• Journal of the Korea Society of Computer and Information
• /
• v.17 no.5
• /
• pp.29-32
• /
• 2012

In this paper, we propose a novel method to extract muscle area from lumbar ultrasonographic image. The muscle area resided in lumbar area can be defined as the area between thoracic vertebra and subcutaneous fat area. A modified 4-directional contour tracing algorithm is designed to detect the boundaries and candidate areas are extracted and verified by the morphological characteristics of lumbar area. The experiment using 392 lumbar images verifies that the proposed method is sufficiently effective by showing over 94% accuracy in extraction.

• Journal of Korea Game Society
• /
• v.11 no.1
• /
• pp.139-146
• /
• 2011

We propose a photomosaic method using PCA(Principal Component Analysis), which uses PCA results to find the most similar candidate fast and correctly. When two images are projected onto a certain principal component, if their coefficients are similar, they are also likely to be similar. Thus our photomosaic method using PCA can take care of both colors and shapes of images. Our method using coefficient comparison is faster than the one using all color comparison and more correct than the one using average comparison. Our hardware accelerated photomosaic algorithm can handle video images in real-time.

• The Journal of the Korea Contents Association
• /
• v.4 no.3
• /
• pp.107-113
• /
• 2004

This paper improved the performance of the face recognition system using the PCA/LDA hybrid method based on the facial geometric feature and the Wavelet transform. Because the previous PCA/LDA methods have measured the similarity according to the formal dispersion, they could not reflect facial boundaries exactly In order to recover this defect, this paper proposed the method using the distance between eyes and mouth. If the difference of the measured distances on the query and the training images is over the given threshold, then the method reorders the candidate images according to energy feature vectors of eyes, a nose, and a chin. To evaluate the performance of the proposed method the computer simulations have been performed with four hundred facial images in the ORL database. The results showed that our method improves about 4％ recognition rate over the previous PCA/LDA method.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.27 no.6C
• /
• pp.610-618
• /
• 2002

This paper presents a new image retrieval method that is based on color space and block region information. The color space information of images can be obtained by color binary set, and the block region information can be obtained by regional segmentation and feature. The candidate images are decided by comparing with color features and its binary set of query image and image feature database for retrieval. Particularly, it is possible that the retrieval using similarity-measurements has the weights of color spatial distribution arid its objective block region features. This retrieval method using color spatial and block region features is shown with the effectiveness on the result of implementation on image database with 6,000 images.

• Smart Media Journal
• /
• v.5 no.1
• /
• pp.49-54
• /
• 2016

Medical image processing is a compulsory process to diagnose many kinds of disease. Therefore, an automatic algorithm for this task is highly demanded as an important part to construct a computer-aided diagnosis system. In this paper, we introduce an automatic method to segment the liver region from 3D abdominal CT images using Otsu method. First, we choose a 2D slice which has most liver information from the whole 3D image. Secondly, on the chosen slice, we enhanced the image based on its intensity using Otsu method with multiple thresholds and use the threshold to enhance the whole 3D image. Then, we apply a liver mask to mark the candidate liver region. After that, we execute the Otsu method again to segment the liver region from the chosen slice and propagate the result to the whole 3D image. Finally, we apply preprocessing on the frontal side of 3D images to crop only the liver region from the image.

• Journal of Korea Multimedia Society
• /
• v.20 no.5
• /
• pp.769-781
• /
• 2017

Deep learning networks like Convolutional Neural Networks (CNNs) show successful performances in many computer vision applications such as image classification, object detection, and so on. For implementation of deep learning networks in embedded system with limited processing power and memory, deep learning network may need to be simplified. However, simplified deep learning network cannot learn every possible scene. One realistic strategy for embedded deep learning network is to construct a simplified deep learning network model optimized for the scene images of the installation place. Then, automatic training will be necessitated for commercialization. In this paper, as an intermediate step toward automatic training under fisheye camera environments, we study more precise human localization in fisheye images, and propose an accurate human localization method, Automatic Ground-Truth Labelling Method (AGTLM). AGTLM first localizes candidate human object bounding boxes by utilizing GoogLeNet-LSTM approach, and after reassurance process by GoogLeNet-based CNN network, finally refines them more correctly and precisely(tightly) by applying saliency object detection technique. The performance improvement of the proposed human localization method, AGTLM with respect to accuracy and tightness is shown through several experiments.

• The Bulletin of The Korean Astronomical Society
• /
• v.43 no.2
• /
• pp.53.2-53.2
• /
• 2018

We present newly discovered dwarf galaxy candidates in deep and wide-field images of NGC 1291 obtained with KMTNet. Through a visual inspection, we find ~ 13 candidates, for which central surface brightness ranges from ${\mu}_{0,R}{\sim}22.5$ to $26.5mag\;arcsec^{-1}$. Adopting the distance to NGC 1291, the candidate dwarfs are brighter than $M_R=-12.5mag$ and their effective radii range from 350 pc to 1.4 kpc. Structural and photometric properties of dwarf candidates near NGC 1291 appears to be consistent with those of ordinary dwarf galaxies in nearby galaxies. We conduct the imaging simulation in order to find an optimal way to detect dwarf galaxies in KMTNet images and to test the completeness of our detection algorithm. We plan to apply this method to deep KMTNet images of other nearby galaxies obtained through KMTNet Nearby Galaxy Survey (KNGS).

• Journal of Korea Society of Industrial Information Systems
• /
• v.14 no.4
• /
• pp.57-64
• /
• 2009

In this paper, We propose an highly efficient preprocessing technique for improving the performance of the crease extraction method, which can improve the accuracy of feature extraction within the fingerprint image. The proposed method applies the 1-dimensional directional slit for each pixel in fingerprint image. Once the direction of every pixel in crease candidate area is estimated, it is decomposed into different images depending on their direction. From the directional images, the crease clusters are estimated by utilizing the property of crease area. The proposed method finally extracts the crease from the crease clusters estimated from directional images.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.48 no.2
• /
• pp.9-15
• /
• 2011

In this paper, we propose a method to extract the external oblique muscle of abdomen images that is often excluded by previous method due to image distortion. In the preprocessing phase of the proposed method, we emphasize the brightness contrast with Ends-in search stretching algorithm after removing noise from the initial ultrasonic images. Then we apply average binarization in vertical direction to extract candidate fascia areas. After removing other areas than fascia with morphological characteristics, the lost part in the fascia during the process is restored with such characteristic information and location information. Then the skin area is also removed with information from the arc appearing in convex filming and the candidate muscle areas are extracted by overlapping two results two way up-down search algorithm. Another noise removing process is done to determine the muscle area. In case of obtaining obscure result, after restoring the muscle area by smearing method, the thickness of the muscle is measured by min square method. The experiment verifies that the proposed method is sufficiently effective to analyze the size and shape of muscles in abdomen in ultrasonography than previously used methods.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.23 no.3
• /
• pp.249-255
• /
• 2013

In this paper, we propose an algorithm to detect scale invariant object from IR image obtained in the sea environment. We create horizontal edge (HL), vertical edge (LH), diagonal edge (HH) of images through 2-D discrete Haar wavelet transform (DHWT) technique after noise reduction using morphology operations. Considering the sea environment, Gaussian blurring to the horizontal and vertical edge images at each level of wavelet is performed and then saliency map is generated by multiplying the blurred horizontal and vertical edges and combining into one image. Then we extract object candidate region by performing a binarization to saliency map. A small area in the object candidate region are removed to produce final result. Experiment results show the feasibility of the proposed algorithm.