• Journal of the Institute of Convergence Signal Processing
• /
• v.19 no.2
• /
• pp.35-41
• /
• 2018

The analysis of plankton species distribution in sea or fresh water is very important in preserving marine ecosystem health. Since manual analysis is infeasible, many automatic approaches were proposed. They usually use images from in situ towed underwater imaging sensor or specially designed, lab mounted microscopic imaging system. Normally they assume that only single plankton is present in an image so that, if there is a clumping among multiple plankton of same species (homogeneous clumping) or if there are multiple plankton of different species scattered in an image (heterogeneous interspersion), they have a difficulty in recognition. In this work, we propose a deep learning based method that can detect and recognize individual plankton in images with homogeneous clumping, heterogeneous interspersion, or combination of both.

• Journal of Information Processing Systems
• /
• v.19 no.6
• /
• pp.858-869
• /
• 2023

As one of the pivotal techniques of image restoration, single-channel blind source separation (SCBSS) is capable of converting a visual-only image into multi-source images. However, image degradation often results from multiple mixing methods. Therefore, this paper introduces an innovative SCBSS algorithm to effectively separate source images from a composite image in various mixed modes. The cornerstone of this approach is a novel triple generative adversarial network (TriGAN), designed based on dual learning principles. The TriGAN redefines the discriminator's function to optimize the separation process. Extensive experiments have demonstrated the algorithm's capability to distinctly separate source images from a composite image in diverse mixed modes and to facilitate effective image restoration. The effectiveness of the proposed method is quantitatively supported by achieving an average peak signal-to-noise ratio exceeding 30 dB, and the average structural similarity index surpassing 0.95 across multiple datasets.

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.839-844
• /
• 2003

This paper presents a method to segment wafer ID marks on poor quality images under uncontrolled lighting conditions of the semiconductor process. The active multiple templates matching method is suggested to search ID areas on wafers and segment them into meaningful regions and it would have been impossible to recognize characters using general OCR algorithms. This active template model is designed by applying a snake model that is used for active contour tracking. Active multiple template model searches character areas and segments them into single characters optimally, tracking each character that can vary in a flexible manner according to string configurations. Applying active multiple templates, the optimization of the snake energy is done using Greedy algorithm, to maximize its efficiency by automatically controlling each template gap. These vary according to the configuration of character string. Experimental results using wafer images from real FA environment are presented.

• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.34C no.4
• /
• pp.36-44
• /
• 1997

An efficient context-free multiple-object segmentation using attention operator based on modified generalized symmetry transform is proposed and implemented by modifying a radial basis function network. By using the difference of intensity gradient, instead of te intensity gradient itself, in generalized symmetry tranform so as to make the attention operator to preserve the edges of the objects shape, an efficient context-free multiple-object segementation is proposed in which no a priori shape informtion on the objects is requried. The attention operator is implemented by using a modified radial basis function network which can reflect symmetry, and by using te edge pyramid of the input image, both of the local and the global symmetry of the objects are reflected simultaneously to make the multiple-object with different sizes be segmented with a singel fixed-size $n\timesm$ can be done with O(n) complexity. The simulaton results show that the proposed algorithm can efficiently be used in context-free multiple-object segmentation even for the low contrast IR images as well as for the images from the camera.

• Current Optics and Photonics
• /
• v.2 no.4
• /
• pp.315-323
• /
• 2018

A new multiple-image encryption scheme that is based on a compressive ghost imaging concept along with a Fourier transform sampling principle has been proposed. This further improves the security of the scheme. The scheme adopts a Fourier transform to sample the original multiple-image information respectively, utilizing the centrosymmetric conjugation property of the spatial spectrum of the images to obtain each Fourier coefficient in the most abundant spatial frequency band. Based on this sampling principle, the multiple images to be encrypted are grouped into a combined image, and then the compressive ghost imaging algorithm is used to improve the security, which reduces the amount of information transmission and improves the information transmission rate. Due to the presence of the compressive sensing algorithm, the scheme improves the accuracy of image reconstruction.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.7
• /
• pp.2328-2344
• /
• 2022

