• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.9
• /
• pp.3797-3822
• /
• 2020

The inspection of cracks on the surface of tunnel linings is a common method of evaluate the condition of the tunnel. In particular, determining the thickness and shape of a crack is important because it indicates the external forces applied to the tunnel and the current condition of the concrete structure. Recently, several automatic crack detection methods have been proposed to identify cracks using captured tunnel lining images. These methods apply an image-segmentation mechanism with well-annotated datasets. However, generating the ground truths requires many resources, and the small proportion of cracks in the images cause a class-imbalance problem. A weakly annotated dataset is generated to reduce resource consumption and avoid the class-imbalance problem. However, the use of the dataset results in a large number of false positives and requires post-processing for accurate crack detection. To overcome these issues, we propose a crack detection method using a ternary classifier. The proposed method significantly reduces the false positive rate, and the performance (as measured by the F1 score) is improved by 0.33 compared to previous methods. These results demonstrate the effectiveness of the proposed method.

• Journal of KIISE:Software and Applications
• /
• v.36 no.11
• /
• pp.912-919
• /
• 2009

A novel algorithm using 2D tensor voting and edge-based approach is proposed for text detection in natural scene images. The tensor voting is used based on the fact that characters in a text line are usually close together on a smooth curve and therefore the tokens corresponding to centers of these characters have high curve saliency values. First, a suitable edge-based method is used to find all possible text regions. Since the false positive rate of text detection result generated from the edge-based method is high, 2D tensor voting is applied to remove false positives and find only text regions. The experimental results show that our method successfully detects text regions in many complex natural scene images.

• Journal of the Korea Society of Computer and Information
• /
• v.17 no.5
• /
• pp.33-40
• /
• 2012

In this paper we propose an anomaly detection scheme to detect new attack paths or new attack methods without false positives by monitoring HTTP Outbound Traffic after efficient training. Our proposed scheme detects web-based attacks by comparing tags or javascripts of HTTP Outbound Traffic with normal behavioral models which apply HMM(Hidden Markov Model). Through the verification analysis under the real-attacked environment, we show that our scheme has superior detection capability of 0.0001% false positive and 96% detection rate.

• Journal of the Korea Society of Computer and Information
• /
• v.22 no.12
• /
• pp.79-85
• /
• 2017

In this paper, we propose a CNN-based swimmer detection algorithm. Every year, water safety accidents have been occurred frequently, and accordingly, intelligent video surveillance systems are being developed to prevent accidents. Intelligent video surveillance system is a real-time system that detects objects which users want to do. It classifies or detects objects in real-time using algorithms such as GMM (Gaussian Mixture Model), HOG (Histogram of Oriented Gradients), and SVM (Support Vector Machine). However, HOG has a problem that it cannot accurately detect the swimmer in a complex and dynamic environment such as a beach. In other words, there are many false positives that detect swimmers as waves and false negatives that detect waves as swimmers. To solve this problem, in this paper, we propose a swimmer detection algorithm using CNN (Convolutional Neural Network), specialized for small object sizes, in order to detect dynamic objects and swimmers more accurately and efficiently in complex environment. The proposed CNN sets the size of the input image and the size of the filter used in the convolution operation according to the size of objects. In addition, the aspect ratio of the input is adjusted according to the ratio of detected objects. As a result, experimental results show that the proposed CNN-based swimmer detection method performs better than conventional techniques.

• Journal of the Korea Society for Simulation
• /
• v.17 no.2
• /
• pp.83-90
• /
• 2008

We introduce the coordination among the intrusion detection agents by BBA(BlackBoard Architecture) that belongs to the field of distributed artificial intelligence. The system which uses BBA for the coordination can be easily expanded by adding new agents and increasing the number of BB(BlackBoard) levels. Several simulation tests performed on the targer network will illustrate our techniques. And this paper applies PBN(Policy-Based Network) to reduce the false positives that is one of the main problems of IDS. The performance obtained from the coordination of intrusion detection agent with PBN is compared against the corresponding non PBN type intrusion detection agent. The application of the research results lies in the experimentation of the various security policies according to the network types in selecting the best security policy that is most suitable for a given network.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.17 no.3
• /
• pp.634-640
• /
• 2013

