Bag of visual words is a promising approach to object categorization. However, in this framework, ambiguity exists in patch encoding by visual words, due to information loss caused by vector quantization. In this paper, we propose to incorporate patch-level contextual information into bag of visual words for reducing the ambiguity mentioned above. To achieve this goal, we construct a hierarchical codebook in which visual words in the upper hierarchy contain contextual information of visual words in the lower hierarchy. In the proposed method, from each sample point we extract patches of different scales, all of which are described by the SIFT descriptor. Then, we build the hierarchical codebook in which visual words created from coarse scale patches are put in the upper hierarchy, while visual words created from fine scale patches are put in the lower hierarchy. At the same time, by employing the corresponding relationship among these extracted patches, visual words in different hierarchies are associated with each other. After that, we design a method to assign patch pairs, whose patches are extracted from the same sample point, to the constructed codebook. Furthermore, to utilize image information effectively, we implement the proposed method based on two sets of features which are extracted through different sampling strategies and fuse them using a probabilistic approach. Finally, we evaluate the proposed method on dataset Caltech 101 and dataset Caltech 256. Experimental results demonstrate the effectiveness of the proposed method.

Local descriptors, Local Binary Pattern (LBP) and Scale Invariant Feature Transform (SIFT) are widely used in various computer applications. They emphasize different aspects of image contents. In this letter, we propose to combine them in sparse coding for categorizing scene images. First, we regularly extract LBP and SIFT features from training images. Then, corresponding to each feature, a visual word codebook is constructed. The obtained LBP and SIFT codebooks are used to create a two-dimensional table, in which each entry corresponds to an LBP visual word and a SIFT visual word. Given an input image, LBP and SIFT features extracted from the same positions of this image are encoded together based on sparse coding. After that, spatial max pooling is adopted to determine the image representation. Obtained image representations are converted into one-dimensional features and classified by utilizing SVM classifiers. Finally, we conduct extensive experiments on datasets of Scene Categories 8 and MIT 67 Indoor Scene to evaluate the proposed method. Obtained results demonstrate that combining features in the proposed manner is effective for scene categorization.

The extened Kalman filter (EKF) and unscented Kalman filter (UKF) have been successively applied in particle filter framework to generate proposal distributions, and shown significantly improving performance of the generic particle filter that uses transition prior, i.e., the system state transition prior distribution, as the proposal distribution. In this paper we propose to use the Gauss-Newton EKF/UKF to replace EKF/UKF for generating proposal distribution in a particle filter. The Gauss-Newton EKF/UKF that uses iterated measurement update can approximate the optimal proposal distribution more closer than EKF/UKF, especially in the case of significant nonlinearity in the measurement function. As a result, the Gauss-Newton EKF/UKF is able to generate and propagate the proposal distribution for each particle much better than EKF/UKF, thus further improving the performance of state estimation. Simulation results for a nonlinear/non-Gaussian time-series demonstrate the superior estimation accuracy of our method compared with state-of-the-art filters.

In this paper, we extend two-image photometric stereo method to treat a concave polyhedron, and present an iterative algorithm to remove the influence of interreflections. By the method we can obtain the shape and reflectance of a concave polyhedron with perfectly diffuse (Lambertian) and unknown constant reflectance. Both simulation and experiment show the feasibility and accuracy of the method.

A network system is proposed for segmenting and extracting multiple moving objects in 2D images. The system uses an interconnected neural network in which grouping factors, such as edge proximity, smoothness of edge orientatio, and smoothness of velocity perpendicular to an edge, are embedded. The system groups edges so that the network energy may be minimized, i.e. edges may be organized into perceptually plausible configuration. Experimantal results are provided to indicate the performance and noise robustness of the system in extracting objects in synthetic images.

We often see reflection phenomenon in our life. For example, through window glass, we can see real objects, but reflection causes virtual objects to appear in front of the glass. Thus, it is sometimes difficult to recognize the real objects. Some works have been proposed to separate these real and virtual objects using an optical property called polarization. However, they have a restriction on one assumption: the angle of incidence. In this paper, we overcome this difficulty using independent component analysis (ICA). We show the efficiency of the proposed method, by experimental results.

The heart rate variability (HRV) is a measure based on the time position of the electrocardiogram (ECG) R-waves. There is a discussion whether or not we can obtain the HRV pattern from blood pressure (BP). In this paper, we propose a method for estimating HRV from a BP signal based on a HIF algorithm and carrying out experiments to compare BP as an alternative measurement of ECG to calculate HRV. Based on the hypotheses that ECG and BP have the same harmonic behavior, we model an alternative HRV signal using a nonlinear algorithm, called heart instantaneous frequency (HIF). It tracks the instantaneous frequency through a rough fundamental frequency using power spectral density (PSD). A novelty in this work is to use fundamental frequency instead of wave-peaks as a parameter to estimate and quantify beat-to-beat heart rate variability from BP waveforms. To verify how the estimate HRV signals derived from BP using HIF correlates to the standard gold measures, i.e. HRV derived from ECG, we use a traditional algorithm based on QRS detectors followed by thresholding to localize the R-wave time peak. The results show the following: 1) The spectral error caused by misestimation of time by R-peak detectors is demonstrated by an increase in high-frequency bands followed by the loss of time domain pattern. 2) The HIF was shown to be robust against noise and nuisances. 3) By using statistical methods and nonlinear analysis no difference between HIF derived from BP and HRV derived from ECG was observed.

