Textual Image Coding Using Context-Adaptive Remapping
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing image compression algorithms, such as JPEG2000 and H.264/AVC, are inadequate for compressing compound images with textual portions, leading to degraded visual quality due to lossy compression.
Innovation Solution
A novel textual image coding method that decomposes textual blocks into base colors and an index map, using context-adaptive arithmetic encoding and remapping to reduce entropy and achieve higher compression ratios without sacrificing visual quality.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If higher compression is applied to reduce image data size, then storage and transmission efficiency is improved, but visual quality of the image is degraded
Solution Approach 1:
The patent segments the image into distinct textual blocks and graphical blocks, applying different compression algorithms to each type. Textual blocks are processed using a specialized text compression algorithm that preserves character integrity, while graphical blocks use traditional image compression. This segmentation allows optimal compression for each block type without compromising overall visual quality.
Solution Approach 2:
The patent applies different compression strategies to different regions of the image based on their content type. Textual regions receive localized text-optimized compression that maintains sharp edges and character clarity, while graphical regions receive image-optimized compression. This local quality approach ensures each region is compressed with the most appropriate method for its specific characteristics.
2Productivity
If traditional image compression algorithms are used on compound images, then general compression is achieved, but textual portions are degraded
Solution Approach 1:
The patent identifies and segments textual portions from graphical portions in compound images, then applies a specialized text compression algorithm to textual blocks while using traditional image compression for graphical blocks. This segmentation enables targeted compression optimization for text regions, preserving character sharpness and readability while maintaining overall compression efficiency.
Solution Approach 2:
The patent changes the compression parameters and algorithms based on the detected content type. For textual blocks, it uses a text-optimized algorithm with parameters tuned for preserving alphanumeric characters and symbols, while graphical blocks use standard image compression parameters. This parameter adaptation allows each block type to be compressed with optimal settings for its specific characteristics.
Data Source
AI summary
Textual image coding involves coding textual portions of an image. In an example embodiment, a textual block of an image is decomposed into multiple base colors and an index map, with the index map having index values that each reference a base color so as to represent the textual block. A set of neighbor index values are ascertained for a particular index of the index map. A context that matches the neighbor index values is generated from among multiple contexts. The matching context includes a set of symbols. At least one symbol-to-value mapping is determined based on the matching context and a symbol to which the particular index corresponds. The particular index is remapped to a particular value in accordance with the symbol-to-value mapping and the symbol to which the particular index corresponds.