Mobile Video Analysis for Automatic Document Capture
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing mobile electronic device applications require manual capture of multiple still photos for multifaceted printed artifacts, such as multi-page documents, which is cumbersome and prone to distortions due to motion and inadequate lighting, and result in large file sizes.
Innovation Solution
A mobile device system that captures video of a printed artifact, analyzes image frames in real-time to identify suitable instances for high-resolution still image capture, using subsampling and sensor data to reduce computational load and improve image quality, and automatically switches between video and photo capture modes to create a single digital file.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If manual photo capture is used for each page of a document, then image quality can be controlled, but the process is cumbersome and time-consuming
Solution Approach 1:
The system automatically captures images by analyzing video frames and triggering photo capture mode when suitable images are detected, eliminating the need for manual user intervention to capture each page individually
Solution Approach 2:
The system first captures video of the document at low resolution for rapid analysis, then uses this preliminary information to trigger high-resolution still image capture only when the video analysis indicates a suitable frame, streamlining the capture process
2Measurement precision
If high-resolution still images are captured continuously, then image quality is maintained, but storage space is consumed and processing time increases
Solution Approach 1:
The system applies different capture resolutions to different situations: low-resolution video capture for general viewing and analysis, and high-resolution still image capture only when the video analysis identifies suitable frames, optimizing both quality and storage efficiency
Solution Approach 2:
The system captures more video frames than would be processed individually, analyzing multiple frames to identify suitable capture moments, which ensures high-quality images are captured only when necessary while reducing overall storage requirements
3Extent of automation
If video analysis is performed in real-time, then suitable images can be automatically identified, but computational load increases
Solution Approach 1:
The system segments the image analysis task by first processing video frames at reduced resolution to identify potential suitable frames, then only analyzing those selected frames in full detail for final capture decision, reducing overall computational complexity while maintaining automation
4Ease of operation
If manual capture is used, then capture control is maintained, but distortion from motion and camera shake occurs
Solution Approach 1:
The system replaces manual mechanical capture control with automated electronic detection and triggering, using video analysis algorithms to detect suitable capture moments and automatically switch to photo capture mode, eliminating human reaction time and maintaining consistent capture conditions
Data Source
AI summary
A system creates an electronic file corresponding to a printed artifact by launching a video capture module that causes a mobile electronic device to capture a video of a scene that includes the printed artifact. The system analyzes image frames in the video in real time as the video is captured to identify a suitable instance. In one example, the suitable instance is a frame or sequence of frames that contain an image of a page or side of the printed artifact and that do not exhibit a page-turn event. In response to identification of the suitable instance, the system will automatically cause a photo capture module of the device to capture a still image of the printed artifact. The still image has a resolution that is higher than that of the image frames in the video. The system will save the captured still images to a computer-readable file.