Local Tone Mapping for Symbol Reading in High Dynamic Range Images
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing image-based symbol reading technologies face challenges in decoding symbols with high dynamic range images due to issues like poor illumination, specular reflections, and limited bit depth, which result in incomplete capture of symbol information, leading to poor decoding performance.
Innovation Solution
The implementation of local tone mapping techniques that map each pixel in a high dynamic range image to a lower bit depth based on its neighborhood intensity and contrast, allowing for improved contrast enhancement and data retention in over-exposed and under-exposed regions, thereby enhancing decoding success rates.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If a single 8-bit image is captured to meet limited bit depth requirements, then device complexity is reduced, but symbol information is lost in over-exposed and under-exposed regions
Solution Approach 1:
The patent segments the image processing into multiple 8-bit images captured at different exposure levels (under-exposed, properly exposed, over-exposed). Each image captures symbol information in specific intensity ranges, and the segments are later fused to reconstruct the complete symbol information that would be lost in a single 8-bit image.
Solution Approach 2:
The patent transitions from a single-dimensional 8-bit image to a multi-dimensional representation by capturing images at multiple exposure levels. This adds the dimension of exposure variation, allowing the system to preserve symbol information across different intensity ranges while maintaining 8-bit depth constraints.
2Loss of information
If multiple images are captured and fused to capture complete symbol information, then information completeness is improved, but processing time and complexity increase
Solution Approach 1:
The patent performs preliminary actions by capturing multiple exposure images in advance and performing fusion processing before symbol decoding. This ensures that complete symbol information is available in the fused image, preventing information loss during decoding while maintaining efficient real-time processing.
3Device complexity
If traditional tone mapping is applied to compress HDR to 8-bit, then bit depth is reduced, but symbol details in high contrast regions are lost
Solution Approach 1:
The patent applies local quality by using adaptive thresholding and local contrast enhancement techniques during the fusion process. Different regions of the image receive different processing treatments based on their local intensity characteristics, preserving symbol details in high contrast regions while maintaining 8-bit depth throughout the final image.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Embodiments related to local tone mapping for symbol reading. A local pixel neighborhood metric is determined for at least one raw pixel in a region-of-interest, which identifies on one or more raw pixels near the at least one raw pixel. A local mapping function is determined for the at least one raw pixel that maps the value of the raw pixel to a mapped pixel value with a mapped bit depth that is smaller than the bit depth associated with the raw image. The local mapping function is based on a value of at least one other raw pixel near the at least one raw pixel within the local pixel neighborhood metric, and at least one parameter determined based on the raw image. A mapped image is computed for the region-of-interest by applying the local mapping function to the raw image.