Color feature detection and classification by learning

In this article, new local matching measures, based on fuzzy similarity, for stereo matching of color images are proposed and evaluated. By formulating the individual similarity between a pair of pixels as a conjunction of the similarities of the respective color components, the field programmable gate array implementation problem becomes more computationally tractable, since the word-length of the numbers carrying the similarity information can be reduced compared to standard techniques (Sum of absolute differences and Sum of squared differences). It is also shown that combining information about color and local image structure (horizontal gradient component) in the matching measure and using a multi-scale measure is advantageous compared to using standard measures, in terms of percentage of correct matches and MSE for the erroneous matches. However, these improvements come at the prize of more complex implementations. Since the techniques are window-based, they share the typical drawbacks associated with other techniques of this type. This is expected, since the focus is on developing new local matching measure without addressing issues like post-processing of the resulting disparity maps. The techniques have been tested on two stereo color image pairs.

Linear discriminant analysis (LDA) is one of the most popular feature extraction methods in image recognition. Nevertheless, LDA always suffers from some undesired behaviors caused by globality, namely ignoring local geometric structure of images. To fully capture the geometric information, we propose a novel two-dimensional linear discriminant analysis with locality preserving (2DLP-LDA) approach, which can cover both within-class and between-class local geometric information. 2DLP-LDA re-characterizes the within-class scatter matrix by employing locality preserving projection technique and re-characterizes the between-class scatter matrix by introducing a Gaussian weighting function, making the samples from the same class moderately cluster, while the samples from different classes properly distribute in the reduced subspace. Encouraging experimental results on FERET face database as well as SEU bovine iris database show the effectiveness of the proposed approach.

We propose to overcome a significant limitation of the iterative closest point (ICP) algorithm used by KinectFusion, namely, its sole reliance upon geometric information. Our approach uses both geometric and color information in a direct manner that uses all the data in order to accurately estimate camera pose. Data association is performed by Lucas–Kanade to compute an affine warp between the color images associated with two RGBD point clouds. A subsequent step then estimates the Euclidean transformation between the point clouds using either a point-to-point or point-to-plane error metric, with a novel method based on a normal covariance test for automatically selecting between them. Together, Lucas–Kanade data association with covariance testing enables robust camera tracking through areas of low geometric features, without sacrificing accuracy in environments in which the existing ICP technique succeeds. Experimental results on several publicly available datasets demonstrate the improved performance both qualitatively and quantitatively.

We represent local spatial structure in a color image using feature matrices that are computed from an image region. Feature matrices contain significantly more information about local image structure than previous representations. Although feature matrices are useful for surface recognition, this representation depends on the spectral properties of the scene illumination. Using a finite dimensional linear model for surface spectral reflectance with the same number of parameters as the number of color bands, we show that illumination changes correspond to linear transformations of the feature matrices and that surface rotations correspond to circular shifts of the matrices. From these relationships we derive an algorithm for illumination and geometry invariant recognition of local surface structure. We demonstrate the algorithm with a series of experiments on images of real objects.

Multimodality semantic segmentation based on polarization and color images

The problem of image similarity has become a challenging task in the field of computer vision through the last two decades. The assessment of (dis)similarity between color (or multichannel, in general) images or parts of images has been studied on several image processing application domains such as image indexing and retrieval, classification and unsupervised segmentation (Rubner et al., 2001). The basic operations that need to be carried out in order to estimate the similarity between two color images are three-fold (Stricker & Orengo, 1995): first, choose an appropriate color space for image representation; then, extract a signature for each image (using, commonly, low-level features) to construct a theoretically valid distribution; finally, establish pairwise comparisons based on these signatures. Each signature constitutes the content description of a corresponding image. It is summarized based on pixel attributes and provides a representation of the image in a multidimensional feature space. There, a proper (dis)similarity measure is defined in order to act as a general rule for comparing any given pair of images. In these directions, several (dis)similarity measures have been developed and used as empirical estimates of the distribution of image features, confirming that distribution-based measures exhibit excellent performance in all areas (Rubner et al., 2001). In the context of visual image similarity, we make use of a nonparametric test from the field of multivariate statistics that deals with the “Multivariate Two-Sample Problem”, originally presented by Friedman and Rafsky (1979). The specific test is a multivariate extension of the classical Wald-Wolfowitz test (WW-test) and compares two different samples of vectorial observations (i.e. two sets of points in

