Image Computer Vision Research Articles

Sparse Wavelet Representations of Spatially Varying Blurring Operators

Restoring images degraded by spatially varying blur is a problem encountered in many disciplines such as astrophysics, computer vision, and biomedical imaging. One of the main challenges in performing this task is to design efficient numerical algorithms to approximate integral operators. We introduce a new method based on a sparse approximation of the blurring operator in the wavelet domain. This method requires $\mathcal{O}(N \epsilon^{-d/M})$ operations to provide $\epsilon$-approximations, where $N$ is the number of pixels of a $d$-dimensional image and $M\geq 1$ is a scalar describing the regularity of the blur kernel. In addition, we propose original methods to define sparsity patterns when only the operator regularity is known. Numerical experiments reveal that our algorithm provides a significant improvement compared to standard methods based on windowed convolutions.

Computer Vision and Digital Image Processing in Intelligent Navigation System

Current intelligent navigation system has been a mature practical science and technology. Computer vision and digital image processing are the core components, which play pivotal role in intelligent navigation system. These two technologies have been widely applied into national defense and traffic industry. Since extreme weather is frequent, there are higher requirement in computer vision and digital image processing technology.

Posture Correction Technique Based on Visual Analysis

In basketball training, if the posture of basketball player is deviated, great impact will be brought to basketball training. Therefore, this paper presents a posture correction technology based on vision analysis. A lot of computer vision image are collected in basketball training, this images are enhanced to improve definition of image, with the high-quality images to identify wrong posture, and compare with standard posture to achieve posture correction in basketball training. Experimental results show that the proposed algorithm for posture correction in basketball training can improve the accuracy of correction, so as to meet the actual needs of basketball training.

Flexible Image Similarity Computation Using Hyper-Spatial Matching.

Spatial pyramid matching (SPM) has been widely used to compute the similarity of two images in computer vision and image processing. While comparing images, SPM implicitly assumes that: in two images from the same category, similar objects will appear in similar locations. However, this is not always the case. In this paper, we propose hyper-spatial matching (HSM), a more flexible image similarity computing method, to alleviate the mis-matching problem in SPM. Besides the match between corresponding regions, HSM considers the relationship of all spatial pairs in two images, which includes more meaningful match than SPM. We propose two learning strategies to learn SVM models with the proposed HSM kernel in image classification, which are hundreds of times faster than a general purpose SVM solver applied to the HSM kernel (in both training and testing). We compare HSM and SPM on several challenging benchmarks, and show that HSM is better than SPM in describing image similarity.

Conformal-Based Surface Morphing and Multi-Scale Representation

This paper presents two algorithms, based on conformal geometry, for the multi-scale representations of geometric shapes and surface morphing. A multi-scale surface representation aims to describe a 3D shape at different levels of geometric detail, which allows analyzing or editing surfaces at the global or local scales effectively. Surface morphing refers to the process of interpolating between two geometric shapes, which has been widely applied to estimate or analyze deformations in computer graphics, computer vision and medical imaging. In this work, we propose two geometric models for surface morphing and multi-scale representation for 3D surfaces. The basic idea is to represent a 3D surface by its mean curvature function, H, and conformal factor function λ, which uniquely determine the geometry of the surface according to Riemann surface theory. Once we have the (λ, H) parameterization of the surface, post-processing of the surface can be done directly on the conformal parameter domain. In particular, the problem of multi-scale representations of shapes can be reduced to the signal filtering on the λ and H parameters. On the other hand, the surface morphing problem can be transformed to an interpolation process of two sets of (λ, H) parameters. We test the proposed algorithms on 3D human face data and MRI-derived brain surfaces. Experimental results show that our proposed methods can effectively obtain multi-scale surface representations and give natural surface morphing results.

The Simulation of the Psychological Impact of Computer Vision De-Noising Technology

The paper mainly discusses the analysis method for the psychological impact of computer vision noising technology. Actually, people's psychological acceptance and corresponding memory capacity of computer vision images with lots of noise are relatively poor. The de-noising process to computer vision images can improve the clarity, thus generating passive psychological impact. Therefore, the paper proposes a spatial domain filtering algorithm-based de-noising method for computer vision. It establishes wavelet packet decomposition tree for computer vision images and de-noises accordance with the decomposing results. The experiment results show that the proposed de-noising method has passive psychological influence and improves the memory capacity of computer vision images.

