Color Image Code Classification via HSV Conversion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Color-based image codes are difficult to recognize due to color changes caused by varying lighting and camera characteristics, making it challenging to accurately classify colors in mobile computing environments.
Innovation Solution
A method involving pixel sampling from each cell of the image code, recognizing the color channel with the highest value, and classifying colors based on frequency or using brightness and saturation values to group cells into achromatic and chromatic groups for hue extraction, enabling accurate color classification despite environmental changes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If color based image codes are used to increase data storage capacity, then the data storage capacity is improved, but the recognition accuracy deteriorates due to color changes from lighting and camera characteristics
Solution Approach 1:
The patent converts color information from RGB color space to HSV color space, changing the parameter representation. By using hue, saturation, and value parameters instead of red, green, and blue values, the system can better distinguish colors under varying lighting conditions. The hue parameter specifically captures color information that remains relatively stable across different lighting environments, thereby maintaining recognition accuracy while preserving color-based data storage capacity.
Solution Approach 2:
The patent introduces an intermediary processing step that converts RGB values to HSV values before color classification. This intermediary transformation acts as a bridge between the raw color data (which is sensitive to lighting) and the final color classification (which needs to be stable). The HSV color space serves as an intermediary representation that separates color information from lighting information, enabling accurate recognition despite environmental variations.
2Device complexity
If conventional color classification methods are used, then the processing is simple, but the color classification accuracy deteriorates under varying lighting conditions
Solution Approach 1:
The patent transforms the color representation parameters from RGB to HSV, which fundamentally changes how color information is organized and processed. This parameter transformation enables the system to achieve high color classification accuracy under varying lighting conditions while maintaining relatively simple processing logic. The conversion to HSV space allows for straightforward threshold-based classification based on hue and saturation values.
Solution Approach 2:
The patent segments color information into three distinct components: hue, saturation, and value. By separating these components, the system can focus on hue and saturation for color classification while using value for brightness-based decisions. This segmentation allows the processing to remain simple while achieving high accuracy, as each component can be processed independently with simple comparison operations.
3Measurement precision
If pixel sampling from each cell is performed to improve color recognition, then the color classification accuracy is improved, but the processing time increases
Solution Approach 1:
The patent applies partial action by sampling only a subset of pixels from each cell rather than processing all pixels. Specifically, it samples pixels at regular intervals or at specific positions within each cell. This partial sampling approach maintains sufficient color classification accuracy while significantly reducing the number of pixels that need to be processed, thereby decreasing processing time and making the system suitable for mobile devices with limited computational resources.
Solution Approach 2:
The patent extracts only the essential color information from each cell by sampling representative pixels and converting them to HSV space. Instead of processing all pixel data, it extracts the key hue and saturation values needed for color classification. This extraction approach reduces processing time while preserving the critical information needed for accurate color recognition.
Data Source
AI summary
Provided is a method of classifying colors of a color based image code. The colors of each cell forming the color based image code are classified by sampling a predetermined number of pixels from each cell and then applying a max channel based clustering method, a white balance based color clustering method, a single-linkage algorithm based color classification method, a K-means algorithm based color classification method, or the like. Accordingly, the colors of an image code can be accurately recognized despite of a color distortion due to characteristics of a camera, a printing medium, etc.


