• Journal of Korea Multimedia Society
• /
• v.21 no.10
• /
• pp.1150-1161
• /
• 2018

Classification is widely used in medical images to categorize patients and non-patients. However, conventional classification requires a complex procedure, including some rigid steps such as pre-processing, segmentation, feature extraction, detection, and classification. In this paper, we propose a novel convolutional neural network (CNN), called LeukemiaNet, to specifically classify two different types of leukemia, including acute lymphoblastic leukemia (ALL) and acute myeloid leukemia (AML), and non-cancerous patients. To extend the limited dataset, a PCA color augmentation process is utilized before images are input into the LeukemiaNet. This augmentation method enhances the accuracy of our proposed CNN architecture from 96.9% to 97.2% for distinguishing ALL, AML, and normal cell images.

• Proceedings of the KSRS Conference
• /
• 2006.03a
• /
• pp.95-100
• /
• 2006

Measurements of ocean color from space since 1970s provided vital information with reference to physical and biogeochemical properties of the oceanic waters. The utility of these data has been explored in order to map and monitor highly toxic/or harmful algal blooms (HABs) that affected most of coastal waters throughout the world due to accelerated eutrophication from human activities and certain oceanic processes. However, the global atmospheric correction and bio-optical algorithms developed for oceanic waters were found to yield false information about the HABs in coastal waters. The present study aimed to evaluate the potential use of red tide index (RI) method, which has been developed by Ahn and Shanmugam (2005), for mapping of HABs in Korean and neighboring waters. Here we employed the SSMM to remove the atmospheric effect in the SeaWiFS image data and the achieved indices by RI method were found more appropriate in correctly identifying potential areas of the encountered HABs in Korean South Sea (KSS) and Chinese coastal waters during 1999-2004. But the existence of high absorbing and scattering materials greatly interfered with the standard OC4 algorithm which falsely identified red tides in these waters. In comparison with other methods, the RI approach for the early detection of HABs can provide state managers with accurate identification of the extent and location of these blooms as a management tool.

• Journal of the Korean Society for Precision Engineering
• /
• v.32 no.6
• /
• pp.537-542
• /
• 2015

The measurement of 3D shape is important in inspecting the quality of product. In this paper, we present a 3D shape measurement system of fastener using a camera and a slit laser. Calibration structure with slits is used in the extrinsic calibration of the camera and laser. The pose of the camera and laser is computed under the same world coordinate system in the calibration structure. Reflection of laser light on the metal surface causes many difficulties in the robust detection of them on image. We overcome this difficulty by using color and dynamic programming. Motor stage is used to rotate the fastener to recover the whole 3D shape of the surface of it.

• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.35C no.11
• /
• pp.48-56
• /
• 1998

In this paper, a moving object detection and face region extraction algorithm which can be used in video monitoring systems is presented. The proposed algorithm is composed of two stages. In the first stage, each frame of an input video sequence is analyzed using three measures which are based on image pixel difference. If the current frame contains moving objects, their skin regions are extracted using color and frame difference information in the second stage. Since the proposed algorithm does not rely on computationally expensive features like optical flow, it is well suited for real-time applications. Experimental results tested on various sequences have shown the robustness of the proposed algorithm.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.24 no.6
• /
• pp.769-776
• /
• 2000

Visible spectral characteristics of cross-sectional emissions from a partially premixed methane/air and propane/air flames have been investigated. An optical train with a two-axis scanning mirror system was used to record line-of-sight emission spectra from 354nm to 618nm, and inversion technique was adapted to obtain cross-sectional emission spectra. By analyzing the reconstructed emission spectra, cross-sectional intensities of CH and $C_2$ radicals were separated from the background emissions. The blue flame edge and yellow flame edge were also obtained by image processing technique for edge detection with color photograph of flame. These edges were compared with radial distributions of CH, $C_2$ radicals and background emissions. The CH radicals were observed at blue flame edge. The background emissions were generated by soot precursor at upstream of flame and by soot at downstream of flame. The $C_2$ radicals in propane/air flame were observed more than those in methane/air flame.

