• Journal of the Korean Institute of Intelligent Systems
• /
• v.1 no.2
• /
• pp.65-71
• /
• 1991

A new algorithm is proposed for the automatic detection of pulmonary blood vessels by simulating the human recognition process by the pyramid images. Large and wide vessels are detected from the most compressed level, followed by the detection of small and narrow ones from the less compressed images with FCM(fuzzy c means). As the proposed algorithm detects blood vessels orderly according to their size, there is no need to consdier the variation of parameters and the brance points which should be considered in other detection algorithms.

• IEIE Transactions on Smart Processing and Computing
• /
• v.5 no.6
• /
• pp.390-394
• /
• 2016

This paper presents a new comparison method for haze-removal algorithms in next-generation automotive systems. Compared to previous peak signal-to-noise ratio-based comparisons, which measure similarity, the proposed modulation transfer function-based method checks sharpness to select a more suitable haze-removal algorithm for lane detection. Among the practical filtering schemes used for a haze-removal algorithm, experimental results show that Gaussian filtering effectively preserves the sharpness of road images, enhancing lane detection accuracy.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.89-92
• /
• 2005

Using natural speech commands for controlling a human-robot is an interesting topic in the field of robotics. In this paper, our main focus is on the verification of a speaker who gives a command to decide whether he/she is an authorized person for commanding. Among possible dynamic features of natural speech, pitch period is one of the most important ones for characterizing speech signals and it differs usually from person to person. However, current techniques of pitch detection are still not to a desired level of accuracy and robustness. When the signal is noisy or there are multiple pitch streams, the performance of most techniques degrades. In this paper, we propose a two-level approach for pitch detection which in compare with standard pitch detection algorithms, not only increases accuracy, but also makes the performance more robust to noise. In the first level of the proposed approach we discriminate voiced from unvoiced signals based on a neural classifier that utilizes cepstrum sequences of speech as an input feature set. Voiced signals are then further processed in the second level using a modified standard AMDF-based pitch detection algorithm to determine their pitch periods precisely. The experimental results show that the accuracy of the proposed system is better than those of conventional pitch detection algorithms for speech signals in clean and noisy environments.

• Journal of the Korea Society of Computer and Information
• /
• v.15 no.5
• /
• pp.57-65
• /
• 2010

In this paper, we propose a new real-time algorithm detecting the flame and smoke in digital CCTV images. Because the forest fire causes the enormous human life and damage of property, the early management according to the early sensing is very important. The proposed algorithm for monitoring forest fire is classified into the flame sensing and detection of smoke. The flame sensing algorithm detects a flame through the conditional test at YCbCr color model from the single frame. For the detection of smoke, firstly the background range is set by using differences between current picture and the average picture among the adjacent frames in the weighted value, and the pixels which get out of this range and have a gray-scale are detected in the smoke area. Because the proposed flame sensing algorithm is stronger than the existing algorithms in the change of the illuminance according to the quantity of sunshine, and the smoke detection algorithm senses the pixel of a gray-scale with the smoke considering the amount of change for unit time, the effective early forest fire detection is possible. The experimental results indicate that the proposed algorithm provides better performance than existing algorithms.

• Journal of Biomedical Engineering Research
• /
• v.44 no.2
• /
• pp.118-124
• /
• 2023

Many recent studies have reported that the quality of input learning data was vital to the detection of regions of interest. However, due to a lack of research on the quality of learning data on lesion detetcting using gastroscopy, we aimed to quantify the impact of quality difference in endoscopic images to lesion detection models using Image Quality Assessment (IQA) algorithms. Through IQA methods such as BRISQUE (Blind/Referenceless Image Spatial Quality Evaluation), Laplacian Score, and PSNR (Peak Signal-To-Noise) algorithm on 430 sheets of high quality data (HQD) and 430 sheets of low quality data (PQD), we showed that there were significant differences between high and low quality images in lesion detecting through BRISQUE and Laplacian scores (p<0.05). The PSNR value showed 10.62±1.76 dB on average, illustrating the lower lesion detection performance of PQD than HQD. In addition, F1-Score of HQD showed higher detection performance at 77.42±3.36% while F1-Score of PQD showed 66.82±9.07%. Through this study, we hope to contribute to future gastroscopy lesion detection assistance systems that involve IQA algorithms by emphasizing the importance of using high quality data over lower quality data.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.5
• /
• pp.1433-1449
• /
• 2023

