Press Release
Korea Deep Learning wins the Korea Economic Daily President's Award at the Korea Impactech Awards for cutting unsorted parcels
Korea Deep LearningPublished

In April 2022, Korea Deep Learning won the Korea Economic Daily President's Award at the 2022 Korea Impactech Awards. The winning technology is a deep learning-based dual recognition system for shipping information built on DEEP OCR. It reduces unsorted items by recognizing again the parcels whose barcodes could not be read during sorting. With the system, Korea Deep Learning was recognized for its technical innovation and strong business potential.
The Korea Impactech Awards are information and communications technology (ICT) awards hosted and jointly organized by the Ministry of Science and ICT, The Korea Economic Daily and the Korea Association for ICT Promotion (KAIT).
From 20,000 to 400,000 a day: dual recognition that cuts unsorted parcels
In parcel sorting, waybill barcodes sometimes fail to read. Parcels whose barcodes cannot be recognized drop out of the automated sorting line as unsorted items, and people have to check each one again by hand. According to Korea Deep Learning, these unsorted items average at least 20,000 a day and reach as many as 400,000.
When a barcode is misread, Korea Deep Learning's dual recognition system for shipping information immediately rereads the address on the waybill, reducing unsorted items. It uses deep learning OCR technology based on the YOLO algorithm from the convolutional neural network (CNN) family, and applies DEEP OCR, proven at large enterprises and public institutions.
In 2019, its first year, Korea Deep Learning built a deep learning waybill recognition system for Korea Post. The dual recognition system grew out of the experience in logistics character recognition the company has built since then.
"Our dual recognition system for shipping information will minimize the needless loss of labor caused by unsorted items and help solve the problem of overwork among delivery drivers, and ultimately we plan to enter the logistics market both in Korea and around the world."
— Kim Ji-hyun, CEO, Korea Deep Learning
From the award to the AI Voucher program, a growing logistics business
The award became the starting point for expanding the company's logistics and data business. Korea Deep Learning was selected, together with Sunghwa Corporate Express, for the National IT Industry Promotion Agency's 2022 AI Voucher Support Program, and will develop an ultra-fast deep learning waybill recognition system to digitize handwritten waybills. Sunghwa Corporate Express, which has a logistics network of about 70 sites nationwide, holds more than 100,000 waybill records. The goal is to turn delivery information into data and recognize handwritten waybills to automate logistics sorting.
Korea Deep Learning said it will work to solve the parcel industry's sorting issues through this consortium, which brings together the lead organization's data and its own OCR solution, DEEP OCR.
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.







