Earticle

본 논문에서는 농인들의 일상 소통을 개선하고 비장애인들의 수화 교육을 위해 AI를 활용하여 수화 통역 과 교육을 할 수 있는 수화 번역 프로그램을 개발한다. 기존의 수화 언어는 한국어와 동등한 언어로 인정되었지 만, 수화 통역 및 교육은 여전히 부족한 상황이다. 농인들은 일상 소통에서 언어적인 격차와 문화적인 어려움을 경험하며, 특히 일반 학교에서 수업을 받는 농인들은 어려움을 겪고 있다. 수화 번역 프로그램은 미디어파이프, OpenCV와 같은 AI 기술을 활용하여 손 동작을 인식하여 수화로 번역한다. 손 동작은 KNN을 사용하여 분석되 어 수화를 인식하고 수화 교육 플랫폼 및 의사소통 도구로 활용된다. 이 연구는 농인들의 일상생활의 불편함을 최소화하고 의사소통과 사회적 참여를 촉진하며, 수화 교육의 접근성을 높이는 데 기여할 것으로 기대된다.

In this paper, we develop a sign language translation program that can use AI for sign language interpretation and education to improve daily communication among farmers and to educate non-disabled people about sign language. Although the existing sign language has been recognized as an equivalent language to Korean, sign language interpretation and education is still lacking. Farmers experience linguistic gaps and cultural challenges in their daily communication, especially those who are educated in mainstream schools. The sign language translation program utilizes AI technologies such as MediaPipe and OpenCV to recognize hand gestures and translate them into sign language. The hand gestures are analyzed using KNN to recognize sign language and used as a sign language education platform and communication tool. This research is expected to contribute to minimizing the inconvenience of farmers' daily life, facilitating communication and social participation, and increasing the accessibility of sign language education. Translated with DeepL.com (free version)

There have been exciting advancements in the fields of computer vision with the development of data analysis techniques and computational efficiency. In this project, we have built a user-friendly image processing tools using the tkinter libraries in Python by defining functions for each computer vision method and implementing pre-processing, filtering, feature extraction, and clustering on images collected from various fields such as environmental sciences, medical sciences, and mobilities. We have sought to assess the utility of automated image processing software to improve image classifiers even by nonprofessionals with no coding and no machine learning expertise. Thus, this program can be easily utilized by researchers without programming experience. This program can be used for various purposes by scholars in various fields such as education, environmental sciences and medicine.