20240020998. CHARACTER RECOGNITION METHOD FOR DYNAMIC IMAGES simplified abstract (Quanta Computer Inc.)
Contents
CHARACTER RECOGNITION METHOD FOR DYNAMIC IMAGES
Organization Name
Inventor(s)
Chen-Chung Lee of Taoyuan City (TW)
Chia-Hung Lin of Taoyuan City (TW)
Chun-Hung Chen of Taoyuan City (TW)
Chien-Kuo Hung of Taoyuan City (TW)
Wen-Kuang Chen of Taoyuan City (TW)
En-Chi Lee of Taoyuan City (TW)
CHARACTER RECOGNITION METHOD FOR DYNAMIC IMAGES - A simplified explanation of the abstract
This abstract first appeared for US patent application 20240020998 titled 'CHARACTER RECOGNITION METHOD FOR DYNAMIC IMAGES
Simplified Explanation
The abstract of the patent application describes a method for character recognition in a series of consecutive images. The method involves detecting a target object in each image and defining its object information based on the area ratio it occupies in the image. The method then determines whether the target object in the current image is the same as the target object in the previous image using the object information. Character recognition is performed on the target object to obtain a recognition result, and a weighting score is calculated based on the object information and the recognition result. The weighting score of the recognition result in the consecutive images is accumulated until it exceeds a preset value, and the final recognition result is output.
- The method detects a target object in a series of consecutive images.
- Object information of the target object is defined based on its area ratio in the image.
- The method determines if the target object in the current image is the same as in the previous image using the object information.
- Character recognition is performed on the target object to obtain a recognition result.
- A weighting score is calculated based on the object information and the recognition result.
- The weighting score of the recognition result in the consecutive images is accumulated until it surpasses a preset value.
- The final recognition result is output.
Potential applications of this technology:
- Optical character recognition (OCR) systems for text recognition in images.
- Object recognition in computer vision applications.
- Handwriting recognition in digital devices.
Problems solved by this technology:
- Efficient and accurate character recognition in a series of consecutive images.
- Handling variations in object appearance and position across consecutive images.
- Reducing false positives and negatives in character recognition.
Benefits of this technology:
- Improved accuracy and reliability in character recognition.
- Automation of character recognition tasks in various applications.
- Time and cost savings in data entry and analysis processes.
Original Abstract Submitted
a character recognition method includes the stages as detailed in the following paragraph. an image is received, wherein the image is one in a plurality of consecutive images. a target object in the image is detected. object information of the target object is defined according to the area ratio of the target object occupied in the image. whether the target object in the image is the same as the target object in the previous image is determined according to the object information. character recognition on the target object is performed to obtain a recognition result. the weighting score of the recognition result is calculated according to the object information and the recognition result. the weighting score of the recognition result of the target object in the consecutive images is accumulated until the weighting score is higher than a preset value, and the recognition result is output.