Existing patterns and database search, string search unit search results for a lot of false positives, a simple search technique unreliable. In addition, the same conditions in addition to other search methods implemented due to wasted of resources and enforcement have been causing a waste of time. Therefore, regular expression and correlation analysis method by applying an integrated linkage information search module is to develop in this paper. From this, existing string search technique that has been noted as a problem by reducing the economic impact false positive and reliability to develop method that will information search secure.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.221-235
• /
• 2022

Manual inspection of steel box girders on long span bridges is time-consuming and labor-intensive. The quality of inspection relies on the subjective judgements of the inspectors. This study proposes an automated approach to detect and segment cracks in high-resolution images. An end-to-end cascaded framework is proposed to first detect the existence of cracks using a deep convolutional neural network (CNN) and then segment the crack using a modified U-Net encoder-decoder architecture. A Naïve Bayes data fusion scheme is proposed to reduce the false positives and false negatives effectively. To generate the binary crack mask, first, the original images are divided into 448 × 448 overlapping image patches where these image patches are classified as cracks versus non-cracks using a deep CNN. Next, a modified U-Net is trained from scratch using only the crack patches for segmentation. A customized loss function that consists of binary cross entropy loss and the Dice loss is introduced to enhance the segmentation performance. Additionally, a Naïve Bayes fusion strategy is employed to integrate the crack score maps from different overlapping crack patches and to decide whether a pixel is crack or not. Comprehensive experiments have demonstrated that the proposed approach achieves an 81.71% mean intersection over union (mIoU) score across 5 different training/test splits, which is 7.29% higher than the baseline reference implemented with the original U-Net.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.37 no.6
• /
• pp.25-37
• /
• 2000

The trajectories of feature points can be defined by the correspondences between points in consecutive frames. The correspondence problem is known to be difficult to solve because false positives and false negatives almost always exist in real image sequences. In this paper, we propose a robust feature tracking algorithm considering incomplete trajectories such as entering and/or vanishing trajectories. The trajectories of feature points are determined by calculating the matching measure, which is defined as the minimum weighted Euclidean distance between two feature points. The weights are automatically updated in order to properly reflect the motion characteristics. We solve the correspondence problem as an optimal graph search problem, considering that the existence of false feature points may have serious effect on the correspondence search. The proposed algorithm finds a local optimal correspondence so that the effect of false feature point can be minimized in the decision process. The time complexity of the proposed graph search algorithm is given by O(mn) in the best case and O($m^2n$) in the worst case, where m and n arc the number of feature points in two consecutive frames. By considering false feature points and by properly reflecting motion characteristics, the proposed algorithm can find trajectories correctly and robustly, which has been shown by experimental results.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.1
• /
• pp.161-171
• /
• 2014

When the Hough transform is applied to identify an instance of a given model, the output is typically a histogram of votes cast by a set of image features into a parameter space. The next step is to threshold the histogram of counts to hypothesize a given match. The question is "What is a reasonable choice of the threshold?" In a standard implementation of the Hough transform, the threshold is selected heuristically, e.g., some fraction of the highest cell count. Setting the threshold too low can give rise to a false alarm of a given shape(Type I error). On the other hand, setting the threshold too high can result in mis-detection of a given shape(Type II error). In this paper, we derive two conditional probability functions of cell counts in the accumulator array of the generalized Hough transform(GHough), that can be used to select a scientific threshold at the peak detection stage of the Ghough.

• Journal of KIISE:Software and Applications
• /
• v.36 no.7
• /
• pp.590-606
• /
• 2009

We present a static analyzer that detects memory leaks in C programs. It achieves relatively high accuracy at a relatively low cost on SPEC2000 benchmarks and several open-source software packages, demonstrating its practicality and competitive edge against other reported analyzers: for a set of benchmarks totaling 1,777 KLOCs, it found 332 bugs with 47 additional false positives (a 12.4% false-positive ratio), and the average analysis speed was 720 LOC/sec. We separately analyze each procedure's memory behavior into a summary that is used in analyzing its call sites. Each procedural summary is parameterized by the procedure's call context so that it can be instantiated at different call sites. What information to capture in each procedural summary has been carefully tuned so that the summary should not lose any common memory-leak-related behaviors in real-world C program. Because each procedure is summarized by conventional fixpoint iteration over the abstract semantics ('a la abstract interpretation), the analyzer naturally handles arbitrary call cycles from direct or indirect recursive calls.