Joonsoo Choi

Contour-based partial object recognition using symmetry in image databases

This paper discusses the problem of partial object recognition in image databases. We propose the method to reconstruct and estimate partially occluded shapes and regions of objects in images from overlapping and cutting. We present the robust method for recognizing partially occluded objects based on symmetry properties, which is based on the contours of objects. Our method provides simple techniques to reconstruct occluded regions via a region copy using the symmetry axis within an object. Based on the estimated parameters for partially occluded objects, we perform object recognition on the classification tree. Since our method relies on reconstruction of the object based on the symmetry rather than statistical estimates, it has proven to be remarkably robust in recognizing partially occluded objects in the presence of scale changes, rotation, and viewpoint changes.

Design, Analysis, and Optimization of LCD Backlight Unit using Ray Tracing Simulation

The design of BLU for LCD devices, whose goal is to achieve uniform illumination and high luminance across the LCD surface, requries an assistance of illumination design programs. The goal of this paper is to develop a design and analysis tool to model an efficient BLU. The rendering techniques traditionally used in the field of computer graphics are the usual tools of choice to analyze BLU. An analysis method based on Monte Carlo photon tracing to evaluate the optical performance of BLU is presented. An optimization technique based on direct search method, a simplex method by Nelder and Mead, to achieve an optimal uniform illumination is also discussed.

Algorithms for finding disjoint path covers in unit interval graphs

A many-to-many k -disjoint path cover ( k -DPC for short) of a graph G joining the pairwise disjoint vertex sets S and T , each of size k , is a collection of k vertex-disjoint paths between S and T , which altogether cover every vertex of G . This is classified as paired, if each vertex of S must be joined to a specific vertex of T , or unpaired, if there is no such constraint. In this paper, we develop a linear-time algorithm for the Unpaired DPC problem of finding an unpaired DPC joining S and T given in a unit interval graph, to which the One-to-One DPC and the One-to-Many DPC problems are reduced in linear time. Additionally, we show that the Paired ? k -DPC problem on a unit interval graph is polynomially solvable for any fixed k .

Characterization of spatial channel model based on ray path analysis in high-rise urban environment

The strongest ray analysis based on the computer simulation of wave propagation between a base station(BS) and mobile stations(MSs) is carried out to obtain the spatial-time wideband channel characteristics. The strongest rays are responsible for about 70% of the total received power for BS-MS pairs on the average and their arrival angles rarely deviate from the shortest path lines between a BS and MSs. However, this does not mean that the strongest ray is necessarily the first arrived ray for each BS-MS pair. The AOA statistics reveal that AOAs of the strongest and the second strongest rays are very close to each other for uplink channel, while those are quite apart for downlink channel.

Mapping of ALOS PALSAR σ 0 -based forest stem volume classification map

ALOS data have provided useful information on forest cover and biomass since 2006. Unfortunately, topographic effects influence illumination and shadow conditions of mountainous areas so that accuracy statements of the biomass derived from ALOS data are confused with ground truth data. Therefore, in this study, the test area was divided by directions and regression of backscattering coefficient σ0 and forest stem volume according to the directions was analyzed. As a result, HH and HV polarization σ0 value of westfacing slope and are always higher in case of east-facing slope, it proved topographic effects of ALOS PALSAR data. Also, since HV has wider dynamic range than HH, HV is more sensitive to forest stem volume than HH. Through these results, we produced sigma-nought-based forest stem volume classification map by directions and tried mosaic.

DEM interpolation from contours using medial axis transformation

Contours and digital elevation model (DEM) are the most commonly used digital terrain models. In this paper, we propose a technique for constructing a DEM from contours. The elevation of each ground point in DEM is computed by interpolating the heights of the two adjacent contours of the point. The technique decomposes each sub-domain between adjacent contours into a set of sub-regions using medial axis transformation. Each sub-region in the decomposition is classified into a variety of terrain features like hillsides, valleys, ridges, canyons, peaks, pits, etc. The elevations of points are interpolated with different methods according to terrain features they belong to. The interpolation is conducted on the approximate steepest or shortest slope lines constructed based on medial axis. The univariate monotone rational Hermite spline and convex rational Hermite spline are used for the interpolation.

Recognition of Partially Occluded Elliptical Objects using Symmetry on Contour

There are many research efforts in object recognition. Most existing methods for object recognition are based on full objects. However, many images contain multiple objects with occluded shapes and regions. Due to the occlusion of objects, image retrieval can provide incomplete, uncertain, and inaccurate results. To resolve this problem, we propose a new method to reconstruct objects using symmetry properties since most objects in a given image database are represented by symmetrical figures. Even though there have been several efforts in object recognition with occlusion, current methods have been highly sensitive to object pose, rotation, scaling, and visible portion of occluded objects. In addition, many appearance-based and model-based object recognition methods assumed that they have known occluded regions of objects or images through extensive training processes with statistical approach. However, our new approach is not limited to recognizing occluded objects by pose and scale changes, and does not need extensive training processes. Unlike existing methods, the proposed method finds shapes and regions to reconstruct occluded shapes and regions within objects. We assume that we only consider the elliptical objects in recognition. The proposed approach can handle object rotation and scaling for dealing with occlusion, and does not require extensive training processes. The main advantage of our proposed approach is that it becomes simple to reconstruct objects from occlusions using symmetry. We present a robust method, which is based on the contours of objects, for recognizing partially occluded objects based on symmetry properties. The contour-based approach finds a symmetry axis using the maximum diameter from the occluded object. In experiments, we demonstrate how a proposed method reconstructs and recognizes occluded shapes and regions using symmetry. Experiments use rotated and scaled objects for dealing with occlusion. We use mirror symmetry to find possible occluded regions in objects. Examples of partially occluded objects are shown in Figure 1.1. We also evaluate the recognition rate of the reconstructed objects using symmetry and the visible portion of the occluded objects for recognition. The method produces average recognition rates for cups and plates above 88% with 30% occlusion. In this case, part of the