Image Processing Device Region Expansion Character Grouping
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional image processing techniques are time-consuming when attempting to specify character groups in an image, as they require separate character recognition for each region within the group.
Innovation Solution
An image processing device and method that includes means to obtain image data, expand and unite regions, determine character regions, and perform processing on identified character regions, with additional features to restrict region union based on size and fill non-character regions with background color to prevent incorrect grouping.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If separate character recognition is performed on each character region using conventional OCR techniques, then character recognition accuracy is maintained, but processing time increases significantly
Solution Approach 1:
The patent segments the image processing task into two levels: first segments character groups from the background using region expansion, then segments individual characters within each group. This hierarchical segmentation allows parallel processing of multiple character groups simultaneously, reducing overall processing time while maintaining recognition accuracy through focused OCR on smaller character-only regions.
Solution Approach 2:
The patent merges adjacent character regions that belong to the same character group into a single processing unit. By expanding character regions and merging them with neighboring character regions, the system creates unified character group regions that can be processed more efficiently than individual characters, reducing the total number of separate OCR operations required.
2Device complexity
If all expanded regions are processed as character regions, then character group detection is simplified, but non-character objects may be incorrectly identified
Solution Approach 1:
The patent applies different processing qualities to different regions: character regions undergo full character recognition processing, while non-character regions (identified by size filtering) are excluded from character recognition. This local quality differentiation ensures that only appropriate regions are processed as characters, maintaining high identification accuracy while keeping the overall system relatively simple through automated filtering.
Solution Approach 2:
The patent changes the parameter of region size as a filtering criterion. By comparing the size of expanded regions against a predetermined threshold, the system automatically adjusts which regions proceed to character recognition. This parameter-based filtering simplifies the processing workflow while reliably distinguishing character regions from non-character objects based on their size characteristics.
3Adaptability or versatility
If region expansion is performed without size restrictions, then character grouping is more comprehensive, but processing load increases and non-character regions are included
Solution Approach 1:
The patent performs preliminary size-based filtering of expanded regions before character recognition processing. By comparing region sizes against predetermined thresholds in advance, the system pre-identifies and excludes non-character regions, preventing unnecessary processing load. This preliminary action maintains comprehensive character grouping for valid regions while improving overall processing efficiency through early elimination of inappropriate candidates.
Data Source
AI summary
To quickly specify a region of a character group included in an image, image obtaining means of an image processing device obtains the image data. Expansion means expands and unites a plurality of regions respectively indicating objects included in an image indicated by the image data obtained by the image obtaining means. Character region determining means determines whether all or some of the regions, which are expanded and united by the expansion means, are character regions. Processing performing means performs predetermined processing on a region that is determined by the character region determining means as a character region.