Character Recognition Using Position and Direction Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing character recognition devices face challenges in achieving high speed and accuracy when recognizing characters in images shot by mobile cameras, as they often rely on excessive word knowledge that leads to increased processing time and reduced accuracy due to variations in lighting and distortion, and the use of positional information alone limits the efficiency of word dictionary utilization.
Innovation Solution
A character recognition system that utilizes both shooting position and direction information to efficiently extract relevant word knowledge from a map database, incorporating position corresponding and non-corresponding-to-position information to enhance recognition accuracy and speed, by transmitting only necessary data between mobile and fixed station devices.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a large volume of word knowledge is used in character recognition processing, then recognition accuracy may be improved, but recognition speed is lowered and processing time increases
Solution Approach 1:
The patent extracts only the necessary word knowledge from the database by determining a shooting object range based on GPS position and camera direction, then selecting words within that range. This extraction principle resolves the contradiction by taking out only the relevant subset of word knowledge needed for accurate recognition, avoiding the need to process the entire database while maintaining high accuracy.
Solution Approach 2:
The patent applies local quality by creating a localized word dictionary specific to the shooting object range rather than using a universal dictionary. The word knowledge is tailored to the local area around the camera position and direction, providing high recognition accuracy for the specific scene while reducing the overall volume of words to be processed.
2Measurement precision
If the shooting object range is determined to be large, then more words are included in the word dictionary, but character recognition speed is reduced due to increased processing volume
Solution Approach 1:
The patent extracts words within a specifically determined shooting object range from the database, rather than loading all possible words. By calculating the range based on GPS position, map data, and camera direction, it extracts only the necessary subset of words, reducing processing time while maintaining adequate coverage for accurate recognition.
3Productivity
If only positional information from GPS is used to select dictionary, then character recognition speed is increased to some extent, but words likely to be contained in the scene image cannot be fully efficiently extracted
Solution Approach 1:
The patent merges multiple information sources - GPS position data, map database information, and camera direction data - to determine the shooting object range and select words. This combination of positional and directional information resolves the contradiction by efficiently extracting the most relevant words without requiring processing of the entire database, achieving both speed and accuracy.
4Measurement precision
If the mobile terminal device stores and processes all position corresponding information locally, then recognition accuracy is maintained, but device complexity and memory requirements increase
Solution Approach 1:
The patent extracts only the necessary position corresponding information from the database based on the determined shooting object range, rather than storing all possible information locally. The mobile terminal stores minimal data (GPS position) and retrieves only needed words when required, reducing device complexity and memory requirements while maintaining recognition accuracy through on-demand extraction.
Data Source
AI summary
Words possibly included in a scene image shot by a mobile camera can be efficiently extracted using a word dictionary or a map database. Positional information acquiring means 101 measures a current position of the device to acquire positional information. Directional information acquiring means 102 detects a direction of the device to acquire directional information. Character recognizing means 104 determines a range of shooting of a scene image based on the current positional information and the directional information. The character recognizing means 104 extracts from a map database 103 information such as store names, building names, and place names associated with positions in the shooting range. Then the character recognizing means 104 conducts character recognition using word knowledge such as the extracted store names, building names, and place names.