Comparison of Neural Networks with Feature Extraction Methods for Depth Map Classification

Abstract

In this paper, a comparison between feature extraction methods (Radon Cosine Method, Canny Contour Method, Fourier Transform, SIFT descriptor, and Hough Lines Method) and Convolutional Neural Networks (proposed CNN and pre-trained AlexNet) is presented. For the evaluation of these methods, depth maps were used. The tested data were obtained by Microsoft Kinect camera (IR depth sensor). The feature vectors were classified by the Support Vector Machine (SVM). The confusion matrix for the evaluation of experimental results was used. The row of confusion matrix represents target class of tested data and the column represents predicted class. From the experimental results, it is evident that the best results were achieved by proposed CNN (97.4%). On the other hand, the pre-trained AlexNet scored 93.7%.

Accurate Prediction of Concentration Changes in Ozone as an Air Pollutant by Multiple Linear Regression and Artificial Neural Networks

“…The architectures of the radial basis function (RBF) neural network are feasibly the most frequently used ANNs [28][29][30][31][32][33][34]. The RBF neural network typically involves three layers: the input layer, the hidden layer and the output layer.…”

“…The inbounding vectors are mapped by the radial basis functions in each hidden node. The output layer produces a vector by linear combination of the outputs of the hidden nodes to yield the final output [30,33,34]. The construction of an n inputs and m outputs RBF neural network can be explained by the following equation:…”