Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{206847,
        author = {Sanjay Nagappa Gouda and Shriram Harishchandra Gouda and Sudeep Anil Naik and Nikhil Subhas Shetty},
        title = {Snapscan-A Smart Document Scanner App: An Automated Document Processing and Evaluation System},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {no},
        pages = {676-685},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=206847},
        abstract = {The shift toward digital education and automated administrative processes has created a noticeable gap in existing technological systems. Current tools mainly focus on converting physical documents into digital formats, but they lack the ability to properly interpret, evaluate, and manage the actual content inside them. This paper presents “Snapscan,” a browser-based system designed to handle document scanning, text extraction, and academic evaluation in a more practical way within the client-side environment. The system integrates Optical Character Recognition (OCR) using WebAssembly along with basic Natural Language Processing (NLP) techniques to reduce manual effort involved in grading. Unlike traditional Optical Mark Recognition (OMR) systems that depend only on fixed inputs, Snapscan supports evaluation of descriptive answers by comparing them with predefined schemes. It calculates scores using multiple factors such as keyword presence, similarity of meaning, and overall answer structure including clarity and completeness. In addition, the system includes features like translation and summarization, which are handled locally to reduce dependency on cloud services. Testing was carried out on different types of academic data, and the results indicate that the system improves consistency in grading while reducing processing time significantly. The performance remains close to human evaluation with noticeable efficiency improvements. Evaluated through extensive simulated academic and administrative scenarios spanning multiple disciplines, the proposed system demonstrates a highly scalable, privacy-centric approach to reducing educator workload, improving grading consistency, and centralizing document workflows within a seamless web-based environment. The experimental results show that Snapscan achieves a grading consistency rating within 5-7% of human educators, while reducing processing time by over 80%.},
        keywords = {.},
        month = {July},
        }