• The Journal of Korea Robotics Society
• /
• v.6 no.2
• /
• pp.118-129
• /
• 2011

In this paper, we suggest a new camera capturing and synthesizing algorithm with the multi-captured left and right images for the better comfortable feeling of 3D depth and also propose 3D image capturing hardware system based on the this new algorithm. We also suggest the simple control algorithm for the calibration of camera capture system with zooming function based on a performance index measure which is used as feedback information for the stabilization of focusing control problem. We also comment on the theoretical mapping theory concerning projection under the assumption that human is sitting 50cm in front of and watching the 3D LCD screen for the captured image based on the modeling of pinhole Camera. We choose 9 segmentations and propose the method to find optimal alignment and focusing based on the measure of alignment and sharpness and propose the synthesizing fusion with the optimized 9 segmentation images for the best 3D depth feeling.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.7
• /
• pp.1706-1725
• /
• 2024

The unique U-shaped structure of U-Net network makes it achieve good performance in image segmentation. This network is a lightweight network with a small number of parameters for small image segmentation datasets. However, when the medical image to be segmented contains a lot of detailed information, the segmentation results cannot fully meet the actual requirements. In order to achieve higher accuracy of medical image segmentation, a novel improved U-Net network architecture called multi-scale encoder-decoder U-Net+ (MEDU-Net+) is proposed in this paper. We design the GoogLeNet for achieving more information at the encoder of the proposed MEDU-Net+, and present the multi-scale feature extraction for fusing semantic information of different scales in the encoder and decoder. Meanwhile, we also introduce the layer-by-layer skip connection to connect the information of each layer, so that there is no need to encode the last layer and return the information. The proposed MEDU-Net+ divides the unknown depth network into each part of deconvolution layer to replace the direct connection of the encoder and decoder in U-Net. In addition, a new combined loss function is proposed to extract more edge information by combining the advantages of the generalized dice and the focal loss functions. Finally, we validate our proposed MEDU-Net+ MEDU-Net+ and other classic medical image segmentation networks on three medical image datasets. The experimental results show that our proposed MEDU-Net+ has prominent superior performance compared with other medical image segmentation networks.

• Journal of KIISE:Computer Systems and Theory
• /
• v.30 no.3_4
• /
• pp.138-148
• /
• 2003

Orthogonal Cross Cylinder mapping and segmentation based modeling methods have been implemented for constructing the image-based navigation system in this paper. The Orthogonal Cross Cylinder (OCC) is the object expressed by the intersection area that occurs when a cylinder is orthogonal with another. OCC mapping method eliminates the singularity effect caused in the environment maps and shows an almost even amount of area for the environment occupied by a single texel. A full-view image from a fixed point-of-view can be obtained with OCC mapping although it becomes difficult to express another image when the point-of-view has been changed. The OCC map is segmented according to the objects that form the environment and the depth value is set by the characteristics of the classified objects for the segmentation based modeling. This method can easily be implemented on an environment map and makes the environment modeling easier through extracting the depth value by the image segmentation. An environment navigation system with a full-view can be developed with these methods.

• Korean Journal of Optics and Photonics
• /
• v.20 no.2
• /
• pp.94-101
• /
• 2009

A novel method for the reconstruction of 3D shape and texture from elemental images has been proposed. Using this method, we can estimate a full 3D polygonal model of objects with seamless triangulation. But in the triangulation process, all the objects are stitched. This generates phantom surfaces that bridge depth discontinuities between different objects. To solve this problem we need to connect points only within a single object. We adopt a segmentation process to this end. The entire process of the proposed method is as follows. First, the central pixel of each elemental image is computed to extract spatial position of objects by correspondence analysis. Second, the object points of central pixels from neighboring elemental images are projected onto a specific elemental image. Then, the center sub-image is segmented and each object is labeled. We used the normalized cut algorithm for segmentation of the center sub-image. To enhance the speed of segmentation we applied the watershed algorithm before the normalized cut. Using the segmentation results, the subdivision process is applied to pixels only within the same objects. The refined grid is filtered with median and Gaussian filters to improve reconstruction quality. Finally, each vertex is connected and an object-based triangular mesh is formed. We conducted experiments using real objects and verified our proposed method.

