SMART VISION ASSISTANT FOR THE VISUALLY IMPAIRED : OBJECT DETECTION AND AUDITORY FEEDBACK
GOKULAKRISHNAN V1, VENKATESH G2, YOKESHRAJ D3, BALAJI R4, KANNAN A5
1Assistan professor, Dept of CSE, Dhanalakshmi Srinivasan Engineering College, Perambalur-621212.
2UG Student, Dept of CSE, Dhanalakshmi Srinivasan Engineering College, Perambalur-621212.
3UG Student, Dept of CSE, Dhanalakshmi Srinivasan Engineering College, Perambalur-621212.
4UG Student, Dept of CSE, Dhanalakshmi Srinivasan Engineering College, Perambalur-621212.
5UG Student, Dept of CSE, Dhanalakshmi Srinivasan Engineering College, Perambalur-621212.
---------------------------------------------------------------------***---------------------------------------------------------------------
ABSTRACT-For individuals with visual impairments, it is crucial to be able to distinguish the products they use daily. Therefore, we have implemented a method utilizing a camera to assist in product recognition during their daily activities. To separate an object from un-necessary background, movement-based technique is used to spot object of concern from the camera by instructing person about recognized objects. The aim of this current project is to develop an object detection system tailored for visually impaired individuals and other commercial applications. This system is designed to effectively recognize objects within a predetermined range, fulfilling the requirements of the target audience. Traditional methods of object detection required extensive training data it takes more time and it’s quite complicated and it’s a difficult task. Object detection is used in many scenarios. Conventional methods of these object detection depend on huge number of datasets and it also takes large amount of time to train these data. Training of small or unseen objects is a more challenging task. Human brains and visual systems are more accurate and faster in detecting objects in real time and has conscious thoughts in detecting obstacles. Due to the availability of large amount of data and with more advanced technologies and better working algorithms, classification and detection of multiple objects in the same frame has become easy with high accuracy. The main objective of the project is to design and implement a real time object recognition using real time camera. And also using implement text detection and recognition system to extract the text from captured image using Optical character recognition algorithm. We can implement the system in real time environment using Python as front end.
Keywords: Object detection, Visually impaired, Real-time recognition, Optical character recognition, python.
