Deep Learning Techniques Implement Circuit board inspection in Smart Industrial

This paper proposed deep learning techniques to implement circuit board inspection. Recently, machine learning, cognitive computing, and considerable progress have been progressed. For example, neural networks (NN), convolutional neural networks (CNN), recurrent neural networks (RNN) and long and short-term memory (LSTM), etc., have been widely used in image recognition and time series inference industrial internet of things field, in which image recognition tasks for computer vision has surpassed human vision. In this study, we used the TensorFlow tool to recognize the microcontroller package position that finds the correct location in a circuit board. It is an important indicator for outbound production.