Set Of Sample Images Research Articles

Temporal posture estimation of nonrigid objects lacking sufficient features based on the automatically generated stick and ellipse model

AbstractWe propose a method for tracking nonrigid objects using an object model automatically generated from a set of sample images. Our model consists of multiple sticks and ellipses that represent the skeleton and the areas of an object, respectively. In previous methods, it is difficult to estimate the entire area and posture of a nonrigid object, which lacks sufficient characteristic features (e.g., texture patterns and shapes), because the previous methods have not dealt with the extraction of appearance features for any object from a 2D image of the object. With the proposed model, on the other hand, our method is effective because (1) each component of the model can fit each rigid part of a nonrigid object and (2) the reliability of each component is evaluated. In order to confirm the effectiveness of the proposed method, we conducted several experiments with goldfish and human subjects. The tracking system automatically generated a model of the target; it could then track multiple targets even when they were partially occluded. © 2006 Wiley Periodicals, Inc. Syst Comp Jpn, 37(6): 21–31, 2006; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/scj.20493

Multivariate statistical modeling for image denoising using wavelet transforms

Recently a variety of efficient image denoising methods using wavelet transforms have been proposed by many researchers. In this paper, we derive the general estimation rule in the wavelet domain to obtain the denoised coefficients from the noisy image based on the multivariate statistical theory. The multivariate distributions of the original clean image can be estimated empirically from a sample image set. We define a parametric multivariate generalized Gaussian distribution (MGGD) model which closely fits the sample distribution. Multivariate model makes it possible to exploit the dependency between the estimated wavelet coefficients and their neighbours or other coefficients in different subbands. Also it can be shown that some of the existing methods based on statistical modeling are subsets of our multivariate approach. Our method could achieve high quality image denoising. Among the existing image denoising methods using the same type of wavelet (Daubechies 8) filter, our results produce the highest peak signal-to-noise ratio (PSNR).

Learning to detect objects in images via a sparse, part-based representation

We study the problem of detecting objects in still, gray-scale images. Our primary focus is the development of a learning-based approach to the problem that makes use of a sparse, part-based representation. A vocabulary of distinctive object parts is automatically constructed from a set of sample images of the object class of interest; images are then represented using parts from this vocabulary, together with spatial relations observed among the parts. Based on this representation, a learning algorithm is used to automatically learn to detect instances of the object class in new images. The approach can be applied to any object with distinguishable parts in a relatively fixed spatial configuration; it is evaluated here on difficult sets of real-world images containing side views of cars, and is seen to successfully detect objects in varying conditions amidst background clutter and mild occlusion. In evaluating object detection approaches, several important methodological issues arise that have not been satisfactorily addressed in previous work. A secondary focus of this paper is to highlight these issues and to develop rigorous evaluation standards for the object detection problem. A critical evaluation of our approach under the proposed standards is presented.

On connected filters in color image processing

A standard approach to extending gray-scale filters to color is the use of gray-scale filters on each of the red, green, and blue bands separately. This RGB component method, when applied to connected filters, causes the introduction of new colors into the image, which could lead to incorrect classification or analysis. We develop a method of applying connected filters to color images using rotation in the hue band of the hue-saturation-value (HSV) color space. The rotation shifts the discontinuity in hue such that the distance to the nearest k-means cluster mean is maximized and the histogram value is simultaneously minimized. When applied to the sample image set, the error from the RGB component approach is of the order of 10 times greater than that of our hue rotation approach. Additionally, our approach yields qualitatively improved images, with fewer new colors introduced than the RGB component method.

GENERAL IMAGE CLASSIFICATION USING ADAPTIVE CELLULAR COLOR DECOMPOSITION

In this paper, a coarse-to-fine hierarchical classification method based on the features derived from adaptive cellular color decomposition is proposed. The proposed method is general and can be applied to all kinds of color image databases as long as a sample set of images have been classified. In addition, the number of classes can be as versatile as required. To achieve the goal mentioned above, our method consists of two phases: color quantization and classification. In the color quantization step, cellular decomposition is used to adaptively quantize color images in the HSV color space since H and S components construct a hexagon structure that is same as the cellular pattern. In the classification step, a coarse-to-fine strategy is employed. In the coarse stage, five image-based features extracted directly from the quantization results of the query images are used to prune irrelevant database images. In the fine stage, two cluster-based features are extracted from a small set of candidate images using closest-cluster matching. On the other hand, according to feature evaluation, one image-based and two cluster-based features are selected to derive individual-based similarity measure, which, in turn, is used to measure image-to-image similarity. In addition, class-based similarity measure using class characteristics is proposed to evaluate image-to-class similarity. Candidate images are then sorted according to the similarity measure, which is a combination of individual-based and class-based similarity measures. Finally, k-NN rule is used to assign the query image to a single class according to the sorting results. The effectiveness and practicability of the proposed method have been demonstrated by various experimental results.

Dynamic Textures for Image-based Rendering of Fine-Scale 3D Structure and Animation of Non-rigid Motion

The problem of capturing real world scenes and then accurately rendering them is particularly difficult for finescale 3D structure. Similarly, it is difficult to capture, model and animate non-rigid motion. We present a method where small image changes are captured as a time varying (dynamic) texture. In particular, a coarse geometry is obtained from a sample set of images using structure from motion. This geometry is then used to subdivide the scene and to extract approximately stabilized texture patches. The residual statistical variability in the texture patches is captured using a PCA basis of spatial filter s. The filter s coefficients are parameterized in camera pose and object motion. To render new poses and motions, new texture patches are synthesized by modulating the texture basis. The texture is then warped back onto the coarse geometry. We demonstrate how the texture modulation and projective homography-based warps can be achieved in real-time using hardware accelerated OpenGL. Experiments comparing dynamic texture modulation to standard texturing are presented for objects with complex geometry (a flower) and non-rigid motion (human arm motion capturing the non-rigidities in the joints, and creasing of the shirt).

Using coincident multispectral satellite data to assess the accuracy of special sensor microwave imager liquid water path measurements

We present techniques to identify and reduce the sources of error in the liquid water path (LWP) of marine stratocumulus clouds retrieved from the special sensor microwave imager (SSMI), using coincident high‐resolution visible and infrared data provided by the operational linescan system (OLS). The OLS data are used to identify cloud‐free areas in order to determine the degree of error in the estimated clear sky polarization difference, an important parameter in the SSMI retrieval algorithm. The retrieval algorithm is refined by including the cloud top temperature derived from the OLS infrared data. Errors in the LWP measurements owing to broken or inhomogeneous clouds are difficult to quantify, but a subpixel analysis of cloud type and spatial variability reveals which measurements are more likely to be biased. The application of these techniques on a set of sample images confirms that the relationships between the liquid water path and other cloud parameters are most robust in overcast conditions.