• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.5
• /
• pp.1466-1488
• /
• 2022

Recently, the importance and necessity of artificial intelligence (AI), especially machine learning, has been emphasized. In fact, studies are actively underway to solve complex and challenging problems through the use of AI systems, such as intelligent CCTVs, intelligent AI security systems, and AI surgical robots. Information security that involves analysis and response to security vulnerabilities of software is no exception to this and is recognized as one of the fields wherein significant results are expected when AI is applied. This is because the frequency of malware incidents is gradually increasing, and the available security technologies are limited with regard to the use of software security experts or source code analysis tools. We conducted a study on MalDC, a technique that converts malware into images using machine learning, MalDC showed good performance and was able to analyze and classify different types of malware. MalDC applies a preprocessing step to minimize the noise generated in the image conversion process and employs an image augmentation technique to reinforce the insufficient dataset, thus improving the accuracy of the malware classification. To verify the feasibility of our method, we tested the malware classification technique used by MalDC on a dataset provided by Microsoft and malware data collected by the Korea Internet & Security Agency (KISA). Consequently, an accuracy of 97% was achieved.

• Korean Journal of Remote Sensing
• /
• v.30 no.6
• /
• pp.817-827
• /
• 2014

In the satellite remote sensing, the operational environment of the satellite sensor causes image degradation during the image acquisition. The degradation results in noise and blurring which badly affect identification and extraction of useful information in image data. This study proposes a maximum a posteriori (MAP) estimation using Point-Jacobian iteration to restore a degraded image. The proposed method assumes a Gaussian additive noise and Markov random field of spatial continuity. The proposed method employs a neighbor window of spoke type which is composed of 8 line windows at the 8 directions, and a boundary adjacency measure of Mahalanobis square distance between center and neighbor pixels. For the evaluation of the proposed method, a pixel-wise classification was used for simulation data using various patterns similar to the structure exhibited in high resolution imagery and an unsupervised segmentation for the remotely-sensed image data of 1 mspatial resolution observed over the north area of Anyang in Korean peninsula. The experimental results imply that it can improve analytical accuracy in the application of remote sensing high resolution imagery.

• IEIE Transactions on Smart Processing and Computing
• /
• v.6 no.1
• /
• pp.53-59
• /
• 2017

Optical character recognition (OCR) automatically recognizes text in an image. OCR is still a challenging problem in computer vision. A successful solution to OCR has important device applications, such as text-to-speech conversion and automatic document classification. In this work, we analyze character recognition performance using the current state-of-the-art deep-learning structures. One is the AlexNet structure, another is the LeNet structure, and the other one is the SPNet structure. For this, we have built our own dataset that contains digits and upper- and lower-case characters. We experiment in the presence of salt-and-pepper noise or Gaussian noise, and report the performance comparison in terms of recognition error. Experimental results indicate by five-fold cross-validation that the SPNet structure (our approach) outperforms AlexNet and LeNet in recognition error.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.2
• /
• pp.207-213
• /
• 2022

Recently, with the improvement of the performance of IoT technology and AI, automation and unmanned work are progressing in a wide range of fields, and interest in image processing, which is the basis of automation such as object recognition and object classification, is increasing. Image noise removal is an important process used as a preprocessing step in an image processing system, and various studies have been conducted. However, in most cases, it is difficult to preserve detailed information due to the smoothing effect in high-frequency components such as edges. In this paper, we propose an algorithm to restore damaged images in AWGN(additive white Gaussian noise) using fuzzy weights based on Gaussian distribution. The proposed algorithm switched the filtering process by comparing the filtering mask and the noise estimate with each other, and reconstructed the image by calculating the fuzzy weights according to the low-frequency and high-frequency components of the image.

