• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 1997.11a
• /
• pp.145-149
• /
• 1997

In this paper, a hierarchical spatio-temporal image segmentation method based on binary split algorithm is proposed. Intensity and displacement vector at each pixel are used for image segmentation. The displacement vectors between two image frames which skip over one or several frames can be approximated by accumulating of the velocity vectors calculated from optical flow between two successive frames when the time interval between the two image frames is short enough or the motion is slow. The pixels whose displacement vector and intensity are ambiguous are precisely decided by the modified watershed algorithm using the proposed priority measure. In the experiment, the region of moving object is precisely segmented.

• The Transactions of the Korean Institute of Electrical Engineers A
• /
• v.48 no.8
• /
• pp.1031-1036
• /
• 1999

A Hierarchical vector Quantization scheme is implemented and an optimal thresholding technique of quadtree segmentation for performing high quality low bit rate image compression is proposes. A mathematical model is constructed under the assumption that the standard deviations of sub-blocks are larger than or equal to the standard deviation of the upper level block which is generated by merging of sub-blocks. This thresholding technique based on the mathematical modeling allows producing about 1 dB improved performance in terms of PSNR at most ranges of bit rates over the quadtree coder, which is based on MSE for quadtree segmentation.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.862-864
• /
• 2003

Thresholding is a popular image segmentation method that converts a gray-level image into a binary image. The selection of optimum threshold has remained a challenge over decades. Many image segmentation techniques are developed using information about image in other space rather than the image space itself. Most of the technique based on histogram analysis information-theoretic approaches. In this paper, the criterion function for finding optimal threshold is developed using an intensity-based classuncertainty (a histogram-based property of an image) and region-homogeneity (an image morphology-based property). The theory of the optimum thresholding method is based on postulates that objects manifest themselves with fuzzy boundaries in any digital image acquired by an imaging device. The performance of the proposed method is illustrated on experimental data obtained by W-band millimeter-wave radiometer image under different noise level.

• Smart Structures and Systems
• /
• v.32 no.2
• /
• pp.111-121
• /
• 2023

This study proposes an automated assembly performance evaluation method for prefabricated steel structures (PSSs) using machine learning methods. Assembly component images were segmented using a modified version of the receptive field pyramid. By factorizing channel modulation and the receptive field exploration layers of the convolution pyramid, highly accurate segmentation results were obtained. After completing segmentation, the positions of the bolt holes were calculated using various image processing techniques, such as fuzzy-based edge detection, Hough's line detection, and image perspective transformation. By calculating the distance ratio between bolt holes, the assembly performance of the PSS was estimated using the k-nearest neighbors (kNN) algorithm. The effectiveness of the proposed framework was validated using a 3D PSS printing model and a field test. The results indicated that this approach could recognize assembly components with an intersection over union (IoU) of 95% and evaluate assembly performance with an error of less than 5%.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.8 no.8
• /
• pp.2881-2894
• /
• 2014

In complicated environment, context information plays an important role in image segmentation/labeling. The recently proposed auto-context algorithm is one of the effective context-based methods. However, the standard auto-context approach samples the context locations utilizing a fixed radius sequence, which is sensitive to large scale-change of objects. In this paper, we present a scale invariant auto-context (SIAC) algorithm which is an improved version of the auto-context algorithm. In order to achieve scale-invariance, we try to approximate the optimal scale for the image in an iterative way and adopt the corresponding optimal radius sequence for context location sampling, both in training and testing. In each iteration of the proposed SIAC algorithm, we use the current classification map to estimate the image scale, and the corresponding radius sequence is then used for choosing context locations. The algorithm iteratively updates the classification maps, as well as the image scales, until convergence. We demonstrate the SIAC algorithm on several image segmentation/labeling tasks. The results demonstrate improvement over the standard auto-context algorithm when large scale-change of objects exists.

