• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.07a
• /
• pp.447-448
• /
• 2022

본 논문에서는 대중의 참여를 통해 캔 음료 제품의 점자 표기 실태를 파악하고, 음료 제조사가 이를 개선하도록 유도하는 방안을 제안한다. 캔 음료 상단에 표기된 점자를 촬영한 이미지에서 OpenCV를 통해 점자의 윤곽을 검출하고, 검출된 윤곽의 좌표를 계산하여 점자를 국문으로 번역하는 모듈을 개발한 후 서버에 이식한다. 서버와 통신하는 모바일 애플리케이션을 개발하여 소비자가 점자 이미지를 서버에 업로드하고, 점자의 인식결과를 확인할 수 있도록 한다. 점자 표기가 적절하지 않다고 판단하는 경우 해당 제품에 대한 정보를 기록하도록 하고, 제조사 별로 제보된 횟수의 순위를 제공한다. 이를 통해 소비자는 올바른 점자 표기를 제공하지 않는 제조사를 파악할 수 있으며, 제조사는 이를 의식하고 점자 표기를 개선할 수 있는 효과를 기대한다.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.12 no.4
• /
• pp.691-700
• /
• 2017

This paper describes the design and implementation of automatic braille converter based on image processing for a person who is visually impaired. The conversion algorithm based on the image processing converts the input image obtained by the web-cam to binary image, and then calculates the cross-correlation with the stored character pattern image by labeling the character area and converts the character pattern image into the corresponding braille. The computer simulations showed that the proposed algorithm showed 95% and 91% conversion success rates for numerals and alphabets printed on A5 paper. The prototype test implemented by the servo motor using Arduino confirmed 89%, conversion performance. Therefore, we confirmed the feasibility of the automatic braille transducer.

• Journal of the Institute of Convergence Signal Processing
• /
• v.23 no.3
• /
• pp.166-172
• /
• 2022

In this study, we photograph driving obstacle objects such as crosswalks, side spheres, manholes, braille blocks, partial ramps, temporary safety barriers, stairs, and inclined curb that hinder or cause inconvenience to the movement of the vulnerable using electric mobility aids. We develop an optimal AI model that classifies photographed objects and automatically recognizes them, and implement an algorithm that can efficiently determine obstacles in front of electric mobility aids. In order to enable object detection to be AI learning with high probability, the labeling form is labeled as a polygon form when building a dataset. It was developed using a Mask R-CNN model in Detectron2 framework that can detect objects labeled in the form of polygons. Image acquisition was conducted by dividing it into two groups: the general public and the transportation weak, and image information obtained in two areas of the test bed was secured. As for the parameter setting of the Mask R-CNN learning result, it was confirmed that the model learned with IMAGES_PER_BATCH: 2, BASE_LEARNING_RATE 0.001, MAX_ITERATION: 10,000 showed the highest performance at 68.532, so that the user can quickly and accurately recognize driving risks and obstacles.

• Journal of the Institute of Convergence Signal Processing
• /
• v.24 no.2
• /
• pp.119-125
• /
• 2023

In this study, we photograph driving obstacle objects such as crosswalks, side spheres, manholes, braille blocks, partial ramps, temporary safety barriers, stairs, and inclined curb that hinder or cause inconvenience to the movement of the vulnerable using electric mobility aids. We develop an optimal AI model that classifies photographed objects and automatically recognizes them, and implement an algorithm that can efficiently determine obstacles in front of electric mobility aids. In order to enable object detection to be AI learning with high probability, the labeling form is labeled as a polygon form when building a dataset. It was developed using a Mask R-CNN model in Detectron2 framework that can detect objects labeled in the form of polygons. Image acquisition was conducted by dividing it into two groups: the general public and the transportation weak, and image information obtained in two areas of the test bed was secured. As for the parameter setting of the Mask R-CNN learning result, it was confirmed that the model learned with IMAGES_PER_BATCH: 2, BASE_LEARNING_RATE 0.001, MAX_ITERATION: 10,000 showed the highest performance at 68.532, so that the user can quickly and accurately recognize driving risks and obstacles.