• Journal of Korea Multimedia Society
• /
• v.22 no.8
• /
• pp.844-851
• /
• 2019

In this paper, we propose a loss function in CNN that introduces inter-class amplitudes to increase inter-class loss and reduce intra-class loss to increase of face recognition performance. This loss function increases the distance between the classes and decreases the distance in the class, thereby improving the performance of the face recognition finally. It is confirmed that the accuracy of face recognition for visible light image of proposed loss function is 99.62%, which is better than other loss functions. We also applied it to face recognition of visible and near-infrared complex images to obtain satisfactory results of 99.76%.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.53 no.5
• /
• pp.123-131
• /
• 2016

To capture color and near-infrared images simultaneously, a multi-spectral filter array(MSFA) sensor is used. This is because an NIR band gives additional invisible information to human eyes to see subject under extremely low light level. However, because lenses have different refractive indices for different wavelengths, lenses may fail to focus widely different rays to the same convergence point. This is why a chromatic aberration(CA) problem occurs and images are degraded. In this paper, the image restoration algorithm for an MSFA image, which removes the CA problem, is presented. The obtained MSFA image is filtered by the estimated low-pass kernel to generate a base image. This base image is used to remove CA problem in multi-spectral(MS) images. By modeling the image degradation process and by using the least squares approach of the difference between the high-frequencies of the base and MS images, the desired high-resolution MS images are reconstructed. The experimental results show that the proposed algorithm performs well in estimating the high-quality MS images and reducing the chromatic aberration problem.

• Journal of Korean Society for Geospatial Information Science
• /
• v.23 no.1
• /
• pp.81-88
• /
• 2015

Various satellite sensors having ranges of the visible, infrared, and thermal wavelengths have been launched due to the improvement of hardware technologies of satellite sensors development. According to the development of satellite sensors with various wavelength ranges, the fusion and integration of multisensor images are proceeded. Image matching process is an essential step for the application of multisensor images. Some algorithms, such as SIFT and SURF, have been proposed to co-register satellite images. However, when the existing algorithms are applied to extract matching points between optical and thermal images, high accuracy of co-registration might not be guaranteed because these images have difference spectral and spatial characteristics. In this paper, location of control points in a reference image is extracted by SURF, and then, location of their corresponding pairs is estimated from the correlation of the local similarity. In the case of local similarity, phase correlation method, which is based on fourier transformation, is applied. In the experiments by simulated, Landsat-8, and ASTER datasets, the proposed algorithm could extract reliable matching points compared to the existing SURF-based method.

• Korean Journal of Remote Sensing
• /
• v.22 no.2
• /
• pp.101-110
• /
• 2006

The accuracy of rural land cover using airborne multispectral images and LEAR (Light Detection And Ranging) data was analyzed. Multispectral image consists of three bands in green, red and near infrared. Intensity image was derived from the first returns of LIDAR, and vegetation height image was calculated by difference between elevation of the first returns and DEM (Digital Elevation Model) derived from the last returns of LIDAR. Using maximum likelihood classification method, three bands of multispectral images, LIDAR vegetation height image, and intensity image were employed for land cover classification. Overall accuracy of classification using all the five images was improved to 85.6% about 10% higher than that using only the three bands of multispectral images. The classification accuracy of rural land cover map using multispectral images and LIDAR images, was improved with clear difference between heights of different crops and between heights of crop and tree by LIDAR data and use of LIDAR intensity for land cover classification.

• The Bulletin of The Korean Astronomical Society
• /
• v.40 no.1
• /
• pp.61.3-62
• /
• 2015

Remote-sensing observation is one of the observation methods that provide valuable information, such as composition and surface physical conditions of solar system objects. The Hayabusa spacecraft succeeded in the first sample returning from a near-Earth asteroid, (25143) Itokawa. It has established a ground truth technique to connect between ordinary chondrite meteorites and S-type asteroids. One of the scientific observation instruments that Hayabusa carried, Asteroid Multi-band Imaging Camera(AMICA) has seven optical-near infrared filters (ul, b, v, w, x, p, and zs), taking more than 1400 images of Itokawa during the rendezvous phase. The reflectance of planetary body can provide valuable information of the surface properties, such as the optical aspect of asteroid surface at near zero phase angle (i.e. Sun-asteroid-observer's angle is nearly zero), light scattering on the surface, and surface roughness. However, only little information of the phase angle dependences of the reflectance of the asteroid is known so far. In this study, we investigated the phase angle dependences of Itokawa's surface to understand the surface properties in the solar phase angle of $0^{\circ}-40^{\circ}$ using AMICA images. About 700 images at the Hayabusa rendezvous phase were used for this study. In addition, we compared our result with those of several photometry models, Minnaert model, Lommel-Seeliger model, and Hapke model. At this conference, we focus on the AMICA's v-band data to compare with previous ground-based observation researches.