2D human pose estimation still faces difficulty in low-resolution images. Most existing top-down approaches scale up the target human bonding box images to the large size and insert the scaled image into the network. Due to up-sampling, artifacts occur in the low-resolution target images, and the degraded images adversely affect the accurate estimation of the joint positions. To address this issue, we propose a multi-resolution input feature fusion network for human pose estimation. Specifically, the bounding box image of the target human is rescaled to multiple input images of various sizes, and the features extracted from the multiple images are fused in the network. Moreover, we introduce a guiding channel which induces the multi-resolution input features to alternatively affect the network according to the resolution of the target image. We conduct experiments on MS COCO dataset which is a representative dataset for 2D human pose estimation, where our method achieves superior performance compared to the strong baseline HRNet and the previous state-of-the-art methods.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.36 no.3
• /
• pp.127-134
• /
• 2018

Electric transmission towers are facilities to transport electrical power from a plant to an electrical substation. The towers are connected using power lines that are installed with a proper sag by loosening the cable to lower the tension and to secure the sufficient clearance from the ground or nearby objects. The power line sag may extend over the tolerance due to the weather such as strong winds, temperature changes, and a heavy snowfall. Therefore the periodical mapping of the power lines is required but the poor accessibility to the power lines limit the work because most power lines are placed at the mountain area. In addition, the manual mapping of the power lines is also time-consuming either using the terrestrial surveying or the aerial surveying. Therefore we utilized multiple overlapping images acquired from a low-cost drone to automatically reconstruct the power lines in the object space. Two overlapping images are selected for epipolar image resampling, followed by the line extraction for the resampled images and the redundant images. The extracted lines from the epipolar images are matched together and reconstructed for the power lines primitive that are noisy because of the multiple line matches. They are filtered using the extracted line information from the redundant images for final power lines points. The experiment result showed that the proposed method successfully generated parabolic curves of power lines by interpolating the power lines points though the line extraction and reconstruction were not complete in some part due to the lack of the image contrast.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.22 no.6
• /
• pp.741-747
• /
• 2012

In this paper, we propose a fast and robust framework for detecting and tracking multiple targets. The proposed system includes two modules: object detection module and object tracking module. In the detection module, we preprocess the input images frame by frame, such as gray and binarization. Next after extracting the foreground object from the input images, morphology technology is used to reduce noises in foreground images. We also use a block-based histogram analysis method to distinguish human and other objects. In the tracking module, color-based tracking algorithm and Kalman filter are used. After converting the RGB images into HSV images, the color-based tracking algorithm to track the multiple targets is used. Also, Kalman filter is proposed to track the object and to judge the occlusion of different objects. Finally, we show the effectiveness and the applicability of the proposed method through experiments.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.22 no.11
• /
• pp.1462-1467
• /
• 2018

A number of algorithms for improving the image quality of low light images have been studied using a single image or multiple exposure images. The low light image is low in contrast and has a large amount of noise, which limits the identification of information of the subject. This paper proposes the hardware design of algorithms that improve the quality of low light image using 2 multiple exposure images taken with a dual camera. The proposed hardware structure is designed in real time processing in a way that does not use frame memory and line memory using transfer function. The proposed hardware design has been designed using Verilog and validated in Modelsim. Finally, when the proposed algorithm is implemented on FPGA using xc7z045-2ffg900 as the target board, the maximum operating frequency is 167.617MHz. When the image size is 1920x1080, the total clock cycle time is 2,076,601 and can be processed in real time at 80.7fps.

• Journal of the Korea Society of Computer and Information
• /
• v.19 no.1
• /
• pp.23-30
• /
• 2014

Feature matching using image descriptors is robust method used recently. However, mismatches occur in 3D transformed images, illumination-changed images and repetitive-pattern images. In this paper, we observe that there are a lot of mismatches in the images which have repetitive patterns. We analyze it and propose a method to eliminate these mismatches. MDMF(Multiple Descriptors-based Mismatch Filtering) eliminates mismatches by using descriptors of nearest several features of one specific feature point. In experiments, for geometrical transformation like scale, rotation, affine, we compare the match ratio among SIFT, ASIFT and MDMF, and we show that MDMF can eliminate mismatches successfully.