Распознавание образов для людей с нарушениями зрения

Abstract

This work is devoted to applying deep learning for object detection. The task was to create a mobile object detector application for the visually impaired using a convolutional neural network (CNN). For this research, Keras Python library with TensorFlow library was used for object detection. As a result, an API with a convolutional neural network which detects presence of indoors objects on an input image and a mobile application that communicates with the API were created. As a future improvement the trained CNN model can be used directly in the application to support offline mode