• Smart Media Journal
• /
• v.5 no.3
• /
• pp.30-34
• /
• 2016

Nowadays, there are a lot of Korean documents, which often need to be identified in one of printed or handwritten text. Early methods for the identification use structural features, which can be simple and easy to apply to text of a specific font, but its performance depends on the font type and characteristics of the text. Recently, the bag-of-words model has been used for the identification, which can be invariant to changes in font size, distortions or modifications to the text. The method based on bag-of-words model includes three steps: word segmentation using connected component grouping, feature extraction, and finally classification using SVM(Support Vector Machine). In this paper, bag-of-words model based method is proposed using SURF(Speeded Up Robust Feature) for the identification of machine printed and handwritten text in Korean documents. The experiment shows that the proposed method outperforms methods based on structural features.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2012.11a
• /
• pp.1468-1471
• /
• 2012

It is always a dream to recreate the experience of a particular place, the Panorama Virtual Reality has been interpreted as a kind of technology to create virtual environments and the ability to maneuver angle for and select the path of view in a dynamic scene. In this paper we examined an efficient algorithm for Image registration and stitching of captured imaged from a video stream. Two approaches are studied in this paper. First, dynamic programming is used to spot the ideal key points, match these points to merge adjacent images together, later image blending is use for smooth color transitions. In second approach, FAST and SURF detection are used to find distinct features in the images and a nearest neighbor algorithm is used to match corresponding features, estimate homography with matched key points using RANSAC. The paper also covers the automatically choosing (recognizing, comparing) images to stitching method.

• Journal of the Korean Society for Precision Engineering
• /
• v.30 no.2
• /
• pp.177-184
• /
• 2013

This paper proposes an enhanced Simultaneous Localization and Mapping (SLAM) algorithm based on matching laser image and Extended Kalman Filter (EKF). In general, laser information is one of the most efficient data for localization of mobile robots and is more accurate than encoder data. For localization of a mobile robot, moving distance information of a robot is often obtained by encoders and distance information from the robot to landmarks is estimated by various sensors. Though encoder has high resolution, it is difficult to estimate current position of a robot precisely because of encoder error caused by slip and backlash of wheels. In this paper, the position and angle of the robot are estimated by comparing laser images obtained from laser scanner with high accuracy. In addition, Speeded Up Robust Features (SURF) is used for extracting feature points at previous laser image and current laser image by comparing feature points. As a result, the moving distance and heading angle are obtained based on information of available points. The experimental results using the proposed laser slam algorithm show effectiveness for the SLAM of robot.

• Journal of the Semiconductor & Display Technology
• /
• v.15 no.4
• /
• pp.97-102
• /
• 2016

Image stitching is a process of combining two or more images with overlapping area to create a panorama of input images, which is considered as an active research area in computer vision, especially in the field of augmented reality with 360 degree images. Image stitching techniques can be categorized into two general approaches: direct and feature based techniques. Direct techniques compare all the pixel intensities of the images with each other, while feature based approaches aim to determine a relationship between the images through distinct features extracted from the images. This paper proposes a novel image stitching method based on feature pixels with approximated clustering filter. When the features are extracted from input images, we calculate a meaning of the minutiae, and apply an effective feature extraction algorithm to improve the processing time. With the evaluation of the results, the proposed method is corresponding accurate and effective, compared to the previous approaches.

• The Journal of the Convergence on Culture Technology
• /
• v.4 no.1
• /
• pp.291-297
• /
• 2018

In this paper, we present an automatic image object tracking system for Studio cameras on the stage. For object tracking, we use the OpenCV-based Python program using PC, Raspberry Pi 3 and mobile devices. There are many methods of image object tracking such as mean-shift, CAMshift (Continuously Adaptive Mean shift), background modelling using GMM(Gaussian mixture model), template based detection using SURF(Speeded up robust features), CMT(Consensus-based Matching and Tracking) and TLD methods. CAMshift algorithm is very efficient for real-time tracking because of its fast and robust performance. However, in this paper, we implement an image object tracking system for studio cameras based CMT algorithm. This is an optimal image tracking method because of combination of static and adaptive correspondences. The proposed system can be applied to an effective and robust image tracking system for continuous object tracking on the stage in real time.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.38 no.5
• /
• pp.477-486
• /
• 2020

Drone has been widely used for many applications ranging from amateur and leisure to professionals to get fast and accurate 3-D information of the surface of the interest. Most of commercial softwares developed for this purpose are performing automatic matching based on SIFT (Scale Invariant Feature Transform) or SURF (Speeded-Up Robust Features) using nadir-looking stereo image sets. Since, there are some situations where not only nadir and nadir-looking matching, but also nadir and oblique-looking matching is needed, the existing software for the latter case could not get good results. In this study, a matching experiment was performed to utilize images with differences in geometry. Nadir and oblique-looking images were acquired through drone for a total of 2 times. SIFT, SURF, which are feature point-based, and IMAS (Image Matching by Affine Simulation) matching techniques based on affine transformation were applied. The experiment was classified according to the identity of the geometry, and the presence or absence of a building was considered. Images with the same geometry could be matched through three matching techniques. However, for image sets with different geometry, only the IMAS method was successful with and without building areas. It was found that when performing matching for use of images with different geometry, the affine transformation-based matching technique should be applied.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.11
• /
• pp.173-182
• /
• 2021

