• IEIE Transactions on Smart Processing and Computing
• /
• v.3 no.4
• /
• pp.191-194
• /
• 2014

This paper proposes a fast and efficient method to extract the skin and bone automatically in CT images. First, the images were smoothed by applying an anisotropic diffusion filter to remove noise. The whole body was then detected by thresholding, which was set automatically. In addition, the contour of the skin was segmented using morphological operators and connected component labeling (CCL). Finally, the bone was extracted by iterative thresholding.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.39A no.12
• /
• pp.739-745
• /
• 2014

It has been shown in compressive sensing that every s-sparse $x{\in}R^N$ can be recovered from the measurement vector y=Ax or the noisy vector y=Ax+e via ${\ell}_1$-minimization as soon as the 3s-restricted isometry constant of the sensing matrix A is smaller than 1/2 or smaller than $1/\sqrt{3}$ by applying the Iterative Hard Thresholding (IHT) algorithm. However, recovery can be guaranteed by practical algorithms for some certain assumptions of acquisition schemes. One of the key assumption is that the sensing matrix must satisfy the Restricted Isometry Property (RIP), which is often violated in the setting of many practical applications. In this paper, we studied a generalization of RIP, called Restricted Biorthogonality Property (RBOP) for anisotropic cases, and the new recovery algorithms called oblique pursuits. Then, we provide an analysis on the success of sparse recovery in terms of restricted biorthogonality constant for the IHT algorithms.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.1689-1694
• /
• 2005

Face detection plays an important role in face recognition, video surveillance, and human computer interface. In this paper, we present a face detection system using eye detection with progressive thresholding from a digital camera. The face candidate is detected by using skin color segmentation in the YCbCr color space. The face candidates are verified by detecting the eyes that is located by iterative thresholding and correlation coefficients. Preprocessing includes histogram equalization, log transformation, and gray-scale morphology for the emphasized eyes image. The distance of the eye candidate points generated by the progressive increasing threshold value is employed to extract the facial region. The process of the face detection is repeated by using the increasing threshold value. Experimental results show that more enhanced face detection in real time.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.402-404
• /
• 2003

We present two methods for the automatic selection of the threshold values in unsupervised change detection. Both methods consist of the same two procedures: 1) to determine the parameters of Gaussian mixtures from a difference image or ratio image, 2) to determine threshold values using the Bayesian rule for minimum error. In the first method, the Expectation-Maximization algorithm is applied for estimating the parameters of the Gaussian mixtures. The second method is based on the iterative thresholding that successively employs thresholding and estimation of the model parameters. The effectiveness and applicability of the methods proposed here are illustrated by an experiment on the multi-temporal KOMPAT-1 EOC images.

• ETRI Journal
• /
• v.37 no.6
• /
• pp.1251-1258
• /
• 2015

We investigate an image recovery method for sparse-view computed tomography (CT) using an iterative shrinkage algorithm based on a second-order approach. The two-step iterative shrinkage-thresholding (TwIST) algorithm including a total variation regularization technique is elucidated to be more robust than other first-order methods; it enables a perfect restoration of an original image even if given only a few projection views of a parallel-beam geometry. We find that the incoherency of a projection system matrix in CT geometry sufficiently satisfies the exact reconstruction principle even when the matrix itself has a large condition number. Image reconstruction from fan-beam CT can be well carried out, but the retrieval performance is very low when compared to a parallel-beam geometry. This is considered to be due to the matrix complexity of the projection geometry. We also evaluate the image retrieval performance of the TwIST algorithm -sing measured projection data.

• Journal of Korea Multimedia Society
• /
• v.19 no.2
• /
• pp.200-208
• /
• 2016

Compressed sensing is a signal processing technique for efficiently acquiring and reconstructing in an under-sampled (i.e., under Nyquist rate) representation. A block compressed sensing with projected Landweber (BCS-SPL) framework is most widely known, but, it has high computational complexity at decoder side. In this paper, by introducing adaptive exit criteria instead of fixed exit criteria to SPL framework, an effective fast algorithm is designed in such a way that it can utilize efficiently the sparsity property in DCT coefficients during the iterative thresholding process. Experimental results show that the proposed algorithm results in the significant reduction of the decoding time, while providing better visual qualities than conventional algorithm.