Different kinds of local image structures (such as homogeneous, edge-like and junction-like patches) can be distinguished by the intrinsic dimensionality of the local signals. Intrinsic dimensionality makes use of variance from a point and a line in spectral representation of the signal in order to classify it as homogeneous, edge-like or junction-like. The concept of intrinsic dimensionality has been mostly exercised using discrete formulations; however, recent work (; ) has introduced a continuous definition. The current study analyzes the distribution of local patches in natural images according to this continuous understanding of intrinsic dimensionality. This distribution reveals specific patterns than can be also associated to local image structures established in computer vision and which can be related to orientation and optic flow features. In particular, we link quantitative and qualitative properties of optic-flow error estimates to these patterns. In this way, we also introduce a new tool for better analysis of optic flow algorithms.

최근 복잡한 3차원 모델의 활용 범위가 확대됨에 따라 메쉬 모델의 간략화에 관한 연구가 활발히 진행되고 있다. 본 논문에서는 기존의 모델 간략화 과정에서 널리 사용되는 모델의 정점에 대한 위치 정보에 근거한 기하 정보 기반의 간략화 방법에 모델의 속성 정보를 동시에 이용한 새로운 간략화 방법을 제시한다. 대부분의 3차원 메쉬 모델의 정보에는 기하 정보뿐만 아니라 모델의 색상, 질감, 그리고 곡률 등과 같은 속성 정보가 포함되며, 기존의 간략화 방법은 통상적으로 기하학적 정보나 속성 정보를 개별적으로 적용하여 메쉬를 간략화 한다. 본 논문에서 제시된 간략화 방법은 모델의 기하학 정보와 속성 정보를 동시에 적용하여 메쉬 간략화를 수행하였다. 특히 본 논문에서는 메쉬의 간략화에 상대적으로 수행 시간과 충실도에 장점을 지닌 이차 오차 척도(quadric error metric)를 확장하여 일반적인 기하학적 정보에 속성 정보를 추가하였다. 따라서, 제안된 메쉬 간략화 방법은 기하 정보기반으로 간략화를 수행하는 이차 오차 척도에 속성 정보가 추가된 간단한 이차식으로 확장하여 표현할 수 있다. 이는 기하 정보만을 이용하였을 때의 이차식의 공간 차수를 m=0으로 두었을 때 추가된 속성 정보의 특성에 따라 차수를 확장 함(m>0)으로서 계산이 가능하다. 실험 결과, 제안된 방법에 의한 모델의 간략화 결과를 원 모델과 비교 시 기하 정보만을 이용한 기존의 간략화 방법의 수행 결과에 비하여 모델의 전체적인 외형 등 특성 정보의 충실도가 높다는 것을 입증할 수 있었다. Recently, the studies for mesh simplification have been increased according to the application area of the complicate 3D mesh models has been expanded. This paper introduces a novel method for mesh simplification which uses the properties of the mesh model in addition to the geometric locations of the model. The information of the 3D mesh model Includes surface properties such as color, texture, and curvature information as well as geometic information of the model. The most of current simplification methods adopt such geometric information and surface properties individually for mesh simplification. However, the proposed simplification method combines the geometric information and solace properties and applies them to the simplification process simultaneously. In this paper, we exploit the extended geometry based quadric error metric(QEM) which relatively allows fast and accurate geometric simplification of mesh. Thus, the proposed mesh simplification utilizes the quadric error metric based on geometric information and the surface properties such as color, normal, and texture. The proposed mesh simplification method can be expressed as a simple quadric equation which expands the quadric error metric based on geometric information by adding surface properties such as color, normal, and texture. From the experimental results, the simplification of the mesh model based on the proposed method shows the high fidelity to original model in some respects such as global appearance rather than using current geometry based simplification.

The retinal vessel is one of the determining factors in an ophthalmic examination. Automatic extraction of retinal vessels from low-quality retinal images still remains a challenging problem. In this paper, we propose a robust and effective approach that qualitatively improves the detection of low-contrast and narrow vessels. Rather than using the pixel grid, we use a superpixel as the elementary unit of our vessel segmentation scheme. We regularize this scheme by combining the geometrical structure, texture, color, and space information in the superpixel graph. And the segmentation results are then refined by employing the efficient minimum spanning superpixel tree to detect and capture both global and local structure of the retinal images. Such an effective and structure-aware tree detector significantly improves the detection around the pathologic area. Experimental results have shown that the proposed technique achieves advantageous connectivity-area-length (CAL) scores of 80.92% and 69.06% on two public datasets, namely, DRIVE and STARE, thereby outperforming state-of-the-art segmentation methods. In addition, the tests on the challenging retinal image database have further demonstrated the effectiveness of our method. Our approach achieves satisfactory segmentation performance in comparison with state-of-the-art methods. Our technique provides an automated method for effectively extracting the vessel from fundus images.

