• The Journal of the Acoustical Society of Korea
• /
• 제37권1호
• /
• pp.12-20
• /
• 2018

Efforts have been made to reconstruct low-resolution underwater images to high-resolution ones by using the image SR (Super-Resolution) method, all to improve efficiency when acquiring side-scan sonar images. As side-scan sonar images are similar with the optical images with respect to exploiting 2-dimensional signals, conventional image restoration methods for optical images can be considered as a solution. One of the most typical super-resolution methods for optical image is a sparse coding and there are studies for verifying applicability of sparse coding method for underwater images by analyzing sparsity of underwater images. Sparse coding is a method that obtains recovered signal from input signal by linear combination of dictionary and sparse coefficients. However, it requires huge computational load to accurately estimate sparse coefficients. In this study, a sparse coding based underwater image super-resolution method is applied while a selective reconstruction method for object region is suggested to reduce the processing time. For this method, this paper proposes an edge detection and object and non object region classification method for underwater images and combine it with sparse coding based image super-resolution method. Effectiveness of the proposed method is verified by reducing the processing time for image reconstruction over 32 % while preserving same level of PSNR (Peak Signal-to-Noise Ratio) compared with conventional method.

• Journal of the Institute of Convergence Signal Processing
• /
• 제4권4호
• /
• pp.1-6
• /
• 2003

In this Paper, the moving image is detected by a collision preventive system. The noise of these images is reduced by a mean filter. In case of detecting a movement with a binary difference image the moving area is detected exactly by the labeling and the projective method. When the image move slowly with the tracking mode of the system, the center of the tracking window move to the previous tracking window. And the tracking windows are divided into a tracking mode and a coasting mode which are determine by the Contrast-Difference Correlation of the date obtained from a difference image. The coasting mode determine whether continue the tracking step or not comparing the coasting-time values to reducing the error by the disturbance. The coasting and tracking of these moving images are verified by the result of the simulation.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권9호
• /
• pp.3583-3597
• /
• 2020

In this paper, a parallel deep learning model using a convolutional neural network and a dilated convolutional neural network is proposed to classify Alzheimer's disease with high accuracy in PET/CT images. The developed model consists of two pipelines, a conventional CNN pipeline, and a dilated convolution pipeline. An input image is sent through both pipelines, and at the end of both pipelines, extracted features are concatenated and used for classifying Alzheimer's disease. Complimentary abilities of both networks provide better overall accuracy than single conventional CNNs in the dataset. Moreover, instead of performing binary classification, the proposed model performs three-class classification being Alzheimer's disease, mild cognitive impairment, and normal control. Using the data received from Dong-a University, the model performs classification detecting Alzheimer's disease with an accuracy of up to 95.51%.

• Journal of Ecology and Environment
• /
• 제41권3호
• /
• pp.85-92
• /
• 2017

Unmanned aerial vehicles (UAVs) are a new and yet constantly developing part of forest inventory studies and vegetation-monitoring fields. Covering large areas, their extensive usage has saved time and money for researchers and conservationists to survey vegetation for various data analyses. Post-processing imaging software has improved the effectiveness of UAVs further by providing 3D models for accurate visualization of the data. We focus on determining the coniferous tree coverage to show the current advantages and disadvantages of the orthorectified 2D and 3D models obtained from the image photogrammetry software, Pix4Dmapper Pro-Non-Commercial. We also examine the methodology used for mapping the study site, additionally investigating the spread of coniferous trees. The collected images were transformed into 2D black and white binary pixel images to calculate the coverage area of coniferous trees in the study site using MATLAB. The research was able to conclude that the 3D model was effective in perceiving the tree composition in the designated site, while the orthorectified 2D map is appropriate for the clear differentiation of coniferous and deciduous trees. In its conclusion, the paper will also be able to show how UAVs could be improved for future usability.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• 제35S권2호
• /
• pp.137-145
• /
• 1998

In this paper, we propose a tube-hole center detection vision algorithm verifying the position of a tele-controlled robot and providing visual information for increasing reliability and efficiency in the diagnosis of steam generator (SG) tubes in nuclear power plant. A tele-controlled robot plays a role in carrying the probe used in inspecting the integrity of SG tubes. Thus accurately locating a tele-controlled robot on the desired tube-hole center is important issue for reliability of inspection. To do this work, we have to find the tube-hole center locations from the input image. At first, we apply the three-class segmentation method modified for this application. WE extract minimum bounding rectangles (MBRs) in the theresholded binary image. Second, for discriminating between MBR by tube and MBR by noise, we introduce the MBR rejection rules as knowledge-based rule set. MBRs are divided into the very dark region MBRs and the very bright region MBRs. In order to describe the region of complete tube-hole, the MBRs need a process of pairing each other. We then can find the tube-hole center from the paired MBR. For more accurately finding the tube-hole center in several sequential images, the centers of some frames need to be averaged. We tested the performance of our method using hundreds of real images.

