Online Document Identification and Verification Using Machine Learning Model

In companies or any organizations, the data is collected in various formats along with government-approved identity documents such as Aadhaar, PAN, license, etc. in soft or hard copy format. They contain valuable information but are stored in an unstructured manner once received. The data on the document needs to be extracted and classified and identity documents need to be verified. Nowadays, many document classifier software products are available in the market for extracting text information and classifying documents. However, these products are used in offline mode, once the documents are collected at the receiver end. This paper proposes a novel method for classifying and verifying identity documents in run time while uploading the document online mode itself. For this, support vector machine (SVM) algorithm and optical character recognition (OCR) are used. For invalid documents, the comment is displayed on the screen to upload the correct document, before submitting data.