Discriminative orthogonal elastic preserving projections for classification

Fisher linear discriminant analysis (FLDA) is a classic linear feature extraction and dimensionality reduction approach for face recognition. It is known that geometric distribution weight information of image data plays an important role in machine learning approaches. However, FLDA does not employ the geometric distribution weight information of facial images in the training stage. Hence, its recognition accuracy will be affected. In order to enhance the classification power of FLDA method, this paper utilizes radial basis function (RBF) with fractional order to model the geometric distribution weight information of the training samples and proposes a novel geometric distribution weight information based Fisher discriminant criterion. Subsequently, a geometric distribution weight information based LDA (GLDA) algorithm is developed and successfully applied to face recognition. Two publicly available face databases, namely, ORL and FERET databases, are selected for evaluation. Compared with some LDA-based algorithms, experimental results exhibit that our GLDA approach gives superior performance.

We present a new approach to volumetric scene reconstruction which can produce accurate models from turntable image sequences. Instead of an epipolar plane image (EPI) volume, we consider a function on the 4D spatiotemporal volume valued with the intensity back projection of the camera (time) to the particular voxel. Using an optical flow technique we compute the local orientation of this spatiotemporal image and decide on occupancy based on the relative orientation between the viewing ray of the voxel at the particular time and the local image structure. Our method does not require a background compensation like the silhouette-based methods and is comparable in performance with space carving.

We present a novel technique for enhancing an image captured in low light by using near-infrared flash images. The main idea is to combine a color image with near-infrared flash images captured at the same time without causing any interference with the color image. In this work, near-infrared flash images are effectively used for removing annoying effects that are commonly observed in images of dimly lit environments, namely, image noise and motion blur. Our denoising method uses a pair of color and near-infrared flash images captured simultaneously. Therefore it is applicable to dynamic scenes, whereas existing methods assume stationary scenes and require a pair of flash and no-flash color images captured sequentially. Our deblurring method utilizes a set of near-infrared flash images captured during the exposure time of a single color image and directly acquires a motion blur kernel based on optical flow. We implemented a multispectral imaging system and confirmed the effectiveness of our technique through experiments using real images.

Recognizing building group patterns is fundamental to numerous fields, such as urban landscape evaluation, social analysis, and map generalization. Despite the increasing number of algorithms available for building group pattern recognition, there is still a lack of satisfactory grouping results due to insufficient information and only geometric features being provided to recognition methods. This study aims to provide a novel building grouping method that combines building function and geometric information. We specifically focus on the process of recognizing building groups in topographic maps as a prerequisite to subsequent map generalization. First, the building functions are inferred using the dynamic time warping (DTW) algorithm based on Tencent user density data and POIs (points of interest). Then, two types of constrained Delaunay triangulations (CDTs) are created for each building block, from which several spatial indices, such as the continuity index (SCI), direction, and distance of every two adjacent buildings, are derived. Finally, each building block is modeled as a graph on the grounds of derived matrices and building function information, and a graph segmentation approach is proposed to extract building groups. A case study is conducted to test the proposed approach. The experimental results indicate that the proposed approach can produce satisfactory results, given that the correctness value is above 81.63% for our study area. Comparative studies reveal that the method without building function information is an ineffective grouping method when buildings with different functions are close to each other. In addition, generalization results derived from the proposed method are more in line with those of maps for daily use, as they provide users with more accurate spatial divisions of urban buildings.

One of the difficulties in estimating optical flow is bias. Correcting the bias using the classical techniques is very difficult. The reason is that knowledge of the error statistics is required, which usually cannot be obtained because of lack of data. In this paper, we present an approach which utilizes color information. Color images do not provide more geometric information than monochromatic images to the estimation of optic flow. They do, however, contain additional statistical information. By utilizing the technique of instrumental variables, bias from multiple noise sources can be robustly corrected without computing the parameters of the noise distribution. Experiments on synthesized and real data demonstrate the efficiency of the algorithm.