• Journal of the Korea Computer Graphics Society
• /
• 제4권1호
• /
• pp.31-40
• /
• 1998

Active Contour Model(ACM) is an efficient method for segmenting an object. The main shortcoming of ACM is that its result is very dependent on the shape and location of an initial contour. To overcome this shortcoming, a new segmentation algorithm is proposed in this paper. The proposed algorithm uses B-splines to describe the active contour and applies Simulated Annealing (SA) and Genetic Algorithm(GA) as energy minimization techniques. We tried to overcome the initialization problem of traditional ACM and compared the result of ACM using GA and that using SA with 2D synthetic binary images. CT and MR images.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• 제10권4호
• /
• pp.288-294
• /
• 2017

Recently, deep learning using convolutional neural network (CNN) has been extensively studied in image recognition. Convolution consists of addition and multiplication. Multiplication is computationally expensive in hardware implementation, relative to addition. It is also important factor limiting a chip design in an embedded deep learning system. In this paper, I propose a parallel-addition processing algorithm that converts grayscale images to the superposition of binary images and performs convolution only with addition. It is confirmed that the convolution can be performed by a parallel-addition method capable of reducing the processing time in experiment for verifying the availability of proposed algorithm.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• 제30권3C호
• /
• pp.112-118
• /
• 2005

In this paper, we propose a new nonlinear matching measure for automatic analysis of the on-off type DNA microarray images in which the hybridized spots are detected by the template matching method. The proposed measure is obtained by binary-thresholding over the whole template region and taking the number of white pixels inside the spotted area. This measure is compared with the normalized covariance in terms of the classification ability of the successfulness of the locating markers. The proposed measure is evaluated for the scanned images of HPV DNA microarrays where the marker locating is a critical issue because of the small number of spots. The targeting spots of HPV DNA chips are designed for genotyping 22 types of the human papilloma virus(HPV). The proposed measure is proven to give more discriminative response reducing the miss cases of the successful marker locating.

• Journal of Information Processing Systems
• /
• 제9권1호
• /
• pp.173-188
• /
• 2013

In Facial Expression Recognition Systems (FERS), only particular regions of the face are utilized for discrimination. The areas of the eyes, eyebrows, nose, and mouth are the most important features in any FERS. Applying facial features descriptors such as the local binary pattern (LBP) on such areas results in an effective and efficient FERS. In this paper, we propose an automatic facial expression recognition system. Unlike other systems, it detects and extracts the informative and discriminant regions of the face (i.e., eyes, nose, and mouth areas) using Haar-feature based cascade classifiers and these region-based features are stored into separate image files as a preprocessing step. Then, LBP is applied to these image files for facial texture representation and a feature-vector per subject is obtained by concatenating the resulting LBP histograms of the decomposed region-based features. The one-vs.-rest SVM, which is a popular multi-classification method, is employed with the Radial Basis Function (RBF) for facial expression classification. Experimental results show that this approach yields good performance for both frontal and near-frontal facial images in terms of accuracy and time complexity. Cohn-Kanade and JAFFE, which are benchmark facial expression datasets, are used to evaluate this approach.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권3호
• /
• pp.1595-1613
• /
• 2017

The IR camera and laser-based IR projector provide an effective solution for real-time collection of moving targets in RGB-D videos. Different from the traditional RGB videos, the captured depth videos are not affected by the illumination variation. In this paper, we propose a novel feature extraction framework to describe human activities based on the above optical video capturing method, namely spatial-temporal texture features for 3D human activity recognition. Spatial-temporal texture feature with depth information is insensitive to illumination and occlusions, and efficient for fine-motion description. The framework of our proposed algorithm begins with video acquisition based on laser projection, video preprocessing with visual background extraction and obtains spatial-temporal key images. Then, the texture features encoded from key images are used to generate discriminative features for human activity information. The experimental results based on the different databases and practical scenarios demonstrate the effectiveness of our proposed algorithm for the large-scale data sets.