• Anish E T
• Balamanikandan V
• Dr.M. Sujithtra

BFSI areas manage bunches of unstructured filtered records which are chronicled in report the executives’ frameworks for additional utilization. For instance, in Insurance area, when a strategy goes for endorsing, guarantors joined a few crude notes with the arrangement, Insureds likewise connect different sort of examined archives like character card, bank proclamation, letters and so on In later pieces of the strategy life cycle assuming cases are made on an approach, related checked reports likewise documented. Presently it turns into a monotonous task to distinguish a specific record from this huge archive. The objective of this contextual investigation is to foster a deep learningbased arrangement which can consequently order filtered archives.

Convolution Neural networks (CNN)-Science operations and test area (SOTA)- VGG16- InceptionResNetV2-Approach-Deep Learning - Ryerson Vision Lab Complex Document Information Processing (RVL-CDIP)

"SCANNED DOCUMENT CLASSIFICATION", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.9, Issue 2, page no.d699-d701, February-2022, Available :http://www.jetir.org/papers/JETIR2202388.pdf

"SCANNED DOCUMENT CLASSIFICATION", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.9, Issue 2, page no. ppd699-d701, February-2022, Available at : http://www.jetir.org/papers/JETIR2202388.pdf