An Automatic Instrument Recognition Approach Based on Deep Convolutional Neural Network

Background: This paper presents an automatic instrument recognition method highlighting the deep learning aspect of instrument identification in order to advance the automatic process of video monitoring remotely equipment of substation. Methods: This work utilizes the Scale Invariant Feature Transform approach (SIFT) and the Gaussian difference model for instrument positioning while proposing a design scheme of the instrument identification system. Results: The experimental outcomes obtained proves that the proposed system is capable of automatically recognizing a modest graphical interface and study independently while improving the effectiveness of the appliance, thereby, realizing the purpose of spontaneous self-check. The proposed approach is applicable for musical instrument recognition, and it provides 92% of the accuracy rate, 87.5% precision value and recall rate of 91.2%. Conclusion: The comparative analysis with other state-of-the-art methods justifies that the proposed deep learning-based music recognition method outperforms the other existing approaches in terms of accuracy, thereby providing a practicable music instrument recognition solution.