In recent years, the rapid development of social networks has led to a rapid increase in the amount of information available on the Internet, which contains a large amount of sensitive information related to pornography, politics, and terrorism. In the aspect of sensitive image detection, the existing machine learning algorithms are confronted with problems such as large model size, long training time, and slow detection speed when auditing and supervising. In order to detect sensitive images more accurately and quickly, this paper proposes a multiclassification sensitive image detection method based on lightweight Convolutional Neural Network. On the basis of the EfficientNet model, this method combines the Ghost Module idea of the GhostNet model and adds the SE channel attention mechanism in the Ghost Module for feature extraction training. The experimental results on the sensitive image data set constructed in this paper show that the accuracy of the proposed method in sensitive information detection is 94.46% higher than that of the similar methods. Then, the model is pruned through an ablation experiment, and the activation function is replaced by Hard-Swish, which reduces the parameters of the original model by 54.67%. Under the condition of ensuring accuracy, the detection time of a single image is reduced from 8.88ms to 6.37ms. The results of the experiment demonstrate that the method put forward has successfully enhanced the precision of identifying multi-class sensitive images, significantly decreased the number of parameters in the model, and achieved higher accuracy than comparable algorithms while using a more lightweight model design.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.3
• /
• pp.91-98
• /
• 2021

Today's information and communication technology is rapidly developing, the security of IT infrastructure is becoming more important, and at the same time, cyber attacks of various forms are becoming more advanced and sophisticated like intelligent persistent attacks (Advanced Persistent Threat). Early defense or prediction of increasingly sophisticated cyber attacks is extremely important, and in many cases, the analysis of network-based intrusion detection systems (NIDS) related data alone cannot prevent rapidly changing cyber attacks. Therefore, we are currently using data generated by intrusion detection systems to protect against cyber attacks described above through Host-based Intrusion Detection System (HIDS) data analysis. In this paper, we conducted a comparative study on machine learning algorithms using LID-DS (Leipzig Intrusion Detection-Data Set) host-based intrusion detection data including thread information, metadata, and buffer data missing from previously used data sets. The algorithms used were Decision Tree, Naive Bayes, MLP (Multi-Layer Perceptron), Logistic Regression, LSTM (Long Short-Term Memory model), and RNN (Recurrent Neural Network). Accuracy, accuracy, recall, F1-Score indicators and error rates were measured for evaluation. As a result, the LSTM algorithm had the highest accuracy.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.2
• /
• pp.31-41
• /
• 2024

Deep learning models show excellent performance in tasks such as image classification and object detection in the field of computer vision, and are used in various ways in actual industrial sites. Recently, research on improving robustness has been actively conducted, along with pointing out that this deep learning model is vulnerable to hostile examples. A hostile example is an image in which small noise is added to induce misclassification, and can pose a significant threat when applying a deep learning model to a real environment. In this paper, we tried to confirm the robustness of the edge-learning classification model and the performance of the adversarial example detection model using it for adversarial examples of various algorithms. As a result of robustness experiments, the basic classification model showed about 17% accuracy for the FGSM algorithm, while the edge-learning models maintained accuracy in the 60-70% range, and the basic classification model showed accuracy in the 0-1% range for the PGD/DeepFool/CW algorithm, while the edge-learning models maintained accuracy in 80-90%. As a result of the adversarial example detection experiment, a high detection rate of 91-95% was confirmed for all algorithms of FGSM/PGD/DeepFool/CW. By presenting the possibility of defending against various hostile algorithms through this study, it is expected to improve the safety and reliability of deep learning models in various industries using computer vision.

• MALSORI
• /
• no.50
• /
• pp.85-97
• /
• 2004

One of the important problems in speech recognition is to accurately detect the existence of speech in adverse environments. The speech detection problem becomes severer when recognition systems are used over the telephone network, especially in a wireless network and a noisy environment. In this paper, we propose a robust speech detection algorithm, which detects speech boundaries accurately by selecting useful bands adaptively to noisy environments. The bands where noises are mainly distributed, so called, noise-centric bands are introduced. In this paper, we compare two different speech detection algorithms with the proposed algorithm, and evaluate them on noisy environments. The experimental results show the excellence of the proposed speech detection algorithm.

• Proceedings of the IEEK Conference
• /
• 2000.06d
• /
• pp.7-10
• /
• 2000

There are many Problems such as low detection ratio, velocity and increase of false hit ratio on the detection of gradual scene changes with the previous shot transition detection algorithms. In this paper, we Propose an improved dissolve detection method using color information on low-frequency subband and edge elements on high-frequency subband. The Possible dissolve transition are found by analyzing the edge change ratio in the high-frequency subband with edge elements of each direction. Using the double chromatic difference on the lowest frequency subband, we have the improvement of the dissolve detection ratio. The simulation results show that the performance of the proposed algorithm is better than the conventional one for dissolve detection on a diverse set of uncompressed video sequences.