On the relevance of sparsity for image classification

In this paper we empirically analyze the importance of sparsifying representations for classification purposes. We focus on those obtained by convolving images with linear filters, which can be either hand designed or learned, and perform extensive experiments on two important Computer Vision problems, image categorization and pixel classification. To this end, we adopt a simple modular architecture that encompasses many recently proposed models.The key outcome of our investigations is that enforcing sparsity constraints on features extracted in a convolutional architecture does not improve classification performance, whereas it does so when redundancy is artificially introduced. This is very relevant for practical purposes, since it implies that the expensive run-time optimization required to sparsify the representation is not always justified, and therefore that computational costs can be drastically reduced.

An Abnormal Crowd Behavior Detection Algorithm Based on Fluid Mechanics

Abnormal crowd behavior detection is an advanced topic researched in fields of computer vision and digital image processing. The problems such as diversity of monitoring scene, different crowd density and mutual occlusion among crowds etc result in a low recognition rate for abnormal crowd behavior detection. In order to solve these problems, this paper combines a streakline model based on fluid dynamics with an abnormal behavior detection method presented by Hassner et al., and proposes a modified algorithm to improve the recognition accuracy of abnormal crowd behavior. Finally, the validity and accuracy of the algorithm are verified via a large amount of challenging real-world surveillance videos.

Spectral Log-Demons: Diffeomorphic Image Registration with Very Large Deformations

This paper presents a new framework for capturing large and complex deformations in image registration and atlas construction. This challenging and recurrent problem in computer vision and medical imaging currently relies on iterative and local approaches, which are prone to local minima and, therefore, limit present methods to relatively small deformations. Our general framework introduces to this effect a new direct feature matching technique that finds global correspondences between images via simple nearest-neighbor searches. More specifically, very large image deformations are captured in Spectral Forces, which are derived from an improved graph spectral representation. We illustrate the benefits of our framework through a new enhanced version of the popular Log-Demons algorithm, named the Spectral Log-Demons, as well as through a groupwise extension, named the Groupwise Spectral Log-Demons, which is relevant for atlas construction. The evaluations of these extended versions demonstrate substantial improvements in accuracy and robustness to large deformations over the conventional Demons approaches.

Recursive Estimation of the Stein Center of SPD Matrices & its Applications.

Symmetric positive-definite (SPD) matrices are ubiquitous in Computer Vision, Machine Learning and Medical Image Analysis. Finding the center/average of a population of such matrices is a common theme in many algorithms such as clustering, segmentation, principal geodesic analysis, etc. The center of a population of such matrices can be defined using a variety of distance/divergence measures as the minimizer of the sum of squared distances/divergences from the unknown center to the members of the population. It is well known that the computation of the Karcher mean for the space of SPD matrices which is a negatively-curved Riemannian manifold is computationally expensive. Recently, the LogDet divergence-based center was shown to be a computationally attractive alternative. However, the LogDet-based mean of more than two matrices can not be computed in closed form, which makes it computationally less attractive for large populations. In this paper we present a novel recursive estimator for center based on the Stein distance - which is the square root of the LogDet divergence - that is significantly faster than the batch mode computation of this center. The key theoretical contribution is a closed-form solution for the weighted Stein center of two SPD matrices, which is used in the recursive computation of the Stein center for a population of SPD matrices. Additionally, we show experimental evidence of the convergence of our recursive Stein center estimator to the batch mode Stein center. We present applications of our recursive estimator to K-means clustering and image indexing depicting significant time gains over corresponding algorithms that use the batch mode computations. For the latter application, we develop novel hashing functions using the Stein distance and apply it to publicly available data sets, and experimental results have shown favorable comparisons to other competing methods.

Characterizing the Variability of Enzymatic Browning in Fresh-Cut Apple Slices

Browning reaction variability in apple slices was characterized using a new procedure denominating the differential pixel method. Using this method, a kinetic rate and an empirical order of reaction were derived for each pixel in an image corresponding to a sliced apple surface undergoing browning; each pixel in the image can be seen as a small portion of the fruit. In the experiments, 40 samples of fresh-cut apple slice were put on a computer vision system and images recorded over time at a room temperature of 5 °C. Data was fitted to the Weibullian model kinetic. Results confirmed strong heterogeneity in the values of enzymatic browning kinetic rate on the apple surface; this variability was characterized as a normal logarithmical distribution, with a mean rate kinetic value of the −0.0117 ± 0.0036 units of L* decayed per minute. The empirical order of reaction was distributed on the surface following a normal statistical distribution with a mean equal to 0.451 ± 0.046. No statistical differences were established in the kinetic rate and in the empirical order when the differential pixel method was compared with the traditional method (where a mean of the L* intensity value was used).