• Journal of Computational Design and Engineering
• /
• v.3 no.3
• /
• pp.191-197
• /
• 2016

Since 3D measurement technologies have been widely used in manufacturing industries edge detection in a depth image plays an important role in computer vision applications. In this paper, we have proposed an edge detection process in a depth image based on the image based smoothing and morphological operations. In this method we have used the principle of Median filtering, which has a renowned feature for edge preservation properties. The edge detection was done based on Canny Edge detection principle and was improvised with morphological operations, which are represented as combinations of erosion and dilation. Later, we compared our results with some existing methods and exhibited that this method produced better results. However, this method works in multiframe applications with effective framerates. Thus this technique will aid to detect edges robustly from depth images and contribute to promote applications in depth images such as object detection, object segmentation, etc.

• Journal of the Korean Institute of Telematics and Electronics D
• /
• v.35D no.8
• /
• pp.76-81
• /
• 1998

This paper presents a new method to synthesize a digital hologram that meets the resolution of a currently manufactured LCD while capable of displaying a 3-D object. That is accomplished by segmenting a hologram, resulting in relaxed sampling constraint. We show that the segmentation of a hologram enables us to utilize the planewave approximation and, unlike in a holographic stereogram, it does not require projection process, but directly takes fourier transform of horizontally sliced 2-D images that constitute a 3-D object, which makes it possible to reconstruct a higher resolution image with depth information. We also show that proposed hologram contains data significantly smaller than the conventional hologram does, which is quite useful for constructing wide-viewing hologram. Finally, simulation results obtained by both methods are compared.

• International Journal of Contents
• /
• v.10 no.3
• /
• pp.9-16
• /
• 2014

Depth-image-based rendering is generally used in real-time 2D-to-3D conversion for 3DTV. However, inaccurate depth maps cause flickering issues between image frames in a video sequence, resulting in eye fatigue while viewing 3DTV. To resolve this flickering issue, we propose a new 2D-to-3D conversion scheme based on fast and robust depth-map generation from a 2D video sequence. The proposed depth-map generation algorithm divides an input video sequence into several cuts using a color histogram. The initial depth of each cut is assigned based on a hypothesized depth-gradient model. The initial depth map of the current frame is refined using color and motion information. Thereafter, the depth map of the next frame is updated using the difference image to reduce depth flickering. The experimental results confirm that the proposed scheme performs real-time 2D-to-3D conversions effectively and reduces human eye fatigue.

• Journal of Institute of Control, Robotics and Systems
• /
• v.18 no.12
• /
• pp.1115-1121
• /
• 2012

This paper proposes a method to extract accurate plane of an object in unstructured environment for a humanoid robot by using a laser scanner. By panning and tilting 2D laser scanner installed on the head of a humanoid robot, 3D depth map of unstructured environment is generated. After generating the 3D depth map around a robot, the proposed plane extraction method is applied to the 3D depth map. By using the hierarchical clustering method, points on the same plane are extracted from the point cloud in the 3D depth map. After segmenting the plane from the point cloud, dimensions of the planes are calculated. The accuracy of the extracted plane is evaluated with experimental results, which show the effectiveness of the proposed method to extract planes around a humanoid robot in unstructured environment.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.10 no.4
• /
• pp.674-679
• /
• 2006

In this paper a gesture recognition system using 3D feature data is described. The system relies on a novel 3D sensor that generates a dense range mage of the scene. The main novelty of the proposed system, with respect to other 3D gesture recognition techniques, is the capability for robust recognition of complex hand postures such as those encountered in sign language alphabets. This is achieved by explicitly employing 3D hand features. Moreover, the proposed approach does not rely on colour information, and guarantees robust segmentation of the hand under various illumination conditions, and content of the scene. Several novel 3D image analysis algorithms are presented covering the complete processing chain: 3D image acquisition, arm segmentation, hand -forearm segmentation, hand pose estimation, 3D feature extraction, and gesture classification. The proposed system is tested in an application scenario involving the recognition of sign-language postures.

• The Journal of Korean Institute of Information Technology
• /
• v.17 no.5
• /
• pp.77-82
• /
• 2019

Diabetic retinopathy is a complicated form of diabetes due to circulatory disorder in the peripheral blood vessels of the retina. We segment the microvessel for diagnosing diabetic retinophathy. The conventional methods using filter and features can segment the thick blood vessels, but it has relatively weak for segmenting fine blood vessels. In pre-processing step, noise reduction filter and histogram equalization are applied to suppress the noise and enhance the image contrast. Then, deep learning technique is used for pixel-by-pixel segmentation. The accuracy of conventional methods is between 90% to 94%, while the proposed method has improved as 95% accuracy. There is a problem of segmentation error around the optic disc and exudate due to the network depth. However the accuracy can be improved by modifying the network architecture in the future.