Object Detection for Signboard using Deep Neural Network
Vijendra Pratap Singh, S Hasan Hussain, Sushma Jaiswal · International Journal of Scientific Methods in Intelligence Engineering Networks · 2023
The goal of this work is to help the visually impaired by making it possible for them to recognize hidden images on signs, which will hopefully lead to fewer accidents. Although traffic signs are essential for maintaining order, they can also increase the risk of accidents if they are obstructed. Individuals who are visually impaired, such as the blind, can benefit greatly from this technique. Furthermore, the proposed system is conducive to the operation of autonomous cars, as the billboards can be read automatically and the vehicles may be directed by the proposed system. When a potentially dangerous image is received, a warning is displayed to the driver. Throughout this piece, ”input image” will refer to the footage recorded by a camera situated at the front of the car. After converting the image to grayscale, a resizing method is applied, and a filter is used to get rid of any noticeable noise that remains. In the end, feature extraction and feature reduction methods are used to priorities certain features over others. Hence, the DNN procedure is an integral aspect of the system, as it is used for both speech recognition and image recognition. This project’s main goal is to recognize incoming photos by comparing them to data sets stored in a database, with successful matches sounding an alarm for the driver.