• The Transactions of the Korea Information Processing Society
• /
• v.7 no.9
• /
• pp.2994-3001
• /
• 2000

In this paper. a method for color image segmentation using region merging is proposed. A inhomogeneity which exists in image is reduced by smoothing with non-linear filtering. saturation enhancement and intensity averaging in previous step of image segmentation. and a similar regions are segmented by non-uniform quantization using zero-crossing information of color histogram. A edge strength of initial region is measured using high frequency energy of wavelet transform. A candidate region which is merged in next step is selected by doing this process. A similarity measure for region merging is processed using Euclidean distance of R. G. B color channels. A Proposed method can reduce an over-segmentation results by irregular light sources et. al, and we illustrated that the proposed method is reasonable by simulation.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2011.07a
• /
• pp.437-438
• /
• 2011

Spectral segmentation is a major trend in image segmentation. Specially, constrained spectral segmentation, inspired by the user-given inputs, remains its challenging task. Since it makes use of the spectrum of the affinity matrix of a given image, its overall quality depends mainly on how to design the graphical model. In this work, we propose a sparse, multi-layer graphical model, where the pixels and the over-segmented regions are the graph nodes. Here, the graph affinities are computed by using the must-link and cannot-link constraints as well as the likelihoods that each node has a specific label. They are then used to simultaneously cluster all pixels and regions into visually coherent groups across all layers in a single multi-layer framework of Normalized Cuts. Although we incorporate only the adjacent connections in the multi-layer graph, the foreground object can be efficiently extracted in the spectral framework. The experimental results demonstrate the relevance of our algorithm as compared to existing popular algorithms.

• The KIPS Transactions:PartB
• /
• v.18B no.4
• /
• pp.173-180
• /
• 2011

This paper shows an approach for real-time object segmentation on GPU (Graphics Processing Unit) using CUDA (Compute Unified Device Architecture). Recently, many applications that is monitoring system, motion analysis, object tracking or etc require real-time processing. It is not suitable for object segmentation to procedure real-time in CPU. NVIDIA provide CUDA platform for Parallel Processing for General Computation to upgrade limit of Hardware Graphic. In this paper, we use adaptive Gaussian Mixture Background Modeling in the step of object extraction and CCL(Connected Component Labeling) for classification. The speed of GPU and CPU is compared and evaluated with implementation in Core2 Quad processor with 2.4GHz.The GPU version achieved a speedup of 3x-4x over the CPU version.

• International Journal of Computer Science & Network Security
• /
• v.21 no.5
• /
• pp.1-8
• /
• 2021

Prostate cancer is one of the most diagnosed malignancies found across the world today. American cancer society in recent research predicted that over 174,600 new prostate cancer cases found and nearly 31,620 death cases recorded. Researchers are developing modest and accurate methodologies to detect and diagnose prostate cancer. Recent work has been done in radiology to detect prostate tumors using ultrasound imaging and resonance imaging techniques. Transrectal ultrasound and Magnetic resonance images of the prostate gland help in the detection of cancer in the prostate gland. The proposed paper is based on comparison and analysis between two novel image segmentation approaches. Seed region growing and cluster based image segmentation is used to extract the region from trans-rectal ultrasound prostate and MR prostate images. The region of extraction represents the abnormality area that presents in men's prostate gland. Detection of such abnormalities in the prostate gland helps in the identification and treatment of prostate cancer

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.221-235
• /
• 2022

Manual inspection of steel box girders on long span bridges is time-consuming and labor-intensive. The quality of inspection relies on the subjective judgements of the inspectors. This study proposes an automated approach to detect and segment cracks in high-resolution images. An end-to-end cascaded framework is proposed to first detect the existence of cracks using a deep convolutional neural network (CNN) and then segment the crack using a modified U-Net encoder-decoder architecture. A Naïve Bayes data fusion scheme is proposed to reduce the false positives and false negatives effectively. To generate the binary crack mask, first, the original images are divided into 448 × 448 overlapping image patches where these image patches are classified as cracks versus non-cracks using a deep CNN. Next, a modified U-Net is trained from scratch using only the crack patches for segmentation. A customized loss function that consists of binary cross entropy loss and the Dice loss is introduced to enhance the segmentation performance. Additionally, a Naïve Bayes fusion strategy is employed to integrate the crack score maps from different overlapping crack patches and to decide whether a pixel is crack or not. Comprehensive experiments have demonstrated that the proposed approach achieves an 81.71% mean intersection over union (mIoU) score across 5 different training/test splits, which is 7.29% higher than the baseline reference implemented with the original U-Net.