• Journal of the Optical Society of Korea
• /
• v.19 no.1
• /
• pp.102-111
• /
• 2015

This paper proposes an algorithm for recovering the colors of objects from multiple near-infrared (near-IR) images. The International Commission on Illumination (CIE) color coordinates of objects are recovered from a series of gray images captured under multiple spectral near-IR illuminations using polynomial regression. The feasibility of the proposed algorithm is tested experimentally by using 24 color patches of the Color Rendition Chart. The experimental apparatus is composed of a monochrome digital camera without an IR cut-off filter and a custom-designed LED illuminator emitting multiple spectral near-IR illuminations, with peak wavelengths near the red edge of the visible band, namely at 700, 740, 780, and 860 nm. The average color difference between the original and the recovered colors for all 24 patches was found to be 11.1. However, if some particular patches with high value are disregarded, the average color difference is reduced to 4.2, and this value is within the acceptability tolerance for complex image on the display.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.22 no.11
• /
• pp.1063-1069
• /
• 2011

NCTR(Non-Cooperative Target Recognition) and ATR(Automatic Target Recognition) are methodologies to identify military targets using radar, optical, and infrared images. Among them, a strategy to recognize ground targets using synthetic aperature radar(SAR) images is called SAR ATR. In general, SAR ATR consists of three sequential stages: detection, discrimination and classification. In this paper, a modification of the polar mapping classifier(PMC) to identify inverse SAR(ISAR) images has been made in order to apply it to SAR ATR. In addition, a preprocessing scheme can mitigate the effect from the clutter, and information on the shadow is employed to improve the classification accuracy.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.37 no.3
• /
• pp.63-71
• /
• 2000

Infrared (IR) detector chip, which detects the IR radiation from all of the objects and converts to image signal, is usually fabricated using hybrid bonding technology with detector away and readout integrated circuit (ROIC). In this study, we designed the readout circuit and simulated its operations. Fabricating readout circuit chips, we measured operation results satisfying its design requirements in 6V supply voltage. After we mount the IR detector chip in the manufactured thermal image system, thermal images were implemented. The obtained thermal images for high and room temperature target objects are sufficiently recognizable. Using the low noise thermal Image system, we expect to obtain thermal images with higher temperature resolution.

• Journal of the Korean Wood Science and Technology
• /
• v.47 no.4
• /
• pp.385-392
• /
• 2019

In our previous study, we investigated the use of ensemble models based on LeNet and MiniVGGNet to classify the images of transverse and longitudinal surfaces of five Korean softwoods (cedar, cypress, Korean pine, Korean red pine, and larch). It had accomplished an average F1 score of more than 98%; the classification performance of the longitudinal surface image was still less than that of the transverse surface image. In this study, ensemble methods of two different convolutional neural network models (LeNet3 for smartphone camera images and NIRNet for NIR spectra) were applied to lumber species classification. Experimentally, the best classification performance was obtained by the averaging ensemble method of LeNet3 and NIRNet. The average F1 scores of the individual LeNet3 model and the individual NIRNet model were 91.98% and 85.94%, respectively. By the averaging ensemble method of LeNet3 and NIRNet, an average F1 score was increased to 95.31%.

• Medical Lasers
• /
• v.10 no.3
• /
• pp.123-131
• /
• 2021

Optical imaging modalities with properties of real-time, non-invasive, in vivo, and high resolution for image-guided surgery have been widely studied. In this review, we introduce two optical imaging systems, that could be the core of image-guided surgery and introduce the system configuration, implementation, and operation methods. First, we introduce the optical coherence tomography (OCT) system implemented by our research group. This system is implemented based on a swept-source, and the system has an axial resolution of 11 ㎛ and a lateral resolution of 22 ㎛. Second, we introduce a fluorescence imaging system. The fluorescence imaging system was implemented based on the absorption and fluorescence wavelength of indocyanine green (ICG), with a light-emitting diode (LED) light source. To confirm the performance of the two imaging systems, human malignant melanoma cells were injected into BALB/c nude mice to create a xenograft model and using this, OCT images of cancer and pathological slide images were compared. In addition, in a mouse model, an intravenous injection of indocyanine green was used with a fluorescence imaging system to detect real-time images moving along blood vessels and to detect sentinel lymph nodes, which could be very important for cancer staging. Finally, polarization-sensitive OCT to find the boundaries of cancer in real-time and real-time image-guided surgery using a developed contrast agent and fluorescence imaging system were introduced.