SBIR/STTR Research Award
Optical Character Recognition (OCR) Automated Document Pre-processing Software
Award amount
$999,923Program and phase
SBIR · Phase IIAward year
2019Award details
- Awarding agency
- Department of Defense
- Branch
- Army
- Recipient company
- NOKOMIS INC
- Proposal award date
- 2019-02-04
- Contract end date
- 2021-12-15
- UEI
- YAPUZLNJ1856
- Solicitation number
- 17.3
- Topic code
- A17-142
Research abstract
Optical Character Recognition (OCR) is confounded by noise and damage in real world documents. Preprocessing documents to remove noise will improve the performance of current OCR software. Nokomis has demonstrated technology that improves Word Error Rate (WER) by performing image denoising and preprocessing prior to OCR. Nokomis will mature this technology and integrate it with the Army’s Machine Foreign Language Translation System (MFLTS). Nokomis will implement a module to automatically classify the level and type of degradation, then apply the optimal pre-processing operations for the given type and level of degradation, improving WER. Nokomis will characterize the performance of the HANDI framework and quantify the improvement in WER as realized in the MFLTS. A test and evaluation of the performance of the HANDI system within the MFLTS will be performed. Based on test and evaluation, Nokomis will improve and customize the system to satisfy the needs of the Army.
Technology keywords
Not reported
Other awards by this recipient
Verified by the same UEI. These are other public SBIR/STTR award pages, not a merged company record.
- “Left of Launch” Indications and Warning for Enhanced Battle Management
- Noise Masked Communication System (NMCS)
- Nokomis Expeditionary Space Domain Awareness (NExSDA) System
- Passive RF-Based Target Detection, Identification, and Geolocation for RF Seekers
- Hiawatha Passive RF Threat Detection and Identification System
Awards with the same topic code
Verified by an exact topic code match. This is not a text-similarity match.
- Hybrid Adaptive Noise Detection and Isolation (HANDI) Algorithm for Automatic Denoising
- Automated Document Pre-Processing Technologies for Optical Character Recognition (OCR)
Research funding history
123 SBIR/STTR records share this UEI (2005–2025). Reported award amounts total $66,765,345. Reported amounts are not federal obligations.
Phases: Phase I, Phase II, Phase II – Direct to Phase II
Agencies: Department of Defense, National Aeronautics and Space Administration, Department of Energy, Department of Health and Human Services, National Science Foundation, Department of Homeland Security