low image quality
Solution Approach 1:
The patent extracts high-frequency components from multiple low-resolution images that represent different details of the same scene. By separating and extracting these high-frequency components, the system can combine them with the low-resolution base image to generate a high-resolution image with preserved details, avoiding the blurriness caused by simple interpolation.
Solution Approach 2:
The patent merges multiple low-resolution images taken at approximately the same time to construct a single high-resolution image. By combining the complementary high-frequency information from multiple images, the system achieves high resolution without the quality degradation associated with traditional interpolation methods.
2Manufacturing precision
If multiple low-resolution images are used to construct a high-resolution image, then image details are improved, but memory space consumption increases significantly
Solution Approach 1:
The patent extracts only the necessary high-frequency components from multiple low-resolution images rather than storing and processing the entire images. This extraction approach maintains image detail quality while significantly reducing the memory space required, as only the essential high-frequency information is retained and combined.
3Manufacturing precision
If learning-based algorithms are used to generate high-resolution images, then image quality is improved, but computational complexity and memory requirements increase
Solution Approach 1:
The patent extracts high-frequency components through straightforward filtering and combination operations rather than employing complex learning-based algorithms. This extraction-based approach achieves high image quality by preserving detail information while avoiding the high computational complexity and memory requirements associated with database searching and feature matching in learning-based methods.
Data Source
AI summary
An image processing apparatus includes a high-frequency component translating unit, a high-frequency component extracting unit, a detail-gain generating unit and an image output unit. The high-frequency component translating unit extracts and translates first high-frequency components of an input image to generate a first image. The high-frequency component extracting unit extracts second high-frequency components to generate a second image. The detail-gain generating unit stores a conversion table and generates detail gains respectively associated with input pixels in the input image according to pixel values of the input pixels and the conversion table. The image output unit calculates a weighted superposition of the first image and the second image and generates a high frequency component of an output image according to the weighted superposition and the detail gains.