• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.18 no.12
• /
• pp.38-44
• /
• 2019

Various automation studies have been conducted to detect defective products based on product images. In the case of machine vision-based studies, size and color error are detected through a preprocessing process. A situation may arise in which the main features are removed during the preprocessing process, thereby decreasing the accuracy. In addition, complex systems are required to detect various kinds of defects. In this study, we designed and developed a system to detect errors by analyzing various conditions of defective products. We designed the deep learning algorithm to detect the defective features from the product images during the automation process using a convolution neural network (CNN) and verified the performance by applying the algorithm to the checker-switch failure detection system. It was confirmed that all seven error characteristics were detected accurately, and it is expected that it will show excellent performance when applied to automation systems for error detection.

• Textile Coloration and Finishing
• /
• v.26 no.4
• /
• pp.305-310
• /
• 2014

In this study, we presented a newly synthesized pyrene-naphthalene diimide(NDI)-pyrene triad. The optical and structural properties were examined using various characterization techniques. A donor-acceptor-donor triad molecule exhibited a strong charge transfer, though there existed neither intramolecular nor intermolecular hydrogen bonding sites, due to the formation of preferential complementary complex between pyrene and NDI. Powder XRD measurement revealed a sharp and distinctive X-ray patterns, indicating the presence of microcrystalline-like structure. POM images showed anisotropic fingerprint texture similar to that of cholesteric phase, and SEM images showed numerous columnar structures with length of 1 to $10{\mu}m$. Above observation clearly demonstrated that ${\pi}$-complementary NDI-pyrene interactions in the traid was strong enough to form columnar aggregates in the long range.

• Journal of the Korean Society for Precision Engineering
• /
• v.16 no.5 s.98
• /
• pp.48-57
• /
• 1999

Applications of thresholding technique are based on the assumption that object and background pixels in a digital image can be distinguished by their gray level values. For the segmentation of more complex images, it is necessary to resort to multiple threshold selection techniques. This paper describes a new method for multiple threshold selection of gray level images which are not clearly distinguishable from the background. The proposed method consists of three main stages. In the first stage, a probability distribution function for a gray level histogram of an image is derived. Cluster points are defined according to the probability distribution function. In the second stage, fuzzy partition matrix of the probability distribution function is generated through the fuzzy clustering process. Finally, elements of the fuzzy partition matrix are classified as clusters according to gray level values by using max-membership method. Boundary values of classified clusters are selected as multiple threshold. In order to verify the performance of the developed algorithm, automatic inspection process of ball grid array is presented.

• Atmosphere
• /
• v.26 no.2
• /
• pp.215-226
• /
• 2016

Conceptual models to analyze both typhoon and Changma using products extracted by the GEO-KOMPSAT-2A (GK-2A) are suggested in this study. The GK-2A which is scheduled to be launched in 2018 has a high resolution, 16 channels, and 52 products. This means GK-2A is expected to obtain high quality images and products, which can detect severe weather earlier than the Communications, Ocean and Meteorological Satellite (COMS). Since there are not enough conceptual models for typhoon and Changma using satellite images and products, our conceptual model can increase both the applicability of satellite data and the accuracy of analysis. In the conceptual model, typhoons are classified as three types by prevailing factors; 1) heavy-rainfall type, 2) wind type, and 3) complex type. For Changma, two types are divided by the characteristics; band type and heavy-rainfall type. Among the high resolution 52 products, each type of typhoon and Changma are selected. In addition, the numerical products and dynamic factors are considered in order to improve conceptual models.

• 한국지구물리탐사학회:학술대회논문집
• /
• 2007.06a
• /
• pp.257-260
• /
• 2007

Two-dimensional (2D) interpretation of MT and AMT data observed in 2004 in Jeju Island is made using two inversion schemes developed by Uchida (1993) and Lee et al. (2002). These interpretations show that the subsurface of Jeju consists of roughly three layers. Reconstructed images along lines E and W reveal that the conductive layer beneath the topmost resistive layer of lava plateau can be a sediment layer. The geoelectrical structure along line E is more complex than that along line W, especially near Mt. Halla. The Uchida’s (1993) scheme gives reasonable images, but much more time-consuming than that of Lee et al. (2002).

