Document Input

The SDK allows our customers to simplify integration so they can use Omnitive Extract in their native (iOS, Android) built mobile applications.

Support for connection to a Kodak-Alaris scanner model that operates as a source for document input. This allows better control of the quality of the documents being processed and automates the processing, simplifying it with just one click on the scanner.

Enhanced Image Recognition

De-skewer & de-noiser function detects noise and skews in documents which improves accuracy and makes results easier to interpret.

Text cleanser corrects and learns words, phrases and characters from OCR errors caused by the poor quality of images.

Semantic Expansion of Knowledge Bases

The flexibility to connect with external sources of information (eg. from a CRM or search engine) to consolidate and validate information extracted and / or validate it while simultaneously enhancing the knowledge base through processing the documents.

Data normalisation allows data or concepts to be transformed from the documents to the format compatible with the destination database.

Intelligent Contextual Extraction

Train the extraction model to determine the position of simple fields of a structured or a semi-structured document, which are always in the same format.

Identifies the key value pairs, allowing the extraction process to be independent of the datapoint position on the document. As long as the key value pair appears in the same configuration (on the right or below) the trained document, the information will be extracted.

Interprets and understands the text and context in semi-structured or unstructured documents through the use of natural and semantic language processing, ascertaining the value of the data required for extraction.

Document classification automatically determines the type of a document at runtime without the need for a user to pre-classify it.

Encompasses a representation, formal naming, and definition of the categories, properties, and relations between the concepts, data, and entities. The creation of the ontology makes data extraction becomes faster and more efficient, as long as adequate knowledge is available to perform the task.


Your browser is unable to display our site correctly.
It is best viewed on a modern browser, such as Chrome, Safari or Firefox.