<\/p>\n
For effective use of documents it is important not only to scan, but also to be able to search for them. We know two options for solving this problem \u2014 documents can be recognized or indexed.<\/p>\n
Recognition of documents is used for primary sources of good quality \u2014 \u201cfresh\u201d book, a magazine, a dictionary, a questionnaire. Without the presence of \u201cartifacts\u201d (garbage, comments, entries in the fields, etc.). For this we use a document recognition system or an OCR- system. This system automatically enters the data into the computer (for example, in a text editor). And after the document is recognized, you can:<\/span><\/p>\n With regard to archival documents<\/a> \u2014 the process of establishing recognition takes longer, and the accuracy is a small percentage. In this case, various methods of semi-automatic conversion of documents into electronic form using keywords (indexing) are used.<\/p>\n Document indexing \u2014 is the process of assigning identification features to scanned documents<\/a>, allowing you to quickly find the necessary information in the database. Such signs can be: type of document, document number, document date, author of the document, etc.<\/p>\n At the stage of recognition or indexing, we work with the most complex data:<\/p>\n When performing full or partial recognition of documents, we use a multi-level quality check of the array. The creation of a resource<\/a> also helps us to avoid possible mistakes, where the whole technology is tested on a small amount of information, the fields are consistent, and the quality criteria are determined.<\/p>\n <\/p>\n <\/p>\n \n\n
Indexing of documents<\/b><\/h3>\n
Our advantages<\/h3>\n
\n
\nPrices for recognition and indexing are determined individually.<\/span><\/div>\n<\/ul>\n<\/div>\n