시각장애인을 위한 딥러닝 기반 음료수 캔 인식 시스템
A Beverage Can Recognition System Based on Deep Learning for the Visually Impaired
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Recently, deep learning has been used in the development of various institutional devices and services to help the visually impaired people in their daily lives. This is because not only are there few products and facility guides written in braille, but less than 10% of the visually impaired can use braille. In this paper, we propose a system that recognizes beverage cans in real time and outputs the beverage can name with sound for the convenience of the visually impaired. Five commercially available beverage cans were selected, and a CNN model and a YOLO model were designed to recognize the beverage cans. After augmenting the image data, model training was performed. The accuracy of the proposed CNN model and YOLO model is 91.2% and 90.8%, respectively. For practical verification, a system was built by attaching a camera and speaker to a Raspberry Pi. In the system, the YOLO model was applied. It was confirmed that beverage cans were recognized and output as sound in real time in various environments.
Abstract
Recently, deep learning has been used in the development of various institutional devices and services to help the visually impaired people in their daily lives. This is because not only are there few products and facility guides written in braille, but less than 10% of the visually impaired can use braille. In this paper, we propose a system that recognizes beverage cans in real time and outputs the beverage can name with sound for the convenience of the visually impaired. Five commercially available beverage cans were selected, and a CNN model and a YOLO model were designed to recognize the beverage cans. After augmenting the image data, model training was performed. The accuracy of the proposed CNN model and YOLO model is 91.2% and 90.8%, respectively. For practical verification, a system was built by attaching a camera and speaker to a Raspberry Pi. In the system, the YOLO model was applied. It was confirmed that beverage cans were recognized and output as sound in real time in various environments.
참고문헌 (19)
- "시각장애인 편의시설 실태조사 후속조치" (2022), 보건복지부[URL]
- "유통기한 확인 못하는 시각장애인, 식품 점자 표시 실태조사" (2022)[URL]
- "시각장애인 두 번 울리는 점자 표기" (2022), 조선비즈[URL]
- "시각장애인에겐 요만큼만...점자 정보 인색한 사회" (2019), 한국일보[URL]
- 시각장애인 식품 점자 표기 소비자문제실태조사, "박정태", 한국소비자원, ~ (2022)
- "착한 식품 기업, 시각장애인 위한 점자 패키지 선봬" (2022), 뉴시스[URL]
- "시각장애인 10명 중 9명은 점자 문맹" (2022), 일간경기[URL]
- 박영웅, "딥러닝 기반의 실시간 영상 처리 기술을 활용한 시각장애인 대상 상품 음성안내 서비스", 한국통신학회, 학술대회논문집, pp.126~127 (2021)
- 윤다연, "CNN 기반 실시간 영상처리를 통한시각장애인 스마트 보조기구", 한국정보기술학회, 종합학술발표논문집, pp.665~669 (2021)
- 양호준, "시각장애인을 위한 딥러닝 기반의 실시간 임베디드 보조 시스템 개발에 관한 연구", 재활복지공학회논문지, 16(1), pp.27~36 (2022), 한국재활복지공학회
- 오세랑, "YOLO V3 기반의 시각장애인을 위한 유도 블록 인식 알고리즘", 한국지능시스템학회 논문지, 31(1), pp.60~67 (2021), 한국지능시스템학회[DOI]
- 이동구, "이미지 인식률 개선을 위한 CNN 기반 이미지 회전 보정 알고리즘", 한국인터넷방송통신학회 논문지, 20(1), pp.225~229 (2020), 한국인터넷방송통신학회[DOI]
- 배선영, "시각장애인을 위한 인공지능 관련 연구 동향 : 1993-2020년 국내·외 연구를 중심으로", 한국콘텐츠학회 논문지, 20(10), pp.688~701 (2020), 한국콘텐츠학회[DOI]
- 이용환, "객체 검출을 위한 CNN과 YOLO 성능 비교 실험", 반도체디스플레이기술학회지, 19(1), pp.85~92 (2020), 한국반도체디스플레이기술학회
- 김익수, "결함검출 적용을 위한 YOLO 딥러닝 알고리즘 비교", 한국생산제조학회지, 30(6), pp.514~519 (2021), 한국생산제조학회[DOI]
- 백석영, "YOLO를 활용한 실시간 교통표지 검출", 한국자동차공학회 춘계학술대회, pp.833~837 (2019)
- 이정환, "YOLOv4 알고리즘을 이용한 저품질 자동차 번호판 영상의 숫자 및 문자영역 검출", (사)디지털산업정보학회 논문지, 18(4), pp.1~11 (2022), (사)디지털산업정보학회
- 김진호, "노상 주차 차량 탐지를 위한 YOLOv4 그리드 셀 조정 알고리즘", (사)디지털산업정보학회 논문지, 18(4), pp.31~40 (2022), (사)디지털산업정보학회
- "Francesco, What is YOLOv8?" (2023)[URL]