I&T Solution |
Intelligent Document Analytics for e-Tender Report System
(REF: S-1572) |
Trial Project |
|
Solution Feature |
- Employ state of art geometric unwarping transformer, illumination correction transformer NLP model to correct the geometric distortion.
- Use illumination correction transformer further removes shading artifacts to improve visual quality and OCR accuracy to achieve 20.02% CER, 15% absolute improvement.
- Pre-trained Deep Learning-based for wide range of document image analysis including classification, layout detection, table detection, and scene text detection.
- Provide a generalized framework and off-the-shelf toolkit for deep learning for layout detection, character recognition, and other digital imaging analysis tasks.
- Provide Comprehensive tools for efficient document image data annotation and model tuning to support different levels of customization.
|
Trial Application and Expected Outcome |
- Test our AI document processing system can extract text correctly to prove the system’s capability to parse geometric distorted documents.
- Test our AI document processing system can extract the text correctly to prove the system’s capability to parse documents at bad Illumination conditions.
- Test our AI document processing system can extract the information in different rows and columns correctly to prove the system’s capability to parse tables in documents.
- Test the system with documents that have various tables and validate the ease of configuring and customizing the system t handle special layout.
- Feed in documents with test documents and generate out in different output formats such as CSV, Json to allow easy integration for downstream systems.
|
Additional Solution Information |
Intelligent Document Analytics for e-Tender Report System Proposal by Beyond Limits - 20231005.pdf
|
Info on I&T Solution Provider |
Solution Provider | : | BEYOND LIMITS HONG KONG LIMITED | Address | : | Unit 336, 19W, | Contact Person | : | Hilda Li |
Position | : | Technical Sales Director | Tel | : | 93160397 | Email | : |
hli@beyond.ai | Webpage | : | beyond.ai |
|