Visually impaired people have various difficulties in their daily lives. Eating is a daily activity that is deeply involved in health management and a feeling of happiness, so it is required to realize an efficient and comfortable meal by some kind of technical support. Therefore, this study proposes a novel system to support visually impaired people to eat alone with chopsticks. The proposed system consists of the image analysis to recognize the type of food and the position of the chopstick tips and a tactile display control system for conveying the relative position of food and chopstick tips to the user. Food images taken vertically downwards are analyzed by YOLOv4 (You Only Look Once version 4), and the positions of food and chopstick tips are recognized with high accuracy in real time. A tactile display is developed that reliably guides chopsticks to the food position by controlling the plane position of the protrusion indicating the relative positional relationship of the food and the chopstick tips. Some experimental verifications are provided to show the effectiveness of the proposed meal support system.