• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.30B no.2
• /
• pp.69-77
• /
• 1993

Automatic image recognition system is essential for a better man-to machine interaction. Because of the noise and deformation due to the sensor operation, it is not simple to build an image recognition system even for the fixed images. In this paper neural network which has been reported to be adequate for pattern recognition task is applied to the fixed and variational(rotation, size, position variation for the fixed image)recognition with a hope that the problems of conventional pattern recognition techniques are overcome. At fixed image recognition system. ART model is trained with face images obtained by camera. When recognizing an matching score. In the test when wigilance level 0.6 - 0.8 the system has achievel 100% correct face recognition rate. In the variational image recognition system, 65 invariant moment features sets are taken from thirteen persons. 39 data are taken to train multi-layer perceptron and other 26 data used for testing. The result shows 92.5% recognition rate.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.36 no.6
• /
• pp.594-599
• /
• 2008

Image data produced from ADD water-tunnel test are currently analyzed manually. The accuracy and elapsed time of this process can be determined by observers. In this paper, the algorithm based on MATLAB for improved image data processing and analysis is proposed. This algorithm consists of camera calibration, gray-level transformation, noise filtering and binarization in image preprocessing, vortex trajectory measurement in image analysis. Experimental results show that the proposed algorithm has better accuracy and execution speed than those of the existing methods.

• Journal of the Korean Society of Radiology
• /
• v.17 no.5
• /
• pp.709-715
• /
• 2023

In this study, the performance evaluation of image quality for noise reduction was implemented using the U-net deep learning architecture in computed tomography (CT) images. In order to generate input data, the Gaussian noise was applied to ground truth (GT) data, and datasets were consisted of 8:1:1 ratio of train, validation, and test sets among 1300 CT images. The Adagrad, Adam, and AdamW were used as optimizer function, and 10, 50 and 100 times for number of epochs were applied. In addition, learning rates of 0.01, 0.001, and 0.0001 were applied using the U-net deep learning model to compare the output image quality. To analyze the quantitative values, the peak signal to noise ratio (PSNR) and coefficient of variation (COV) were calculated. Based on the results, deep learning model was useful for noise reduction. We suggested that optimized hyper parameters for noise reduction in CT images were AdamW optimizer function, 100 times number of epochs and 0.0001 learning rates.

• Investigative Magnetic Resonance Imaging
• /
• v.20 no.4
• /
• pp.215-223
• /
• 2016

Purpose: The management of metal-induced field inhomogeneities is one of the major concerns of distortion-free magnetic resonance images near metallic implants. The recently proposed method called "Slice Encoding for Metal Artifact Correction (SEMAC)" is an effective spin echo pulse sequence of magnetic resonance imaging (MRI) near metallic implants. However, as SEMAC uses the noisy resolved data elements, SEMAC images can have a major problem for improving the signal-to-noise ratio (SNR) without compromising the correction of metal artifacts. To address that issue, this paper presents a novel reconstruction technique for providing an improvement of the SNR in SEMAC images without sacrificing the correction of metal artifacts. Materials and Methods: Low-rank approximation in each coil image is first performed to suppress the noise in the slice direction, because the signal is highly correlated between SEMAC-encoded slices. Secondly, SEMAC images are reconstructed by the best linear unbiased estimator (BLUE), also known as Gauss-Markov or weighted least squares. Noise levels and correlation in the receiver channels are considered for the sake of SNR optimization. To this end, since distorted excitation profiles are sparse, $l_1$ minimization performs well in recovering the sparse distorted excitation profiles and the sparse modeling of our approach offers excellent correction of metal-induced distortions. Results: Three images reconstructed using SEMAC, SEMAC with the conventional two-step noise reduction, and the proposed image denoising for metal MRI exploiting sparsity and low rank approximation algorithm were compared. The proposed algorithm outperformed two methods and produced 119% SNR better than SEMAC and 89% SNR better than SEMAC with the conventional two-step noise reduction. Conclusion: We successfully demonstrated that the proposed, novel algorithm for SEMAC, if compared with conventional de-noising methods, substantially improves SNR and reduces artifacts.

• Proceedings of the IEEK Conference
• /
• 2007.07a
• /
• pp.399-400
• /
• 2007

This paper proposes an regional analytic approach in image data space for radiographic image. Image is segmented into four regions, such as background, thickness, weld area and tube area, due to directional properties. Each region has its own gray level distribution, contrast range and noise property, originated from X-ray project mechanism and electric control system itself. Projection incorrectness and noise influence included on imaging quality is analyzed functionally and statistically. The experimental results shows not only segmental effects, but also visual edge evaluation.

• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• v.25 no.4
• /
• pp.327-336
• /
• 2021

In this paper, we will introduce the image processing methods for the remote pupillary light reflex measurement using the video taken by a general smartphone camera without a special device such as an infrared camera. We propose an algorithm for estimate the size of the pupil that changes with light using image data analysis without a learning process. In addition, we will introduce the results of visualizing the change in the pupil size by removing noise from the recorded data of the pupil size measured for each frame of the video. We expect that this study will contribute to the construction of an objective indicator for remote pupillary light reflex measurement in the situation where non-face-to-face communication has become common due to COVID-19 and the demand for remote diagnosis is increasing.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2018.10a
• /
• pp.530-532
• /
• 2018

Digital imaging equipment has been used for a variety of purposes in a wide range of society and has become an important element of the fourth industrial revolution. However, there are various causes of noise in the process of transmitting / receiving data and processing of the equipment, thus affecting the accuracy and reliability of the equipment. In this paper, we propose an image restoration algorithm based on pixel range set by standard deviation to effectively remove Salt and Pepper noise. In the conventional methods, the performance degrades in the edge and high frequency components of the image. However, the proposed method has better noise reduction performance than the conventional method by performing the noise elimination considering the image boundary. It has confirmed that the performance of such PSNR and magnified image, the experimental results showed that the proposed algorithm superior compared to existing methods.

• Journal of the Korean Society of Radiology
• /
• v.17 no.6
• /
• pp.843-849
• /
• 2023

This study attempted to determine the optimal algorithm after quantitatively analyzing noise, SNR, and CNR measurements by reconstructing four algorithms (Standard, Soft, Bone, and Detail) from head and neck CT images of patients who underwent implant surgery. As an analysis method, pixel values were calculated through the region of interest in the reconstructed image using the Image J program. For noise, SNR, and CNR, the region of interest was measured at the location of the pharynx, masseter muscle, and parotid gland in the image, and the mean and SD values were obtained. The values of SNR and CNR were calculated based on the given formula. As a result, the standard algorithm showed the lowest noise and the highest SNR. CNR was highest in the Soft algorithm, but showed no significant difference from the Standard algorithm. Therefore, it is believed that the Standard algorithm is the optimal algorithm for examining patients wearing intraoral implants in head and neck CT examinations. We hope that the data from this study will be used as basic data for image evaluation in head and neck CT examinations, and that the quality of images will be further improved through various algorithm changes. It is believed that this will be an opportunity to do so.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.9
• /
• pp.1176-1182
• /
• 2021

Recently, with the development of artificial intelligence and IoT technology, automation, and unmanned work are progressing in various fields, and the importance of image processing, which is the basis of AI object recognition, is increasing. In particular, in systems that require detailed data processing, noise removal is used as a preprocessing step, but the existing algorithm does not consider the noise level of the image, so it has the disadvantage of blurring in the filtering process. Therefore, in this paper, we propose a modified Gaussian filter that determines the weight by determining the noise level of the image. The proposed algorithm obtains the noise estimate for the AWGN of the image using quadtree segmentation, determines the Gaussian weight and the pixel weight, and obtains the final output by convolution with the local mask. To evaluate the proposed algorithm, it was simulated compared to the existing method, and superior performance was confirmed compared to the existing method.

• Proceedings of the Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography Conference
• /
• 2006.04a
• /
• pp.193-198
• /
• 2006

Among 242 Hyperion bands, there are 46 bands that contain completely no information and some other bands with various kinds of noise. It is mainly due to the atmosphenc absorption and the low signal-to-noise ratio. The visual inspection for selecting clean and stable bands is a simple practice, but is a manual, inefficient, and subjective Process. Though uncalibrated, overlapping, and all deep water absorption bands are removed, there still exist noisy bands. In this paper, we propose that the extrema ratio be measured for noise estimation and the unsupervised band selection be performed using the Expectation-Maximization algorithm. The Hyperion data were classified into 5 categories according to the image quality by visual inspection, and used as the reference data. The accuracy of the proposed method was compared with signal-to-noise ranking and entropy ranking. As a result, the proposed mettled was effective as preprocessing step for band selection.