Traffic sign detection and recognition using RGSM and a novel feature extraction method

Independent mobility involves various challenges to Visual Impairment or Blindness (VIB) people. Most of the mobile devices are accessible to people with VIB that makes the use of available specific applications in online stores. Some applications support the independent mobility for VIB users in safely crossing road. The traffic sign detection and recognition (TSDR) is an essential challenge to VIB people. Existing research offers various techniques to detect the traffic sign in an open road environment. However, this system did not correctly recognizes the traffic sign. This research addressed the problem of traffic sign recognition to support the VIB people for safely crossing the road. Traffic sign detection and recognition are achieved by using novel Random Gradient Succession with Momentum (RGSM) with novel shape specific feature extraction method. Finally, the CNN classifier will be utilized to categorize the trained output labels, which then converts the traffic sign into the audio signal in both the training phase and the testing phase. The results are estimated for the performance measures like accuracy, specificity, precision, F-score, Jaccard coefficient, kappa, and Dice coefficient. Estimation of the results shows a better improvement for this parameter on comparing the proposed system with that of the existing methods. The proposed traffic sign detection system involves the robust audio signal processing that increased the feature extraction and classification performances. The suggested solution solves the obstacles faced by visually impaired peoples for independent mobility.