AI Based Voice Assisted Object Recognition for Visually Impaired Society

Blind individuals face the significant challenge of not being able to clearly identify objects in their environment, relying heavily on their other senses to navigate the world. The absence of sight limits their ability to independently experience and understand the physical world around them. To address this fundamental issue, we propose the development of a voice-assisted application that aims to provide technical support and assistance to blind individuals through their smartphones. Unlike existing methods that often require in-person assistance, our application seeks to bridge the gap in the visually impaired community’s access to information and independence, leveraging current technological advancements. Our object detection model system combines multiple components, including optical character recognition and object and human recognition utilizing obstacle detection sensors. When the smartphone’s camera captures an image, it is then processed through a dataset that we have curated. The processing involves a matching process using the K-nearest neighbor algorithm in machine learning to identify and provide information about the objects and people within the image. This comprehensive approach not only aids in object identification but also enhances the user’s understanding of their surroundings. The primary goal of this application is to empower blind individuals to lead more independent lives. By providing real-time information about their environment, it equips them with the tools they need to make informed decisions and navigate the world with greater confidence. Ultimately, our voice-assisted application represents a significant step toward breaking down the barriers faced by the blind community, leveraging technology to enhance their quality of life and foster greater autonomy.