Stereoscopic vision technology is applied in a wide range of fields, from 3D movies to medical care. Stereoscopic vision makes it possible to observe images in parallax between both eyes. However, parallax images cannot be used all the time due to a situation called “occlusion”, in which an object is hidden in the depths by another object. In this case, different images are projected on the right and left retina. Here, we propose a psychology experiment to elucidate the function of parvocellular cells in the LGN of the visual cortex of the brain using occlusion perception. As a new psychology experiment to clarify whether parvocellular cells in the LGN of the visual cortex, said to process chromatic and luminance information, can detect a disagreement between the retinal images produced by each eye, we measured convergence eye movement when gazing at the rim of a column under occlusion using an equiluminance random dot pattern. When eye movement prevented the disagreement of the retinal images caused by occlusion, we thought that convergence eye movement to move both eyes in front of the rim or divergence eye movement to move them behind the rim would occur. In other words, we thought that we could clarify whether there was parvocellular system process agreement or disagreement between the right and left retinal images under equiluminance. Therefore, we examined whether a system to detect disagreement between the retinal images exists in the brain when gazing at the rim of a column onto which an equiluminance random dot texture was mapped. Results suggested that the mechanism to avoid disagreement between the retinal images of the eyes caused by occlusion occurs in the parvocellular cells, which mainly process color information, as well as in the magnocellular cells, which process binocular disparity.

We propose a method for compensating distortion of image by calibrating intrinsic camera parameters by image registration which does not need point-to-point correspondence. The proposed method divides the registration between a calibration pattern and a distorted image observed by a camera into two steps. The first step is the straightforward registration from the pattern in order to correct the displacement due to projection. The second step is the backward registration from the observed image for compensating the distortion of the image. Both of the steps use Gauss-Newton method, a nonlinear optimization technique, to minimize residuals of intensities so that the pattern and the observed image become the same. Experimental results show the usefulness of the proposed method. Finally we discuss the convergence of the proposed method which consists of the two registration steps.

We propose a learning strategy for acceleration in learning speed of genetic programming (GP), named hierarchical structure GP (HSGP). The HSGP exploits multiple learning nodes (LNs) which are connected in a hierarchical structure, e.g., a binary tree. Each LN runs conventional evolutionary process to evolve its own population, and sends the evolved population into the connected higher-level LN. The lower-level LN evolves the population with a smaller subset of training data. The higher-level LN then integrates the evolved population from the connected lower-level LNs together, and evolves the integrated population further by using a larger subset of training data. In HSGP, evolutionary processes are sequentially executed from the bottom-level LNs to the top-level LN which evolves with the entire training data. In the experiments, we adopt conventional GPs and the HSGPs to evolve image recognition programs for given training images. The results show that the use of hierarchical structure learning can significantly improve learning speed of GPs. To achieve the same performance, the HSGPs need only 30-40% of the computation cost needed by conventional GPs.

Event-related are the kind of signals that are time-related to a given event. In this work, we will study the effect of bias and overlapping noise on Fourier linear combiner (FLC)-based filters, and its implication on filtering event-related signals. We found that the bias alters the weights behaviour, and therefore the filter output, and we discuss solutions to the problem of spectral overlap.

The blind separation of sources is a recent and important problem in signal processing. Since 1984, it has been studied by many authors whilst many algorithms have been proposed. In this paper, the description of the problem, its assumptions, its currently applications and some algorithms and ideas are discussed.

In this letter we propose a filter for extracting a quasi-periodic signal from a noisy observation using wavelets. It is assumed that the instantaneous frequency of the signal is known. A particularly difficult task when the frequency and amplitude of the desired signal are varying with time is shown. The proposed algorithm is compared with three other methods.

In this letter, a new approach to segment depth-of-field (DoF) images is proposed. The methodology is based on a two-stage model of visual neuron. The first stage is a retinal filtering by means of luminance normalizing non-linearity. The second stage is a V1-like filtering using filters estimated by independent component analysis (ICA). Segmented image is generated by the response activity of the neuron measured in terms of kurtosis. Results demonstrate that the model can discriminate image parts in different levels of depth-of-field. Comparison with other methodologies and limitations of the proposed methodology are also presented.

We discuss the uniqueness of 3-D shape reconstruction of a polyhedron from a single shading image. First, we analytically show that multiple convex (and concave) shape solutions usually exist for a simple polyhedron if interreflections are not considered. Then we propose a new approach to uniquely determine the concave shape solution using interreflections as a constraint. An example, in which two convex and two concave shapes were obtained from a single shaded image for a trihedral corner, has been given by Horn. However, how many solutions exist for a general polyhedron wasn't described. We analytically show that multiple convex (and concave) shape solutions usually exist for a pyramid using a reflectance map, if interreflection distribution is not considered. However, if interreflection distribution is used as a constraint that limits the shape solution for a concave polyhedron, the polyhedral shape can be uniquely determined. Interreflections, which were considered to be deleterious in conventional approaches, are used as a constraint to determine the shape solution in our approach.

In this letter, we introduce a novel patch sampling strategy for the task of image classification, which is fundamentally different from current patch sampling strategies. A top-down guidance learned from training images is used to guide patch sampling towards informative regions. Experiment results show that this approach achieved noticeable improvement over baseline patch sampling strategies for the classification of both object categories and scene categories.

We propose a new multi-objective genetic programming (MOGP) for automatic construction of image feature extraction programs (FEPs). The proposed method was originated from a well known multi-objective evolutionary algorithm (MOEA), i.e., NSGA-II. The key differences are that redundancy-regulation mechanisms are applied in three main processes of the MOGP, i.e., population truncation, sampling, and offspring generation, to improve population diversity as well as convergence rate. Experimental results indicate that the proposed MOGP-based FEP construction system outperforms the two conventional MOEAs (i.e., NSGA-II and SPEA2) for a test problem. Moreover, we compared the programs constructed by the proposed MOGP with four human-designed object recognition programs. The results show that the constructed programs are better than two human-designed methods and are comparable with the other two human-designed methods for the test problem.