Abstract: Firstly, the image is uploaded from the outside environment with a smart device, followed by detection of the edge of a signboard. It will not check if the image which is captured by the device is related to the sign board or not. It will capture all types of images as input. The next phase is the detection of text and the recognition of the text into two languages such as urdu and english. Here the capture image will be check, that the image is related signboard or not. If the image is related to the signboard it displays the output. Final phase uses Artificial Neural Network for the classification and recognition of the manual extracted from the natural scenes or an outside atmosphere. This paper present , it detect the color image as input and produces the output in the form of black and white. Here the images are capture based on color segmentation and Thresholding. CNN is used to identify the type of pic. Our model has achieved accuracy about 99%.
Keywords: Traffic sign ,detection,CNN,Prediction
|
DOI:
10.17148/IJARCCE.2022.115120
