• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.4
• /
• pp.1648-1672
• /
• 2020

There are several types of image registration in the sense of stitching separated images that overlap each other. One of these is feature-based registration by a common feature descriptor. In this study, we generate a mosaic of images using feature-based registration for drone aerial images. As a feature descriptor, we apply the scale-invariant feature transform descriptor. In order to investigate the authenticity of the feature points and to have the mapping function, we employ the sample consensus method; we consider the sensed image's inherent characteristic such as the geometric congruence between the feature points of the images to propose a novel hypothesis estimation of the mapping function of the stitching via some optimally chosen initial candidate inliers in the sample consensus method. Based on the experimental results, we show the efficiency of the proposed method compared with benchmark methodologies of random sampling consensus method (RANSAC); the well-ordering property defined in the context and the extensive stitching examples have supported the utility. Moreover, the sample consensus scheme proposed in this study is uncomplicated and robust, and some fatal miss stitching by RANSAC is remarkably reduced in the measure of the pixel difference.

• Journal of Korea Multimedia Society
• /
• v.14 no.2
• /
• pp.201-209
• /
• 2011

This paper suggests a panorama image stitching system which consists of an image matching algorithm: modified SURF (Speeded Up Robust Feature) and an image blending algorithm: multi-band blending. In this paper, first, Modified SURF is described and SURF is compared with SIFT (Scale Invariant Feature Transform), which also gives the reason why modified SURF is chosen instead of SIFT. Then, multi-band blending is described, Lastly, the structure of a panorama image stitching system is suggested and evaluated by experiments, which includes stitching quality test and time cost experiment. According to the experiments, the proposed system can make the stitching seam invisible and get a perfect panorama for large image data, In addition, it is faster than the sift based stitching system.

• Journal of Korea Multimedia Society
• /
• v.18 no.6
• /
• pp.701-709
• /
• 2015

Image stitching method is a technique for obtaining an high-resolution image by combining two or more images. In X-ray image for clinical diagnosis, the size of the imaging region taken by one shot is limited due to the field-of-view of the equipment. Therefore, in order to obtain a high-resolution image including large regions such as a whole body, the synthesis of multiple X-ray images is required. In this paper, we propose a rapid stitching method of digital X-ray images using template-based registration. The proposed algorithm use principal component analysis(PCA) and k-nearest neighborhood(k-NN) to determine the location of input images before performing a template-based matching. After detecting the overlapping position using template-based matching, we synthesize input images by alpha blending. To improve the computational efficiency, reduced images are used for PCA and k-NN analysis. Experimental results showed that our method was more accurate comparing with the previous method with the improvement of the registration speed. Our stitching method could be usefully applied into the stitching of 2D or 3D multiple images.

• Advanced Composite Materials
• /
• v.18 no.2
• /
• pp.121-134
• /
• 2009

The present study investigated, both experimentally and numerically, the improvement of low-velocity impact damage resistance of carbon fiber reinforced plastic (CFRP) laminates due to through-the-thickness stitching. First, we conducted drop-weight impact tests for stitched and unstitched laminates. The results of damage inspection confirmed that stitching did improve the impact damage resistance, and revealed that the improvement effect became greater as the impact energy increased. Moreover, the stitching affected the through-the-thickness damage distribution. Next, we performed FEM analysis and calculated the energy release rate of the delamination crack using the virtual crack closure technique (VCCT). The numerical results revealed that the stitching affected the through-the-thickness damage distribution because the stitch threads had a marked effect on decreasing both the modes I and II energy release rate around the bottom of the laminate. Comparison of the results for models that contained delaminations of various sizes revealed that the energy release rate became lower as delamination size increased; therefore the stitching improved the impact resistance more effectively when the impact energy was higher.

• Composites Research
• /
• v.32 no.2
• /
• pp.102-107
• /
• 2019

Several studies related to reinforce composites structures in the through thickness direction have been developed along the years. As follows, in this study a new reinforced process is proposed based on previous experimental results using a novel stitching process in T-joints and one-stitched specimens. It was established the need to perform more analysis under standard test methods to obtain a better understanding. FEM analysis were compared after performed mode I interlaminar fracture toughness test, using different stitching patterns to analyze the through thickness strength with reference laminates without stitching. The stitching patterns were defined in $2{\times}2$ and $3{\times}3$, where the upper and lower head of the non-continuous stitching process (I-Fiber) has proven to influence in a higher through thickness strength of the laminate. In order to design the numerical model, cohesive parameters were required to define the surface to surface bonding elements using the cohesive zone method (CZM) and simulate the crack opening behavior from the double cantilever beam (DCB) test.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.47 no.6
• /
• pp.977-995
• /
• 2023

This study was aimed at determining the connection between ancient Korean embroidery and the Cheonsuguk mandala-embroidery insignia. Literature and empirical studies were conducted simultaneously, with the scope of these analyses spanning up to 7C in ancient Korea and Japan. The present study confirmed that the structure of Goguryeo tomb murals influenced by Buddhist art is represented in the Cheonsuguk mandala-embroidery insignia, and changes in the image resulted in modifications to the embroidery technique. Embroidery and color composition via complementary color contrast were implemented through Variant 1 outline stitching, which exhibited the development of Baekje embroidery. The embroidery technique confirmed that the form of embroidery developed in to chain stitching, needle looping stitching, outline stitching, satin stitching and Variant 1·2 outline stitching. These findings indicate that Cheonsuguk mandala-embroidery insignia is the result of the integration of the Goguryeo and Baekje cultures.