• 제어로봇시스템학회:학술대회논문집
• /
• 1997.10a
• /
• pp.365-370
• /
• 1997

In this paper we suggest a development of surface defect inspection algorithms for cold mill strip using tree structure. The defects which exist in a surface of cold mill strip have a scattering or singular distribution. This paper consists of preprocessing, feature extraction and defect classification. By preprocessing, the binarized defect image is achieved. In this procedure, Top-hit transform, adaptive thresholding, thinning and noise rejection are used. Especially, Top-hit transform using local min/max operation diminishes the effect of bad lighting. In feature extraction, geometric, moment, co-occurrence matrix, histogram-ratio features are calculated. The histogram-ratio feature is taken from the gray-level image. For the defect classification, we suggest a tree structure of which nodes are multilayer neural network clasifiers. The proposed algorithm reduced error rate comparing to one stage structure.

• The KIPS Transactions:PartB
• /
• v.16B no.5
• /
• pp.377-384
• /
• 2009

A new algorithm in order to classify various contents in the image documents, such as text, figure, graph, table, etc. is proposed in this paper by classifying contents using texture-based PCA, and by segmenting document images using local entropy-based histogram. Local entropy and histogram made the binarization of image document not only robust to various transformation and noise, but also easy and less time-consuming. And texture-based PCA algorithm for each segmented region was taken notice of each content in the image documents having different texture information. Through this, it was not necessary to establish any pre-defined structural information, and advantages were found from the fact of fast and efficient classification. The result demonstrated that the proposed method had shown better performances of segmentation and classification for various images, and is also found superior to previous methods by its efficiency.

• Journal of the Semiconductor & Display Technology
• /
• v.13 no.2
• /
• pp.7-12
• /
• 2014

A vehicle license plate includes the most important information for recognition and classification of the vehicle. In this paper, we propose a vehicle license plate recognition system using image binarization and template matching. In the proposed system, an image of the vehicle license plate is converted into a gray scale image and the gray image undergoes the binarization process. Finally, the numbers on the plate are extracted from the binary image using the template matching algorithm.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.29 no.7C
• /
• pp.937-945
• /
• 2004

A binary decision model which is used to denoising has demerits to measure the precise ratio of signal to noise because of only a binary classification. To supplement these demerits, complex statistical model and undecimated wavelet transform are generally exploited. In this paper, we propose a noise reduction method using a multi-level decision model for measuring the ratio of noise in noisy image. The propose method achieves good denoising performance with orthogonal wavelet transform because the ratio of signal to noise can be calculated to multi-valued form. In simulation results, the proposed denoising method outperforms 0.1dB in the PSNR sense than the state of art denoising algorithms using orthogonal wavelet transform.

• Korean Journal of Geomatics
• /
• v.4 no.1
• /
• pp.1-8
• /
• 2004

In the middle-resolution remote sensing, the Ground Sampled Distance (GSD) that the detector senses and samples is generally larger than the actual size of the objects (or materials) of interest, and so several objects are embedded in a single pixel. In this case, as it is impossible to detect these objects by the conventional spatial-based image processing techniques, it has to be carried out at sub-pixel level through spectral properties. In this paper, we explain the sub-pixel analysis algorithm, also known as the Linear Spectral Mixing (LSM) model, which has been experimented using the Hyperion data. To find Endmembers used as the prior knowledge for LSM model, we applied the concept of the convex geometry on the two-dimensional scatter plot. The Atmospheric Correction and Minimum Noise Fraction techniques are presented for the pre-processing of Hyperion data. As LSM model is the simplest approach in sub-pixel analysis, the results of our experiment is not good. But we intend to say that the sub-pixel analysis shows much more information in comparison with the image classification.

• Proceedings of the IEEK Conference
• /
• 1999.11a
• /
• pp.525-528
• /
• 1999

Abstract - In this paper, a segmentation method for brain Magnetic Resonance(MR) image using region clustering technique with statistical distribution of gradient image and fuzzy rules is described. The brain MRI consists of gray matter and white matter, cerebrospinal fluid. But due to noise, overlap, vagueness, and various parameters, segmentation of MR image is a very difficult task. We use gradient information rather than intensity directly from the MR images and find appropriate thresholds for region classification using gradient approximation, rayleigh distribution function, region clustering, and merging techniques. And then, we propose the adaptive fuzzy rules in order to extract anatomical structures and diseases from brain MR image data. The experimental results shows that the proposed segmentation algorithm given better performance than traditional segmentation techniques.