Image Analysis Apparatus Excluding Target Objects from Text Recognition
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing image analysis systems face challenges in accurately performing character recognition within text areas due to the presence of target objects that are falsely recognized as part of the text, leading to incorrect interpretations.
Innovation Solution
An image analysis apparatus is designed with an extraction section to identify text areas, an acquisition section to define target-object conditions, an exclusion section to search and exclude target objects from character recognition, and a recognition section to perform character recognition on the text areas from which target objects have been excluded, using methods such as reference images or line arrangements to determine similarity and exclude irrelevant objects.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If character recognition is performed on the entire text area including target objects, then the recognition process covers all elements in the area, but target objects are falsely recognized as text characters leading to incorrect interpretation
Solution Approach 1:
The text area is segmented into multiple regions: text character regions and target object regions. The extraction unit divides the text area based on characteristics such as line arrangements, allowing the recognition unit to process only the text character regions while excluding target objects, thus preventing false recognition while maintaining comprehensive coverage of actual text
Solution Approach 2:
Target objects are extracted and excluded from the text area before character recognition. The extraction unit identifies and removes regions corresponding to target objects based on their distinctive characteristics (such as not being arranged in line patterns), leaving only pure text regions for the recognition unit to process, thereby eliminating false recognition sources
2Productivity
If the text area is processed without excluding target objects, then the processing is simple and fast, but false recognition occurs reducing interpretation accuracy
Solution Approach 1:
The extraction unit performs preliminary extraction of text areas and identification of target objects before the recognition unit processes the text. By pre-separating text regions from target objects based on structural characteristics like line arrangements, the system prepares clean text inputs for recognition, maintaining high processing speed while ensuring recognition accuracy
Data Source
AI summary
An image analysis apparatus includes an extraction section, an acquisition section, an exclusion section, and a recognition section. The extraction section extracts, from a target image, a text area including a character. The acquisition section acquires a predetermined target-object condition. The predetermined target-object condition defines a target object. The exclusion section searches for the target object in the text area and excludes the target object from a target of character recognition. The text area is extracted by the extraction section. The target object satisfies the predetermined target-object condition. The recognition section performs character recognition on the text area. The text area is an area from which the target object is excluded.