Robotics is a field of research that has undergone several changes in recent years. Currently, robot applications are commonly used for many applications, such as pump deactivation, mobile robotic manipulation, etc. However, most robots today are programmed to follow a predefined path. This is sufficient when the robot is working in a settled environment. Nonetheless, for many tasks, autonomous robots are needed. In this way, NAO humanoid robots constitute the new active research platform within the robotics community. In this article, we present a vision system that connects to the NAO robot, allowing robots to detect and recognize the visible text present in objects in images of natural scenes and use that knowledge to interpret the content of a given scene. The proposed vision system is based on deep learning methods and was designed to be used by NAO robots and consists of five stages: 1) capturing the image; 2) after capturing the image, the YOLOv3 algorithm is used for object detection and classification; 3) selection of the objects of interest; 4) text detection and recognition stage, based on the OctShuffleMLT approach; and 5) synthesis of the text. The choice of these models was due to the better results obtained in the COCO databases, in the list of objects, and in the ICDAR 2015, in the text list, these bases are very similar to those found with the NAO robot. Experimental results show that the rate of detecting and recognizing text from the images obtained through the NAO robot camera in the wild are similar to those presented in models pre-trained with natural scenes databases.