RGB-D image classification method and system based on deep learning

Abstract

The invention relates to an RGB-D image classification method and system based on deep learning. The method comprises the following steps: acquiring an RGB_D object data set; performing background removal processing by using the RGB picture and the depth picture corresponding to the mask picture; dividing the processed RGB_D object data set into a training set and a test set; obtaining a VGG16 transfer learning model; adding two convolution layers in front of the VGG16 transfer learning model to obtain shallow layer features of a mixed image, adding straightening operation behind the VGG16 transfer learning model, using a Softmax classifier to carry out classification, taking a Leaky_Relu function as an activation function to activate a hidden layer, and constructing an RGB-D image classification model; adopting an Adam optimization algorithm, and training the RGB-D image classification model by using the training set; and according to the test set, utilizing the trained RGB-D image classification model. According to the invention, the accuracy and efficiency of image recognition can be improved.

Description

technical field [0001] The invention relates to the field of digital image processing, in particular to a deep learning-based RGB-D image classification method and system. Background technique [0002] With the development of information science and technology, people have needs for various applications such as target detection and analysis, object and character recognition, and image retrieval. Moreover, many applications are based on real-time processing. However, due to changes in lighting conditions, changes in the lighting angle of view during the image collection process will lead to inaccurate recognition, so how to obtain accurate recognition under different conditions is very important. [0003] The current existing classification methods include: object classification based on word bag type, and object recognition classification based on deep learning. These two categories include the vast majority of different classification algorithms, for example: artificial d...

AI Technical Summary

Problems solved by technology

The optimization method used in the references is the batch gradient descent method (BGD) to optimize the parameters in the neural network. Although this method has advantages, it also has some shortcomings. In the process of updating the gradient once, this method needs Use the entire batch of sample data to update the gradient. When the amount of data is too large, the calculation speed of the optimization process will become slower.

Images