Showing papers by "Vladimir Khryashchev published in 2017"

Facial expression recognition algorithm based on deep convolution neural network

Abstract: This paper presents algorithms for smile detection and facial expression recognition. The developed algorithms are based on the implementation of a relatively new approach in the field of deep machine learning — a convolutional neural network. The aim of this network is to classify facial images into one of the six types of emotions. The studying of algorithms was carried using face images from the CMU MultiPie database. To accelerate the neural network operation, the training and testing processes were performed parallel, on a large number of independent streams on GPU. Fo r developed models there were given metrics of quality.

Face verification based on convolutional neural network and deep learning

Abstract: This paper presents the new face verification algorithm based on deep convolutional neural network. The algorithm produces face feature vectors, distance between these vectors allows to determine whether images from the same class. Comparative experimental results are given for LFW test database and modern face recognition algorithms. ROC-curve and equal error rate are used to determine the accuracy of compared algorithms. Testing was carried out under the “image restricted” verification paradigm. With unsupervised learning, the algorithm can't have any access to the data class labels, the statistics of these labels, or the means of generating these labels. Proposed face verification algorithm is more accurate than other modern algorithms.

Enhancement of fast face detection algorithm based on a cascade of decision trees

Abstract: . Face detection algorithm based on a cascade of ensembles of decision trees (CEDT) is presented. The new approach allows detecting faces other than the front position through the use of multiple classifiers. Each classifier is trained for a specific range of angles of the rotation head. The results showed a high rate of productivity for CEDT on images with standard size. The algorithm increases the area under the ROC-curve of 13% compared to a standard Viola-Jones face detection algorithm. Final realization of given algorithm consist of 5 different cascades for frontal/non-frontal faces. One more thing which we take from the simulation results is a low computational complexity of CEDT algorithm in comparison with standard Viola-Jones approach. This could prove important in the embedded system and mobile device industries because it can reduce the cost of hardware and make battery life longer.

Research of the speech signal reconstruction at empirical mode decomposition

Abstract: We discuss a method of signal analysis — empirical mode decomposition, and also its modification — complementary ensemble empirical mode decomposition. Both methods are used to research the reconstruction of a speech signal by the means of intrinsic mode functions that were received during the decomposition. Researches were performed using two English databases of speech signals which contain speech sentences. Sentences are pronounced by male and female speakers. We utilized next objective indexes for our investigations: relative power and root mean square error of reconstruction, quality index PESQ and intelligibility index SNRloss. Results of a computational experiment are given. These results demonstrate a high quality of the signal reconstruction at its full restoration, and also advantages of the complementary decomposition in comparison with the customary decomposition.

Full-focused image fusion in the presence of noise

Abstract: The implementation and analysis of the algorithm for the full-focused image fusion in the presence of noise are presented. Three methods of combining noisy images are considered: without pre-processing and post-processing, using prefiltration of original images, using post-filtering of the fused image. The database of test scenes created by the authors was used for testing the proposed algorithm for full-focused image fusion. Additive white Gaussian noise was considered as an noise model. Two-stage digital image processing scheme, based on principal components analysis was used as a filtering algorithm. Quantitative and visual results are shown and demonstrate the main features of the proposed algorithm.