Electronic Device Character Recognition Data Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Server-based optical character recognition (OCR) technology faces slow processing speeds due to the need for electronic devices to transmit large amounts of data to servers, leading to prolonged character recognition times.
Innovation Solution
An electronic device with an imaging device, communication circuit, and processor that transmits only partial image and text data to a server, allowing for efficient data transmission and processing by distinguishing between overlapping and non-overlapping image regions, thereby reducing the amount of data sent.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If all image data is transmitted to the server for OCR processing, then recognition accuracy is improved, but transmission time and processing time are increased
Solution Approach 1:
The patent divides the image data into multiple blocks and transmits them sequentially to the server only when necessary. Instead of transmitting the entire image at once, the system segments the image into manageable blocks (e.g., 8x8 pixel blocks) and processes them in stages, allowing the OCR operation to continue with partial data while reducing overall transmission time.
Solution Approach 2:
The patent performs preliminary analysis of the image to identify text regions and prioritizes transmission of blocks containing text information. The system pre-processes the image to detect potential text areas and schedules transmission of these critical blocks first, ensuring that the most important data reaches the server before other non-critical image blocks.
2Loss of time
If image data is transmitted in blocks, then transmission time is reduced, but implementation complexity is increased
Solution Approach 1:
The patent implements a universal block processing framework that handles both text-containing blocks and non-text blocks through the same transmission and processing pipeline. The server receives blocks in sequence and applies the same OCR processing logic to each block, regardless of whether it contains text or not, simplifying the overall system architecture while maintaining efficiency.
Solution Approach 2:
The system implements a feedback mechanism where the server analyzes received image blocks and provides information about whether text has been detected. This feedback allows the client device to determine whether to continue transmitting remaining blocks or stop transmission early if sufficient text has been recognized, optimizing the balance between completeness and efficiency.
Data Source
AI summary
An electronic device according to an embodiment disclosed in the present document may comprise: an imaging device for generating image data; a communication circuit; at least one processor operatively connected to the imaging device and the communication circuit; and a memory operatively connected to the processor, for storing a command.