Deep Learning

Current Convolutional neural networks have become a standard method of machine learning for 'mesh data' (pictures, videos, etc.). Initially we commenced with the FER-2013 emotion dataset and endeavored implementing general CNN with different classifiers, achieved 66.05% [1] classification accuracy and improved it to further 71.11% till we reach the plateau. To improve it further, we started accumulating more and more data and then propose a CNN (Convolutional Neural Networks) and RNN (Recurrent Neural Networks) mixed model [2] for image classification, the proposed network, called CNN-RNN model. Image data can be viewed as two-dimensional wave data, and convolution calculation is a filtering process. It can filter non-critical band information in an image, leaving behind important features of image information. The CNN-RNN model can utilize the RNN to Calculate the Dependency and Continuity Features of the Intermediate Layer Output of the CNN Model, connect the characteristics of these middle tiers to the final full-connection network for classification prediction, which will result in better classification accuracy, achieved greater classification success rate 85.04%.

Once you’re interested in any of the features

Connect to us for a quick demo in no time

Want to know more? Reach Us