Real-time keypoint recognition using restricted Boltzmann machine

M-ary Phase Position Shift Keying Demodulation Using Stacked Denoising Sparse Autoencoders

A deep-learning based detector for M-ary phase position shift keying (MPPSK) systems is proposed in this paper. The major components of this detector include a special impact filter, a stacked denoising sparse autoencoder (DSAE), which was trained in unsupervised learning to extract features from the modulation signals, and a softmax classifier. The features learned by the stacked DSAE were then used to train the softmax classifier to demodulate the received signals into M classes. The architecture presented herein was trained and tested on a simple dataset extended by adding Gaussian noise only. The results from the theoretical analysis and simulation show that the detection performance of the proposed scheme is superior to that of existing detectors.

Bipartite Differential Neural Network for Unsupervised Image Change Detection

Image change detection detects the regions of change in multiple images of the same scene taken at different times, which plays a crucial role in many applications. The two most popular image change detection techniques are as follows: pixel-based methods heavily rely on accurate image coregistration while object-based approaches can tolerate coregistration errors to some extent but are sensitive to image segmentation or classification errors. To address these issues, we propose an unsupervised image change detection approach based on a novel bipartite differential neural network (BDNN). The BDNN is a deep neural network with two input ends, which can extract the holistic features from the unchanged regions in the two input images, where two learnable change disguise maps (CDMs) are used to disguise the changed regions in the two input images, respectively, and thus demarcate the unchanged regions therein. The network parameters and CDMs will be learned by optimizing an objective function, which combines a loss function defined as the likelihood of the given input image pair over all possible input image pairs and two constraints imposed on CDMs. Compared with the pixel-based and object-based techniques, the BDNN is less sensitive to inaccurate image coregistration and does not involve image segmentation or classification. In fact, it can even skip over coregistration if the degree of transformation (due to the different view angles and/or positions of the camera) between the two input images is not that large. We compare the proposed approach with several state-of-the-art image change detection methods on various homogeneous and heterogeneous image pairs with and without coregistration. The results demonstrate the superiority of the proposed approach.

Restricted Boltzmann Machines With Gaussian Visible Units Guided by Pairwise Constraints

Restricted Boltzmann machines (RBMs) and their variants are usually trained by contrastive divergence (CD) learning, but the training procedure is an unsupervised learning approach, without any guidances of the background knowledge. To enhance the expression ability of traditional RBMs, in this paper, we propose pairwise constraints (PCs) RBM with Gaussian visible units (pcGRBM) model, in which the learning procedure is guided by PCs and the process of encoding is conducted under these guidances. The PCs are encoded in hidden layer features of pcGRBM. Then, some pairwise hidden features of pcGRBM flock together and another part of them are separated by the guidances. In order to deal with real-valued data, the binary visible units are replaced by linear units with Gaussian noise in the pcGRBM model. In the learning process of pcGRBM, the PCs are iterated transitions between visible and hidden units during CD learning procedure. Then, the proposed model is inferred by approximative gradient descent method and the corresponding learning algorithm is designed. In order to compare the availability of pcGRBM and traditional RBMs with Gaussian visible units, the features of the pcGRBM and RBMs hidden layer are used as input "data" for K -means, spectral clustering (SP) and affinity propagation (AP) algorithms, respectively. We also use tenfold cross-validation strategy to train and test pcGRBM model to obtain more meaningful results with PCs which are derived from incremental sampling procedures. A thorough experimental evaluation is performed with 12 image datasets of Microsoft Research Asia Multimedia. The experimental results show that the clustering performance of K -means, SP, and AP algorithms based on pcGRBM model are significantly better than traditional RBMs. In addition, the pcGRBM model for clustering tasks shows better performance than some semi-supervised clustering algorithms.

An Improved Randomized Local Binary Features for Keypoints Recognition

In this paper, we carry out researches on randomized local binary features. Randomized local binary features have been used in many methods like RandomForests, RandomFerns, BRIEF, ORB and AKAZE to matching keypoints. However, in those existing methods, the randomness of feature operators only reflects in sampling position. In this paper, we find the quality of the binary feature space can be greatly improved by increasing the randomness of the basic sampling operator. The key idea of our method is to use a Randomized Intensity Difference operator (we call it RID operator) as a basic sampling operator to observe image patches. The randomness of RID operators are reflected in five aspects: grids, position, aperture, weights and channels. Comparing with the traditional incompletely randomized binary features (we call them RIT features), a completely randomized sampling manner can generate higher quality binary feature space. The RID operator can be used on both gray and color images. We embed different kinds of RID operators into RandomFerns and RandomForests classifiers to test their recognition rate on both image and video datasets. The experiment results show the excellent quality of our feature method. We also propose the evaluation criteria for robustness and distinctiveness to observe the effects of randomization on binary feature space.