• Journal of Digital Convergence
• /
• v.16 no.2
• /
• pp.335-341
• /
• 2018

This study is a study on effective stitching technique for video recorded by using a dual-lens $360^{\circ}$ camera composed of two fisheye lenses. First of all, this study located a problem in the result of stitching by using a bundled program. And the study was carried out, focusing on looking for a stitching technique more efficient and closer to perfect by comparatively analyzing the results of stitching by using Autopano Video Pro and Autopano Giga, professional stitching program. As a result, it was shown that the problems of bundled program were horizontal and vertical distortion, exposure and color mismatch and unsmooth stitching line. And it was possible to solve the problem of the horizontal and vertical by using Automatic Horizon and Verticals Tool of Autopano Video Pro and Autopano Giga, problem of exposure and color by using Levels, Color and Edit Color Anchors and problem of stitching line by using Mask function. Based on this study, it is to be hoped that $360^{\circ}$ VR video content closer to perfect can be produced by efficient stitching technique for video recorded by using dual-lens $360^{\circ}$ camera in the future.

• The KIPS Transactions:PartB
• /
• v.19B no.2
• /
• pp.93-98
• /
• 2012

Recently, we can easily create high resolution images with digital cameras for high-performance and make use them at variety fields. Especially, the image stitching method which adjusts couple of images has been researched. Image stitching can be used for military purposes such as satellites and reconnaissance aircraft, and computer vision such as medical image and the map. In this paper, we have proposed fast image stitching based on improved SURF algorithm using meaningful features in the process of images matching after extracting features from scenery image. The features are extracted in each image to find out corresponding points. At this time, the meaningful features can be searched by removing the error, such as noise, in extracted features. And these features are used for corresponding points on image matching. The total processing time of image stitching is improved due to the reduced time in searching out corresponding points. In our results, the processing time of feature matching and image stitching is faster than previous algorithms, and also that method can make natural-looking stitched image.

• Journal of the Korean Home Economics Association
• /
• v.9 no.2
• /
• pp.40-47
• /
• 1971

The purpose of this study was to examine the effects of several methods of the patching on the strength of the seam-texture. The main findings warranted from the present study were as follows : 1. The breaking strength was increased in proportion to the number of stitches in the case of 5 stitches per cm and 7 stitches per cm, not in the case of 9 stitches per cm where the tendency to damage the texture stitches appeared because of the excessive. 2. In comparing the effects of three methods (1. attaching a single patch, 2. attaching a single patch and seaming, 3. attaching several ply patch), no significant difference was found among these three. 3. There was a significant difference between the effects of two methods (1. attaching a single patch and stitching one edge of it on one side of the seam, 2. attaching a single patch and stitching both edges of it on the both sides of seam). In other words, the latter was found to be significantly more effective than the former. 4. In the case of unbalanced texture 9for example, single to two ply, single ply to two ply, or single to three ply), attaching a single patch to single ply and stitching both edges of it, and attaching a single patch to cover the plain-seam and stitching both edges of it, were more effective than attaching a single patch without stitching. 5. In comparing the effects of stitching both edges of the patch in 4 stitches per cm by the machine and by the hand, no significant difference was found. But these were more effective than stitching its both edges in 2 stitches per cm by hand. 6. The plain-seam stitched one edge of patch in 2 stitches per cm by machine and other by hand was significantly stronger than the plain-seam without a patch or with patch not stitched.

• ETRI Journal
• /
• v.37 no.6
• /
• pp.1143-1153
• /
• 2015

In this paper, we propose an efficient architecture for a real-time image stitching engine for vision SoCs found in motor vehicles. To enlarge the obstacle-detection distance and area for safety, we adopt panoramic images from multiple telegraphic cameras. We propose a stitching method based on a fixed homography that is educed from the initial frame of a video sequence and is used to warp all input images without regeneration. Because the fixed homography is generated only once at the initial state, we can calculate it using SW to reduce HW costs. The proposed warping HW engine is based on a linear transform of the pixel positions of warped images and can reduce the computational complexity by 90% or more as compared to a conventional method. A dual-core SW/HW image stitching engine is applied to stitching input frames in parallel to improve the performance by 70% or more as compared to a single-core engine operation. In addition, a dual-core structure is used to detect a failure in state machines using rock-step logic to satisfy the ISO26262 standard. The dual-core SW/HW image stitching engine is fabricated in SoC with 254,968 gate counts using Global Foundry's 65 nm CMOS process. The single-core engine can make panoramic images from three YCbCr 4:2:0 formatted VGA images at 44 frames per second and frequency of 200 MHz without an LCD display.