Passport Information Extractor
Extract information from passport using Pixuate's OCR
IntroductionBusinesses have a need to automate the orders that are received in various structured formats such as passport images. Scanned passports are received in the form of emails, fax, PDF and are being manually processed by the backend team. Pixuate is offering a Passport Information Extractor which uses machine learning to process structured formats (emails/fax/ pdf, HTML, excel etc.,) into formats (XML, CSV, XLS, JSON) which can be directly read by existing ERP systems. No matter the nationalities —Pixuate® processes and delivers critical data accurately and on time. With our solutions, one can make passport processing completely paperless and people independent. Businesses can process passports received in any format and structure using Pixuate® solution.
FeaturesPixuate® Document Processing Solution has the following features:
- Supports multiple formats – JPEG, Excel, PDF
- Reads from non-standardized formats
- Supports multiple languages
- Integrates easily with existing ERPs
Structured Form Document ProcessingAs the name suggests, these types of documents such as passports have a consistent structure, with every data field located in the same place. Consequently, structured forms are the easiest to process with Optical Character Recognition (OCR) engines, and generate excellent accuracy rates for data capture. Although structured forms are ideal for accurate and efficient high-volume document processing, it is estimated some 80 percent of organizations use semi-structured or unstructured forms. Pixuate® can assist organizations in the design of standardized, structured paper and web-based forms to improve the accuracy and efficiency of data capture—a business process improvement that delivers significant cost savings.
- Fast, automated data capture
- Lower processing costs
- Very high data-capture accuracy
How it works?The working procedure can be summarized as follows:
- Clients from across the world send passport images via email or fax.
- For those passports which are received in standard formats, the API processes it directly and saves the result in a .csv file.
- Only 4 different formats are allowed namely .pdf, .jpg, .txt and .xls
- Pixuate performs OCR on the passport images and the users can ‘Verify Results’ and correct manually if any change is necessary. The users can edit or even delete the images in the ‘Order Status’ section. The rest are added to the queue for further processing.
- The ‘Buckets’ section contains the list of documents, format, size and the corresponding name value pairs.
- The final report can be downloaded in a .csv file.
Advantages of Pixuate Passport Information Extractor
- Ability to process structured documents
- Multiple formats such as .jpg, .pdf, .txt, .xls .
- Keeps good track of customer and seller details
- Options to edit the results and make necessary changes
- Very high accuracy