• The Journal of the Acoustical Society of Korea
• /
• v.42 no.4
• /
• pp.305-312
• /
• 2023

Physics-Informed Neural Network (PINN) is used to invert bubble size distributions from attenuation losses. By considering a linear system for the bubble population inversion, Adaptive Learned Iterative Shrinkage Thresholding Algorithm (Ada-LISTA), which has been solved linear systems in image processing, is used as a neural network architecture in PINN. Furthermore, a regularization based on the linear system is added to a loss function of PINN and it makes a PINN have better generalization by a solution satisfying the bubble physics. To evaluate an uncertainty of bubble estimation, deep ensemble is adopted. 20 Ada-LISTAs with different initial values are trained using the same training dataset. During test with attenuation losses different from those in the training dataset, the bubble size distribution and corresponding uncertainty are indicated by average and variance of 20 estimations, respectively. Deep ensemble Ada-LISTA demonstrate superior performance in inverting bubble size distributions than the conventional convex optimization solver of CVX.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.4
• /
• pp.173-180
• /
• 2014

Compressive sensing is a new signal acquisition paradigm that enables sparse/compressible signal to be sampled under the Nyquist-rate. To fully benefit from its much simplified acquisition process, huge efforts have been made on improving the performance of compressive sensing recovery. However, concerning color images, compressive sensing recovery lacks in addressing image characteristics like energy distribution or human visual system. In order to overcome the problem, this paper proposes a new group-sparsity hard thresholding process by preserving some RGB-grouped coefficients important in both terms of energy and perceptual sensitivity. Moreover, a smoothed group-sparsity iterative hard thresholding algorithm for compressive sensing of color images is proposed by incorporating a frame-based filter with group-sparsity hard thresholding process. In this way, our proposed method not only pursues sparsity of image in transform domain but also pursues smoothness of image in spatial domain. Experimental results show average PSNR gains up to 2.7dB over the state-of-the-art group-sparsity smoothed recovery method.

• Journal of International Society for Simulation Surgery
• /
• v.2 no.1
• /
• pp.33-39
• /
• 2015

Purpose The head of infants under 24 months old who has Craniosynostosis grows extraordinarily that makes head shape unusual. To diagnose the Craniosynostosis, surgeon has to inspect computed tomography(CT) images of the patient in person. It's very time consuming process. Moreover, without a surgeon, it's difficult to diagnose the Craniosynostosis. Therefore, we developed technique which detects Craniosynostosis automatically from the CT volume. Materials and Methods At first, rotation correction is performed to the 3D CT volume for detection of the Craniosynostosis. Then, cranial area is extracted using the iterative thresholding method we proposed. Lastly, we diagnose Craniosynostosis by analyzing centroid relationships of clusters of cranial bone which was divided by cranial suture. Results Using this automatical cranial detection technique, we can diagnose Craniosynostosis correctly. The proposed method resulted in 100% sensitivity and 90% specificity. The method perfectly diagnosed abnormal patients. Conclusion By plugging-in the software on CT machine, it will be able to warn the possibility of Craniosynostosis. It is expected that early treatment of Craniosynostosis would be possible with our proposed algorithm.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.36S no.12
• /
• pp.51-57
• /
• 1999

In this paper, an adaptive thresholding of the nonuniformly contrasted images is proposed through using the contrast pre-enhancement of the local regions and the bilinear interpolation between the local threshold values. The nonuniformly contrasted image is decomposed into 9${\times}$9 sized local regions, and the contrast is enhanced by intensifying the gray level difference of each low contrasted or blurred region. Optimal threshold values are obtained by iterative method from the gray level distribution of each contrast-enhanced local region. Discontinuities are reduced at the region of interest or at the characters by using bilinear interpolation between the neighboring threshold surfaces. Character recognition experiments are conducted using backpropagation neural network on the characters extracted from the nonuniformly contrasted document, PCB, and wafer images binarized through using the proposed thresholding and the conventional thresholding methods, and the results prove the relative effectiveness of the proposed scheme.