• Journal of the Optical Society of Korea
• /
• v.20 no.3
• /
• pp.341-357
• /
• 2016

A novel asymmetric multiple-image encryption method using an octonion Fresnel transform (OFST) and a two-dimensional Sine Logistic modulation map (2D-SLMM) is presented. First, a new multiple-image information processing tool termed the octonion Fresneltransform is proposed, and then an efficient method to calculate the OFST of an octonion matrix is developed. Subsequently this tool is applied to process multiple plaintext images, which are represented by octonion algebra, holistically in a vector manner. The complex amplitude, formed from the components of the OFST-transformed original images and modulated by a random phase mask (RPM), is used to derive the ciphertext image by employing an amplitude- and phase-truncation approach in the Fresnel domain. To avoid sending whole RPMs to the receiver side for decryption, a random phase mask generation method based on SLMM, in which only the initial parameters of the chaotic function are needed to generate the RPMs, is designed. To enhance security, the ciphertext and two decryption keys produced in the encryption procedure are permuted by the proposed SLMM-based scrambling method. Numerical simulations have been carried out to demonstrate the proposed scheme's validity, high security, and high resistance to various attacks.

• ETRI Journal
• /
• v.41 no.6
• /
• pp.797-810
• /
• 2019

Image saliency detection is the basis of perceptual image processing, which is significant to subsequent image processing methods. Most saliency detection methods can detect only a single object with a high-contrast background, but they have no effect on the extraction of a salient object from images with complex low-contrast backgrounds. With the prior knowledge, this paper proposes a method for detecting salient objects by combining the boundary contrast map and the geodesics-like maps. This method can highlight the foreground uniformly and extract the salient objects efficiently in images with low-contrast backgrounds. The classical receiver operating characteristics (ROC) curve, which compares the salient map with the ground truth map, does not reflect the human perception. An ROC curve with distance (distance receiver operating characteristic, DROC) is proposed in this paper, which takes the ROC curve closer to the human subjective perception. Experiments on three benchmark datasets and three low-contrast image datasets, with four evaluation methods including DROC, show that on comparing the eight state-of-the-art approaches, the proposed approach performs well.

• International Journal of Control, Automation, and Systems
• /
• v.4 no.5
• /
• pp.637-644
• /
• 2006

Biomedical image is often complex. An applied image analysis system should deal with the images which are of quite low quality and are challenging to segment. This paper presents a framework for color cell image segmentation by learning and classification online. It is a robust two-stage scheme using kernel method and watershed transform. In first stage, a two-class SVM is employed to discriminate the pixels of object from background; where the SVM is trained on the data which has been analyzed using the mean shift procedure. A real-time training strategy is also developed for SVM. In second stage, as the post-processing, local watershed transform is used to separate clustering cells. Comparison with the SSF (Scale space filter) and classical watershed-based algorithm (those are often employed for cell image segmentation) is given. Experimental results demonstrate that the new method is more accurate and robust than compared methods.

• KIPS Transactions on Software and Data Engineering
• /
• v.3 no.5
• /
• pp.195-200
• /
• 2014

Typical methods of active contour model for object contour extraction are snake and level. Snake is usually faster than level set, but has limitation to compute topology of objects. Level set on the other hand is slower but good at it. In this paper, a new object contour extraction algorithm to use advantage of each is proposed. The algorithm is composed of two main steps. In the first step, snake is used to extract the rough contour and then in the second step, level set is applied to extract the complex contour exactly. 5 binary images and 2 natural images with different contours are simulated by a proposed algorithm. It is shown that speed is reduced and contour is better extracted.

• Journal of the Korea Society of Computer and Information
• /
• v.10 no.4 s.36
• /
• pp.133-141
• /
• 2005

An edge is where the intensity of an image moves from a low value to high value or vice versa. The edges tell where objects are. their shape and size. and something about their texture. Many traditional edge operators are derivative based and perform reasonably well for simple noise-free images. In recent, statistical edge detectors for complex images with noises have been described. This paper compares and analysis the performance of statistical edge detectors based on the T test and Wilcoxon test, and mathematical edge detectors based on Sobel operator, and the well-known Canny detector and Wavelet transformation detector, and provides the implementation of these edge detectors using Java on the web.