• Korean Journal of Remote Sensing
• /
• v.32 no.6
• /
• pp.647-656
• /
• 2016

Growth of UAV technology leads to expansion of UAV image applications. Many UAV image-based applications use a method called incremental bundle adjustment. However, incremental bundle adjustment produces large computation overhead because it attempts feature matching from all image pairs. For efficient feature matching process we have to confine matching only for overlapping pairs using exterior orientation parameters. When exterior orientation parameters are not available, we cannot determine overlapping pairs. We need another methods for feature matching candidate constitution. In this paper we compare matching candidate constitution methods without exterior orientation parameters, including partial feature matching, Bag-of-keypoints, image intensity method. We use the overlapping pair determination method based on exterior orientation parameter as reference. Experiment results showed the partial feature matching method in the one with best efficiency.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.11 no.6
• /
• pp.1162-1169
• /
• 2007

In this paper, we proposed a container identifier recognition method for containers used in harbors. After converting a real container image to a gray image, edges are detected from the gray image applying Prewitt mask and candidate identifier area is extracted using morphological features of individual identifier for identifying containers. Because noises are included in the extracted candidate identifier area, noises are eliminated and each identifier is separated using 4-directional edge tracking algorithm and Grassfire algorithm. Each identifier in the noise-free candidate identifier area is recognized using FCM-based row RBF network for discriminating containers. We used 300 real container images for experiment to evaluate the performance of the proposed method, and we could verify the proposed method is better than a conventional method.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.45 no.2
• /
• pp.8-17
• /
• 2008

This paper proposes a robust license plate extraction method from images taken under unconstrained environments. Utilization of the color and the edge information in complementary fashion makes the proposed method deal with not only various lighting conditions, hilt blocking artifacts frequently observed in compressed images. Computational complexity is significantly reduced by applying Hough transform to estimate the skew angle, and subsequent do-skewing procedure only to the candidate regions. The true plate region is determined from the candidates under examination using clues including the aspect ratio, the number of zero crossings from vertical scan lines, and the number of connected components. The performance of the proposed method is evaluated using compressed images collected under various realistic circumstances. The experimental results show 94.9% of correct license plate extraction rate.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.4
• /
• pp.45-50
• /
• 2004

In this paper, we propose a new PCA-based LDA Mixture Algorithm(PLMA) for real-time face recognition system. This system greatly consists of the two parts: 1) face extraction part; 2) face recognition part. In the face extraction part we applied subtraction image, color filtering, eyes and mouth region detection, and normalization method, and in the face recognition part we used the method mixing PCA and LDA in extracted face candidate region images. The existing recognition system using only PCA showed low recognition rates, and it is hard in the recognition system using only LDA to apply LDA to the input images as it is when the number of image pixels ire small as compared with the training set. To overcome these shortcomings, we reduced dimension as we apply PCA to the normalized images, and apply LDA to the compressed images, therefore it is possible for us to do real-time recognition, and we are also capable of improving recognition rates. We have experimented using self-organized DAUface database to evaluate the performance of the proposed system. The experimental results show that the proposed method outperform PCA, LDA and ICA method within the framework of recognition accuracy.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.26 no.12A
• /
• pp.2019-2026
• /
• 2001

In this paper, we proposed the car license plate extraction and recognition algorithm using both the dynamical thresholding method and the kohonen algorithm. In general, the areas of car license plate in the car images have distinguishing characteristics, such as the differences in intensity between the areas of characters and the background of the plates, the fixed ratio of width to height of the plates, and the higher dynamical thresholded density rate 7han the other areas, etc. Taking advantage of the characteristics, the thresholded images were created from the original images, and also the density rates were computed. A candidate area was selected, whose density rate was corresponding to the properties of the car license plate obtained from the car license plate. The contour tracking method by utilizing the Kohonen algorithm was applied to extract the specific area which included characters and numbers from an extracted plate area. The characters and numbers of the license place were recognized by using Kohonen algorithm. Kohonen algorithm was very effective o? suppressing noises scattered around the contour. In this study, 80 car images were tested. The result indicate that we proposed is superior in performance.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.36 no.9C
• /
• pp.546-554
• /
• 2011

