• Journal of the Korea Institute of Military Science and Technology
• /
• v.13 no.3
• /
• pp.445-452
• /
• 2010

Adequate segmentation of target objects from the background plays an important role for the performance of automatic target recognition(ATR) system. This paper presents a new segmentation algorithm using fuzzy thresholding to extract a target. The proposed algorithm consists of two steps. In the first step, the region of interest(ROI) including the target can be automatically selected by the proposed robust method based on the frame difference of each image sensor. In the second step, fuzzy thresholding with a proposed membership function is performed within the only ROI selected in the first step. The proposed membership function is based on the similarity of intensity and the adjacency of target area on each image. Experimental results applied to real CCD/IR images show a good performance and the proposed algorithm is expected to enhance the performance of ATR system using multi-sensors.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.363-365
• /
• 2003

This paper presents an object oriented approach(OOA) for classification of multi-channel and multi-polarization NASA/JPL POLSAR images. Some test results in Taiwan are also given and analyzed. It is concluded that this approach can utilize as more information of both low- and high-levels involved in all images as possible for image classification and thus provides a better classification accuracy. For instance, the OOA has a better overall classification accuracy(98.27%) than the nearest-neighbor classifier(91.31%) and minimum-distance classifier(80.52%).

• Journal of Korea Multimedia Society
• /
• v.21 no.12
• /
• pp.1467-1472
• /
• 2018

For the problem that the face image of surveillance video cannot be accurately identified due to the low resolution, this paper proposes a low resolution face recognition solution based on convolutional neural network model. Convolutional Neural Networks (CNN) model for multi-scale input The CNN model for multi-scale input is an improvement over the existing "two-step method" in which low-resolution images are up-sampled using a simple bi-cubic interpolation method. Then, the up sampled image and the high-resolution image are mixed as a model training sample. The CNN model learns the common feature space of the high- and low-resolution images, and then measures the feature similarity through the cosine distance. Finally, the recognition result is given. The experiments on the CMU PIE and Extended Yale B datasets show that the accuracy of the model is better than other comparison methods. Compared with the CMDA_BGE algorithm with the highest recognition rate, the accuracy rate is 2.5%~9.9%.

• 제어로봇시스템학회:학술대회논문집
• /
• 1997.10a
• /
• pp.828-831
• /
• 1997

One of the most important design factor for the image tracker is the speed of the data processing which allows real-time operation of the system and provides reasonably accurate performance at the same time. Use of powerful DSP alone does not guarantee to meet such requirement. In this paper, a simple efficient algorithm for real-time multi-target image tracking is suggested. The suggested method is based on a recursive centroiding technique and color table look-up. This method has been successfully implemented in a image processing system for Micro-Robot Soccer Tournament(MIROSOT). This tracker can track positions of a ball, 3 enemies, and 3 agents at the same time. The experimental results show that the processing time for each frame of image is less than 7ms, which is well within the 60Hz sampling interval for real-time operation.

• Proceedings of the KSRS Conference
• /
• v.2
• /
• pp.780-783
• /
• 2006

The KOrea Multi-Purpose Satellite-2 (KOMPSAT-2) was launched in July 2006 and the main mission of the KOMPSAT-2 is a high resolution imaging for the cartography of Korea peninsula by utilizing Multi Spectral Camera (MSC) images. The camera resolutions are 1 m in panchromatic scene and 4 m in multi-spectral imaging. This paper provides an initial geometric accuracy assessment of the KOMPSAT-2 high resolution image without ground control points and briefly introduces the sensor model of KOMPSAT-2. Also investigated and evaluated the obtained 3-dimensional terrain information using the MSC pass image and scene images acquired from the KOMPSAT-2 satellite.

• International Journal of Advanced Culture Technology
• /
• v.6 no.3
• /
• pp.142-150
• /
• 2018

This paper describes the algorithm that lowers the dimension, maintains the object recognition and significantly reduces the eigenspace configuration time by combining the edge orientation histogram and principle component analysis. By using the detected object region as a recognition input image, in this paper the object recognition method combined with principle component analysis and the multi-layer network which is one of the intelligent classification was suggested and its performance was evaluated. As a pre-processing algorithm of input object image, this method computes the eigenspace through principle component analysis and expresses the training images with it as a fundamental vector. Each image takes the set of weights for the fundamental vector as a feature vector and it reduces the dimension of image at the same time, and then the object recognition is performed by inputting the multi-layer neural network.

• Textile Coloration and Finishing
• /
• v.21 no.1
• /
• pp.53-58
• /
• 2009

A real-time inspection system has been developed by combining CCD based image processing algorithm and a standard lighting equipment. The system was tested for defective fabrics showing nozzle contact scratch marks, which were one of the frequently occurring defects. Multi-resolution analysis(MRA) algorithm were used and evaluated according to both their processing time and detection rate. Standard value for defective inspection was the mean of the non-defect image feature. Similarity was decided via comparing standard value with sample image feature value. Totally, we achieved defective inspection accuracy above 95%.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.33B no.10
• /
• pp.38-49
• /
• 1996

In this paper, we propose a fast hierarchical image segmentation using mathematical morphology. The proposed segmentation method is composed of five basic steps; multi-thresholding, open-close by reconstructing, mode operation, marker extraction, and region decision. In the multi-thresholding, an input image is simplified by Lloyd clustering algorithm. The multi-thresholded image then is more simplified by open-close by reconstruction and mode operating. In the region decision, to which region each uncertainty pixel belongs finally is decided by a watershed algorithm. Experimental results show that the quality of the segmentation results by the proposed method is not inferior to that by the conventional method and the average times elapsed by the proposed method can be reduced by one tghird of those elapsed by the conventional method.

• Journal of Korea Multimedia Society
• /
• v.22 no.10
• /
• pp.1149-1159
• /
• 2019

We present a novel deep learning architecture for obtaining a latent image from a single blurry image, which contains dynamic motion blurs through object/camera movements. The proposed architecture consists of two sub-modules: blur image restoration and optical flow estimation. The tasks are highly related in that object/camera movements make cause blurry artifacts, whereas they are estimated through optical flow. The ablation study demonstrates that training multi-task architecture simultaneously improves both tasks compared to handling them separately. Objective and subjective evaluations show that our method outperforms the state-of-the-arts deep learning based techniques.

• Journal of The Korean Astronomical Society
• /
• v.52 no.2
• /
• pp.49-55
• /
• 2019

The New Vacuum Solar Telescope (NVST) is the largest solar telescope in China. When using CCDs for imaging, equal-thickness fringes caused by thin-film interference can occur. Such fringes reduce the quality of NVST data but cannot be removed using standard flat fielding. In this paper, a correction method based on multi-scale decomposition and adaptive partitioning is proposed. The original image is decomposed into several sub-scales by multi-scale decomposition. The region containing fringes is found and divided by an adaptive partitioning method. The interference fringes are then filtered by a frequency-domain Gaussian filter on every partitioned image. Our analysis shows that this method can effectively remove the interference fringes from a solar image while preserving useful information.