Ik-Hyun Lee

Accurate Registration Using Adaptive Block Processing for Multispectral Images

Image registration is a challenging task, with applications in surveillance, motion estimation, and fusion systems. Due to the diversity of sensors, local distortions and large image size, satellite images are often difficult to accurately register. In the literature, local descriptor-based processing techniques, such as scale-invariant feature transforms (SIAdaptive Block ProcessingFTs), have been applied to register satellite images, which provide robust features. However, these techniques suffer from a high-computational cost, lack of features, and low-distribution quality, which affect the registration accuracy. In this paper, we develop an algorithm to register satellite images based on adaptive block processing to increase the number of features and to improve the distribution quality. In addition, outlier removal using statistical masks are associated with classical random sample consensus (RANSAC); a subsequent comparative analysis demonstrates the accuracy of the proposed method. Typically, a classical SIFT prevents its wide application in recent remote sensing, although this is no longer the case with the proposed adaptive block processing method.

Optimizing image focus for 3D shape recovery through genetic algorithm

Three-dimensional information of objects is advantageous and widely used in multimedia systems and applications. Shape form focus (SFF) is a passive optical technique that reconstructs 3D shape of an object using a sequence of images with varying focus settings. In this paper, we propose an optimization of the focus measure. First, Wiener filter is applied for noise reduction from the image sequence. At the second stage, genetic algorithm (GA) is applied for focus measure optimization. GA finds the maximum focus measurement under a fitness criterion. Finally, 3D shape of the object is determined by maximizing focus measure along the optical direction. The proposed method is tested with image sequences of simulated and real objects. The performance of the proposed technique is analyzed through statistical criteria such as root mean square error (RMSE) and correlation. Comparative analysis shows the effectiveness of the proposed method.

Robust Depth Estimation and Image Fusion Based on Optimal Area Selection

Mostly, 3D cameras having depth sensing capabilities employ active depth estimation techniques, such as stereo, the triangulation method or time-of-flight. However, these methods are expensive. The cost can be reduced by applying optical passive methods, as they are inexpensive and efficient. In this paper, we suggest the use of one of the passive optical methods named shape from focus (SFF) for 3D cameras. In the proposed scheme, first, an adaptive window is computed through an iterative process using a criterion. Then, the window is divided into four regions. In the next step, the best focused area among the four regions is selected based on variation in the data. The effectiveness of the proposed scheme is validated using image sequences of synthetic and real objects. Comparative analysis based on statistical metrics correlation, mean square error (MSE), universal image quality index (UIQI) and structural similarity (SSIM) shows the effectiveness of the proposed scheme.

Depth estimation based on blur measurement for three dimensional camera

Depth from Focus (DFF) is the one of the optical methods to estimate depth information. In this paper, we propose a new approach based on blur estimation to obtain depth map. The optimal focused points are selected by maximizing absolute values of deferences in blur signal. The proposed method provides more robust depth information.

Selective area based depth estimation for three dimensional camera

Contrary to compute focus measure on fixed local area for depth estimation, we propose computing selective area using neighborhood around each center point in image sequence. Proposed method provides more accurate depth information and suppresses the noise effectively than conventional methods.

A non-linear approach for depth from focus for digital cameras

Contrary to uniform local averaging, we propose non-linear approach for precise sparse depth map extraction. Noisy focus measurements are replaced with estimated values. This helps to compute accurate 3D shape while preserving edges of objects.

Three-dimensional visualization of a cell by using shape from focus method

A cell is the structural and functional unit of all known living organisms, and its three-dimensional shape is an interesting research topic and having many applications in biology. Usually, cells are kept surrounded with some liquid materials on glass plates. In obtained image sequence, liquid material causes unwanted background in the images, and some virtual images due to the glass plates occurs, which makes difficulty to recover the three-dimensional shape of the cell. Therefore, conventional optical passive methods for three-dimensional shape recovery do not compute depth map accurately. The purpose of this work is to reconstruct three-dimensional shape of HeLa cell by applying shape from focus (SFF) method. SFF method is one of the optical passive methods to estimate three-dimensional shape by using focal information from image sequence. To overcome problems from transparency and reflection, transparent part is segmented from images by using the fact that background of the cell does not have focal point, and an original image sequence is divided into two image sequences for real and virtual part by finding two focused points in itself. For more accurate segmentation of the background part, the labeling method is used, and for automatically dividing an original image sequence into two image sequences, the iterative threshold selection method is used. The proposed approach is tested by using HeLa cell which is one of the most famous cells in biological research area. The experimental result demonstrates the effectiveness.

Optimization of focus measure using genetic algorithm

This paper presents the use of Genetic Algorithm as a search method for focus measure in Shape From Focus (SFF). Previous methods compute focus value for each pixel locally by summing all values within a small window. This summation is a good approximation of focus quality, but is not optimal one. The Genetic Algorithm is used as a fine tuning process in which a measure of best focus is used as the fitness function corresponding to motion parameter values which make up each gene. The experimental results show that the proposed method performs better than previous algorithms such as Sum of the Modified Laplacian(SML), Grey Level Variance(GLV) and Tenenbaum Focus Measure. The results are compared using root mean square error(RMSE) and correlation. The experiments are conducted using objects simulated cone, real cone and TFT-LCD color filter1 to evaluate performance of the proposed algorithm.