Near targets in the infrared (IR) images have the steady feature for inner region and the transient feature for the boundary region. Based on these features, this paper proposes a new method to extract the fine target shape of near targets in the IR images. First, we detect the boundary region of the candidate targets using the local variance weighted information entropy (WIE) of the original images. And then, a coarse target region can be estimated based on the labeling of the boundary region. For the coarse target region, we use the opening filter with an adaptive structure element to extract the fine target shape. The decision of the adaptive structure element size is optimized for the width information of target boundary by calculating the average WIE in the enlarged windows. The experimental results show that a proposed method has better extraction performance than the previous threshold algorithms.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.24 no.5
• /
• pp.409-416
• /
• 2006

To use image data obtained from different sensors and different techniques, the preprocessing step that registers them in a common coordinate system is needed. For this purpose, we developed the methodology to register middle- and low-resolution satellite images automatically. Firstly, candidate matching points were extracted using the Harris and Harris-affine algorithm. Secondly, we used the correlation coefficient, normalized correlation coefficient and SIFT algorithm to detect conjugate matching points from candidates. Then, to test the feasibility of approaches, we applied the developed methodology to various kinds of satellite images and compared results. The results clearly demonstrate that the methology using the SIFT is appropriate to register these multi-resolution satellite images automatically, compared with the classical cross-correlation.

• Journal of Internet Computing and Services
• /
• v.10 no.5
• /
• pp.183-194
• /
• 2009

In this paper, we propose a new method for detecting objectionable images with an active shape model. Our method first learns the shape of breast lines through principle component analysis and alignment as well as the distribution of intensity values of corresponding landmarks, and then extracts breast lines with the learned shape and intensity distribution. To accurately select the initial position of active shape model, we obtain parameters on scale, rotation, and translation. After positioning the initial location of active shape model using scale and rotation information, iterative searches are performed. We can identify adult images by calculating the average of the distance between each landmark and a candidate breast line. The experiment results show that the proposed method can detect adult images effectively by comparing various results.

• Journal of the Korean Society for Marine Environment & Energy
• /
• v.2 no.2
• /
• pp.38-48
• /
• 1999

The oil spill accident near Goeje Island on April 3, 1997 was analyzed using two RADARSAT SAR images. The first scene was acquired 3 days after the accident as an extended low beam mode and the second scene was acquired 12 hours after the first scene as a standard beam mode. The two scenes showed slicks not only by oil spills but also by oil spill look-alikes caused by wind sheltering, low wind, natural film, and etc. These slicks were analyzed and classified, and natural films produced from aquaculture farms around Goeje Island were also suggested as a strong candidate for slicks on SAR images. The study with two SAR imags indicated the oil spill patterns which spreaded to the southwest immediately after the accident and switched the direction to the east. The spreading patterns shown in two SAR images also showed good agreement with in-situ observations.

• Spatial Information Research
• /
• v.16 no.2
• /
• pp.193-206
• /
• 2008

If stereo images is used for Digital Elevation Model (DEM) generation, a DEM is generally made by matching left image against right image from stereo images. In stereo matching, tie-points are used as initial match candidate points. The number and distribution of tie-points influence the matching result. DEM made from matching result has errors such as holes, peaks, etc. These errors are usually interpolated by neighbored pixel values. In this paper, we propose the DEM generation method combined with automatic tie-points extraction using existing DEM, image pyramid, and interpolating new DEM using existing DEM for more reliable DEM. For test, we used IKONOS, QuickBird, SPOT5 stereo images and a DTED level 2 data. The test results show that the proposed method automatically makes reliable DEMs. For DEM validation, we compared heights of DEM by proposed method with height of existing DTED level 2 data. In comparison result, RMSE was under than 15 m.