Tenderness prediction in porcine longissimus dorsi muscles using instrumental measurements along with NIR hyperspectral and computer vision imagery

Abstract Tenderness is an important attribute influencing consumer opinion about the eating quality of fresh meat. Manual assessment of tenderness requires lengthy procedures with tedious sample preparations. An objective, non-destructive, and rapid technique for assessing meat tenderness is required by the meat industry. In this study, the development of partial least squares (PLS) regression models to relate near-infrared (NIR) reflectance spectra and statistical features (mean, standard deviation, norm-1 energy, norm-2 energy, average residual, and entropy) from discrete wavelet transforms (DWT) of raw porcine longissimus dorsi muscle images, to slice shear force (SSF) instrumental measurements, was investigated. The coefficient of determination (R2) of the PLS regression model was 0.63 when only spectral information from hyperspectral (HS) images was analyzed, while PLS models using DWT features extracted from computer vision (CV) images yielded coefficient of determination of 0.48. By combining them, the R2 increased to 0.75. The study has shown the potential for NIR measurements combined with wavelet features from CV images to provide better correlations with muscle tenderness. Industrial relevance The study has shown the potential for NIR measurements combined with wavelet features from CV images to provide better correlations with muscle tenderness for the meat industry.

Low-Resolution and Low-Quality Face Super-Resolution in Monitoring Scene via Support-Driven Sparse Coding

Monitoring cameras are now widely used to monitor everything from a room in a house to an entire warehouse. However, in real monitoring scenarios, a variety of factors, such as underexposure, optical blurring, defocusing, have an impact on the quality of images, which leads to low-quality and low-resolution (LR) of the individual of interest. Reconstruction of a high-resolution (HR) face image with detailed facial features, from a LR observation based on a set of HR and LR training image pairs, plays an important role in computer vision and face image analysis applications. To super-resolve an HR face given a LR face image, the key issue is how to effectively encode the LR image patch. However, due to stability and accuracy issues, the coding approaches proposed so far are far from satisfactory. In this paper, we present a novel sparse coding method via exploiting the support information on the coding coefficients. According to the distances between the input patch and bases in the dictionary, we first assign different weights to the coding coefficients and then obtain the coding coefficients by solving a weighted sparse problem. Experiments on commonly used databases and some face images on the real monitoring conditions demonstrate that our method outperforms state-of-the-art.

A New Image Fusion Method based on Integration of Wavelet and Fast Discrete Curvelet Transform

Image fusion is one of the most useful term related to digital image processing, computer vision and medical imaging. The objective of image fusion is to extract the useful information from several images into a single image. Recently, more research has been done on wavelet based image fusion methods for medical application. Wavelet transform is useful for objects with point singularities and analyses the feature of images in detailed, but it does not provide information about edges clearly. While curvelet transform is more useful for the analysis of images having curved shape edges. So, in this paper, a new image fusion method is proposed based on the integration of wavelet and fast discrete curvelet transform, which describe the curved shapes of images and analyses feature of images better. This paper uses MRI and CT images for fusion which contains complementary information helpful for diagnosis of disease. The fusion results obtained from proposed method are analyzed and compared visually and statistically with different types of wavelets used in image fusion. The results of proposed method are efficient and improve the Entropy, PSNR, Mean, STD and MSE. The proposed method can be helpful for better medical diagnosis.

Development of Tea Whitener Using Concentrated Whey and Milk Solids

Whey and toned milk was effectively used for the development of tea whitener. Cheese whey was concentrated to 12% solids in a vacuum evaporator, pasteurized at 72℃±2℃ for 15 s, diluted back to 11.5% solids and was cold blended with toned milk of 11.5% solids in three ratios viz. 25:75, 50:50 and 75:25 and selected blends were homogenized at 1200-1500 psi. Tea was prepared by adding 80 mL whitener to 100 mL decoction and addition of sugar at 8% (w/v). The tea whitener was selected based on the sensory attributes of tea beverages. The colour of the beverages, tea whiteners and decoction were analyzed by reflectance meter and computer vision image analysis technique. The viscosity of the beverage was tested using a Brookfield viscometer. Coffee stability test was done to assess the stability of tea whitener under acidic conditions. Standard plate count, Coliform count and Presumptive Coliform test were done to assess the microbiological quality of the whitener. Homogenization had a positive impact on the viscosity and colour. The reflectance value of tea prepared from 25% homogenised whey milk blend and toned milk were in the range of 43-46 and 45-49, respectively. The viscosity of tea was found to increase with homogenization and whey levels. The sedimentation values of 25% whey blends and toned milk were 1.25 mL and 1 mL respectively. The shelf life of the blends was 2 days under refrigerated conditions. It can be concluded that a satisfactory tea whitener can be prepared by blending whey with toned milk in 25:75 proportion followed by homogenization.

