Research on Image Recognition of Electrical Equipment based on Deconvolution Feature Extraction

Based on machine learning technology and combining the operation of from idea neural network, this paper focuses classification recognition image data transformers, circuit breakers isolation switches in substations. Firstly, enhancement is carried out basis original image, which simulates possible scenes reality. Secondly, using dual-mode a deconvolutional network to capture significant features in-depth visible infrared images. Furthermore, all these are subjected program conduct transfer weighted fusion. The (DMDN) extracts highlights electrical equipment. Compared traditional model, accuracy improved model reached at 99.17%.