In this paper, we analyzed driver's and passenger's motions that cause driver's distraction, and recognized 10 driver's behaviors related to mobile phones. First, distraction-inducing behaviors were classified into environments and factors, and related recent papers were analyzed. Based on the analyzed papers, 10 driver's behaviors related to cell phones, which are the main causes of distraction, were recognized. The experiment was conducted based on about 100,000 image data. Features were extracted through SURF and tested with three models (CNN, ResNet-101, and improved ResNet-101). The improved ResNet-101 model reduced training and validation errors by 8.2 times and 44.6 times compared to CNN, and the average precision and f1-score were maintained at a high level of 0.98. In addition, using CAM (class activation maps), it was reviewed whether the deep learning model used the cell phone object and location as the decisive cause when judging the driver's distraction behavior.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.9
• /
• pp.49-55
• /
• 2019

This paper presents a marker image evaluation method based on analysis of object distribution in images and classification of images with repetitive patterns for effective marker-based augmented reality (AR) system development. We measure the variance of feature point coordinates to distinguish marker images that are vulnerable to occlusion, since object distribution affects object tracking performance according to partial occlusion in the images. Moreover, we propose a method to classify images suitable for object recognition and tracking based on the fact that the distributions of descriptor vectors among general images and repetitive-pattern images are significantly different. Comprehensive experiments for marker images confirm that the proposed marker image evaluation method distinguishes images vulnerable to occlusion and repetitive-pattern images very well. Furthermore, we suggest that scale-invariant feature transform (SIFT) is superior to speeded up robust features (SURF) in terms of object tracking in marker images. The proposed method provides users with suitability information for various images, and it helps AR systems to be realized more effectively.

• Korean Journal of Remote Sensing
• /
• v.37 no.5_1
• /
• pp.1135-1147
• /
• 2021

In order to geometrically correct high-resolution satellite imagery, the sensor modeling process that restores the geometric relationship between the satellite sensor and the ground surface at the image acquisition time is required. In general, high-resolution satellites provide RPC (Rational Polynomial Coefficient) information, but the vendor-provided RPC includes geometric distortion caused by the position and orientation of the satellite sensor. GCP (Ground Control Point) is generally used to correct the RPC errors. The representative method of acquiring GCP is field survey to obtain accurate ground coordinates. However, it is difficult to find the GCP in the satellite image due to the quality of the image, land cover change, relief displacement, etc. By using image maps acquired from various sensors as reference data, it is possible to automate the collection of GCP through the image matching algorithm. In this study, the RPC of KOMPSAT-3A satellite image was corrected through the extracted matching point using the UAV (Unmanned Aerial Vehichle) imagery. We propose a pre-porocessing method for the extraction of matching points between the UAV imagery and KOMPSAT-3A satellite image. To this end, the characteristics of matching points extracted by independently applying the SURF (Speeded-Up Robust Features) and the phase correlation, which are representative feature-based matching method and area-based matching method, respectively, were compared. The RPC adjustment parameters were calculated using the matching points extracted through each algorithm. In order to verify the performance and usability of the proposed method, it was compared with the GCP-based RPC correction result. The GCP-based method showed an improvement of correction accuracy by 2.14 pixels for the sample and 5.43 pixelsfor the line compared to the vendor-provided RPC. In the proposed method using SURF and phase correlation methods, the accuracy of sample was improved by 0.83 pixels and 1.49 pixels, and that of line wasimproved by 4.81 pixels and 5.19 pixels, respectively, compared to the vendor-provided RPC. Through the experimental results, the proposed method using the UAV imagery presented the possibility as an alternative to the GCP-based method for the RPC correction.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.7 no.7
• /
• pp.1690-1704
• /
• 2013

An affine invariant descriptor is proposed, which is able to well represent the affine covariant regions. Estimating main orientation is still problematic in many existing method, such as SIFT (scale invariant feature transform) and SURF (speeded up robust features). Instead of aligning the estimated main orientation, in this paper ellipse orientation is directly used. According to ellipse orientation, affine covariant regions are firstly divided into 4 sub-regions with equal angles. Since affine covariant regions are divided from the ellipse orientation, the divided sub-regions are rotation invariant regardless the rotation, if any, of ellipse. Meanwhile, the affine covariant regions are normalized into a circular region. In the end, the gradients of pixels in the circular region are calculated and the partition-based descriptor is created by using the gradients. Compared with the existing descriptors including MROGH, SIFT, GLOH, PCA-SIFT and spin images, the proposed descriptor demonstrates superior performance according to extensive experiments.