• The KIPS Transactions:PartB
• /
• v.10B no.6
• /
• pp.705-710
• /
• 2003

Recent years, as a rapid development of multimedia technology, video database system to retrieve video data efficiently seems to core technology in the oriented society. This thesis describes an efficient automatic frame detection and location method for content based retrieval of video. Frame extraction part is consist of incoming / outgoing car frame extraction and car number frame extraction stage. We gain star/end time of car video also car number frames. Frames are selected at fixed time interval from video and key frames are selected by color scale histogram and edge operation method. Car frame recognized can be searched by content based retrieval method.

• Proceedings of the Korean Society for Agricultural Machinery Conference
• /
• 1996.06c
• /
• pp.852-862
• /
• 1996

This study was carried out to develop tools to detect defects of apple using machine vision. For the purpose, 6 kinds of frame for color images, R, G, B, h, S, and I frame, and a frame for near infra-red images (NIR frame) were tested first to select one which is useful to segment defect areas from apple images. After then, several methods to classify kind of defect for the segmented defect areas were developed and tested. Five kinds of apple defect -bruise , decay ,fleck worm hole and scar were investigated . The results are as follows: NIR frame was selected as the best one among the 7 kinds of image frame, and R, G and I frames showed favourable result to segment areas of apple defect. Various features of the segmented defect areas were measured to classify the defect areas. Eight kids of feature of the areas-size, roundness, axes length ratio, mean and variance of pixel values, variance of real part of spectrum, mean and variance of power spectrum resulted from spacial ourier transform were observed for the segmented defect areas in the selected 4 frames. then procedures to classify defects using the features were developed for the 4 frames and tested with 75-113 defects on apples. The test resulted that NIR and I frames showed high accuracies to classify the kind of defect as 77% and 76% , respectively.

• Journal of Digital Contents Society
• /
• v.17 no.5
• /
• pp.367-373
• /
• 2016

In this paper, we propose a novel method to improve the accuracy of eye trackers and how to analyze them. The proposed method extracts a user profile information created by extracting gaze coordinates and color information based on the exact pupil information, and then, it maintains a high accuracy in the display. In case that extract the user profile information, the changes of the accuracy for the gaze time also is estimated and the optimum parameter value is extracted. In the experimental results for the accuracy of the gaze detection, the accuracy was low if a user took a short time in a specific point. On the other hand, when taking more than two seconds, the accuracy was measured more than 80 %.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.65 no.3
• /
• pp.477-486
• /
• 2016

This paper presents the area classification, identification, and tracking for multiple moving objects with the similar colors. To do this, first, we use the GMM(Gaussian Mixture Model)-based background modeling method to detect the moving objects. Second, we propose the use of the binary and morphology of image in order to eliminate the shadow and noise in case of detection of the moving object. Third, we recognize ROI(region of interest) of the moving object through labeling method. And, we propose the area classification method to remove the background from the detected moving objects and the novel method for identifying the classified moving area. Also, we propose the method for tracking the identified moving object using Kalman filter. To the end, we propose the effective tracking method when detecting the multiple objects with the similar colors. Finally, we demonstrate the feasibility and applicability of the proposed algorithms through some experiments.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.56 no.11
• /
• pp.2051-2057
• /
• 2007

In Oriental medicine, the status of a tongue is the important indicator to diagnose one's health like physiological and clinicopathological changes of inner parts of the body. The method of tongue diagnosis is not only convenient but also non-invasive and widely used in Oriental medicine. However, tongue diagnosis is affected by examination circumstances a lot like a light source, patient's posture and doctor's condition. To develop an automatic tongue diagnosis system for an objective and standardized diagnosis, segmenting a tongue is inevitable but difficult since the colors of a tongue, lips and skin in a mouth are similar. The proposed method includes preprocessing, graph-based over-segmentation, detecting positions with a local minimum over shading, detecting edge with color difference and estimating edge geometry from the probable structure of a tongue, where preprocessing performs down-sampling to reduce computation time, histogram equalization and edge enhancement. A tongue was segmented from a face image with a tongue from a digital tongue diagnosis system by the proposed method. According to three oriental medical doctors' evaluation, it produced the segmented region to include effective information and exclude a non-tongue region. It can be used to make an objective and standardized diagnosis.