Project

Discovery and Classification of Images and Video content

Objective

A program that can discover images and video files in a given data storage device/filesystem and help classify the discovered content in various classification categories- PII, Sensitive, Confidential etc. Possibly use ML to improve the accuracy of classification.

Outcome

Scope Input i) S3 Compatible Storage ii) Local filesystem iii) additional cloud providers Service classification List assets Add data to assets from given Input source classification service use text extractor(tool to finalize-Tesseract OCR?) + use classification tool for classification(tool to finalize-Presidio?) classification reports Show results from classification service UC Input data source Start/stop classification Show reports classification runs classification results extended classification source adapters Pull reports from api available from cloud provider and add it to classification reports schema