Back to the newsroom

Press Release

Korea Deep Learning wins the IF 2020 Demo Day grand prize with Jamsimanyo, its unattended entry system

Korea Deep LearningPublished

Korea Deep Learning wins the IF 2020 Demo Day grand prize with Jamsimanyo, its unattended entry system
In October 2020, Korea Deep Learning received the Financial Services Commission Chairman's Award, the grand prize of the IF 2020 YES Demo Day, for its unattended entry system Jamsimanyo.

On October 30, 2020, Korea Deep Learning received the Financial Services Commission Chairman's Award, the grand prize, at the YES (Young Entrepreneur Startups) Demo Day of IF (Imagine Future) 2020, a startup festival held at COEX in Seoul. The winning entry was Jamsimanyo, an AI-powered unattended entry system that recognizes ID cards to keep minors out of unattended stores.

The problem of minors entering unattended stores

Jamsimanyo grew out of a problem on the ground that came with the rise of unattended stores. As more stores such as unattended coin karaoke rooms, unattended PC cafés and unattended motels opened, teenagers entering after 10 p.m. became an issue. If a minor is caught on the premises, the owner can face fines and a business suspension, but in a store with no staff it is hard to check the age of everyone who comes in.

A door that opens and closes with an ID card

Installed at a store's entrance, Jamsimanyo recognizes the ID card of the person entering and restricts unattended entry by minors. It also detects whether an ID card has been forged, altered or stolen. With a built-in electronic visitor log, it can also handle visitor management for COVID-19 prevention in one step. Korea Deep Learning's deep learning-based character recognition technology, DEEP OCR, was used for ID card verification.

It caught investors' attention because it directly solves a problem small business owners face on the ground, and because it was already generating revenue.

A grand prize won against odds of 17 to 1 among 170 teams

YES Demo Day is a stage where university students who dream of starting a business share their ideas with experts and develop them into businesses. In 2020, 170 teams applied, 10 teams from nine universities made the finals after beating odds of 17 to 1, and Korea Deep Learning took the grand prize.

Korea Deep Learning is a student startup founded in May 2019 by CEO Kim Ji-hyun, who was double majoring in ceramics and software at Kyung Hee University. In its first year, in October 2019, it supplied an ID card recognition OCR system to EDMS, and in July 2020 it filed a patent for AI identity verification technology. A company that had been building up its ID card reading technology in the field won an award with that technology. What makes the award meaningful is that a company that started as a student venture took the grand prize with a product used in real stores.

About DEEP OCR

Korea Deep Learning started out by reading documents. Built on KDL's own document-specialized VLM, DEEP OCR is Korea's first VLM-based OCR solution, reading not just the characters but the structure and meaning of a document together. It handles unstructured documents in every kind of layout without building separate training data, and extracts text and key-value data from visual elements such as seals, signatures, tables, numbers and symbols. From loan documents in finance to administrative documents in the public sector and handwritten waybills in logistics, documents people used to copy out by hand become business data through DEEP OCR. More information is available on the DEEP OCR page at koreadeep.com.

About Korea Deep Learning

Korea Deep Learning (KDL), founded in 2019, is an enterprise AI agent company. Built on KDL Frontier, its own vision-language model (VLM) specialized for documents, KDL makes AI agents that take on and complete the document work of businesses and public institutions. Its main products are DEEP OCR, DEEP Parser, DEEP Agent and DEEP Ops.

Source