Double Feature Combination: Region Contrast for Visual Salient Object Detection

Visual saliency detection has become an important step between computer vision and digital image processing. Recent methods almost form a computational model based on color, which are difficult to overcome the shortcoming with cluttered and textured background. This paper proposes a novel salient object detection algorithm integrating with region color contrast and histograms of oriented gradients (HoG). Extensively experiments show that our algorithm outperforms other state-of-art saliency methods, yielding higher precision and better recall rate, even lower mean absolution error.

A Comparative Study on Application of Computer Vision and Fluorescence Imaging Spectroscopy for Detection of Huanglongbing Citrus Disease in the USA and Brazil

The overall objective of this work was to develop and evaluate computer vision and machine learning technique for classification of Huanglongbing-(HLB)-infected and healthy leaves using fluorescence imaging spectroscopy. The fluorescence images were segmented using normalized graph cut, and texture features were extracted from the segmented images using cooccurrence matrix. The extracted features were used as an input into the classifier, support vector machine (SVM). The classification results were evaluated based on classification accuracies and number of false positives and false negatives. The results indicated that the SVM could classify HLB-infected leaf fluorescence intensities with up to 90% classification accuracy. Though the fluorescence intensities from leaves collected in Brazil and the USA were different, the method shows potential for detecting HLB.

Learning for Meta-Recognition

In this paper, we consider meta-recognition, an approach for postrecognition score analysis, whereby a prediction of matching accuracy is made from an examination of the tail of the scores produced by a recognition algorithm. This is a general approach that can be applied to any recognition algorithm producing distance or similarity scores. In practice, meta-recognition can be implemented in two different ways: a statistical fitting algorithm based on the extreme value theory, and a machine learning algorithm utilizing features computed from the raw scores. While the statistical algorithm establishes a strong theoretical basis for meta-recognition, the machine learning algorithm is more accurate in its predictions in all of our assessments. In this paper, we present a study of the machine learning algorithm and its associated features for the purpose of building a highly accurate meta-recognition system for security and surveillance applications. Through the use of feature- and decision-level fusion, we achieve levels of accuracy well beyond those of the statistical algorithm, as well as the popular “cohort” model for postrecognition score analysis. In addition, we also explore the theoretical question of why machine learning-based algorithms tend to outperform statistical meta-recognition and provide a partial explanation. We show that our proposed methods are effective for a variety of different recognition applications across security and forensics-oriented computer vision, including biometrics, object recognition, and content-based image retrieval.

Conjunctive Patches Subspace Learning With Side Information for Collaborative Image Retrieval

Content-Based Image Retrieval (CBIR) has attracted substantial attention during the past few years for its potential practical applications to image management. A variety of Relevance Feedback (RF) schemes have been designed to bridge the semantic gap between the low-level visual features and the high-level semantic concepts for an image retrieval task. Various Collaborative Image Retrieval (CIR) schemes aim to utilize the user historical feedback log data with similar and dissimilar pairwise constraints to improve the performance of a CBIR system. However, existing subspace learning approaches with explicit label information cannot be applied for a CIR task, although the subspace learning techniques play a key role in various computer vision tasks, e.g., face recognition and image classification. In this paper, we propose a novel subspace learning framework, i.e., Conjunctive Patches Subspace Learning (CPSL) with side information, for learning an effective semantic subspace by exploiting the user historical feedback log data for a CIR task. The CPSL can effectively integrate the discriminative information of labeled log images, the geometrical information of labeled log images and the weakly similar information of unlabeled images together to learn a reliable subspace. We formally formulate this problem into a constrained optimization problem and then present a new subspace learning technique to exploit the user historical feedback log data. Extensive experiments on both synthetic data sets and a real-world image database demonstrate the effectiveness of the proposed scheme in improving the performance of a CBIR system by exploiting the user historical feedback log data.

Local polynomial regression for symmetric positive definite matrices

Local polynomial regression has received extensive attention for the nonparametric estimation of regression functions when both the response and the covariate are in Euclidean space. However, little has been done when the response is in a Riemannian manifold. We develop an intrinsic local polynomial regression estimate for the analysis of symmetric positive definite (SPD) matrices as responses that lie in a Riemannian manifold with covariate in Euclidean space. The primary motivation and application of the proposed methodology is in computer vision and medical imaging. We examine two commonly used metrics, including the trace metric and the Log-Euclidean metric on the space of SPD matrices. For each metric, we develop a cross-validation bandwidth selection method, derive the asymptotic bias, variance, and normality of the intrinsic local constant and local linear estimators, and compare their asymptotic mean square errors. Simulation studies are further used to compare the estimators under the two metrics and to examine their finite sample performance. We use our method to detect diagnostic differences between diffusion tensors along fiber tracts in a study of human immunodeficiency virus.