• Smart Structures and Systems
• /
• v.23 no.3
• /
• pp.279-293
• /
• 2019

To ensure high quality data being used for data mining or feature extraction in the bridge structural health monitoring (SHM) system, a practical sensor fault diagnosis methodology has been developed based on the similarity of symmetric structure responses. First, the similarity of symmetric response is discussed using field monitoring data from different sensor types. All the sensors are initially paired and sensor faults are then detected pair by pair to achieve the multi-fault diagnosis of sensor systems. To resolve the coupling response issue between structural damage and sensor fault, the similarity for the target zone (where the studied sensor pair is located) is assessed to determine whether the localized structural damage or sensor fault results in the dissimilarity of the studied sensor pair. If the suspected sensor pair is detected with at least one sensor being faulty, field test could be implemented to support the regression analysis based on the monitoring and field test data for sensor fault isolation and reconstruction. Finally, a case study is adopted to demonstrate the effectiveness of the proposed methodology. As a result, Dasarathy's information fusion model is adopted for multi-sensor information fusion. Euclidean distance is selected as the index to assess the similarity. In conclusion, the proposed method is practical for actual engineering which ensures the reliability of further analysis based on monitoring data.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.3
• /
• pp.653-669
• /
• 2024

Dynamic scene deblurring is a complex computer vision problem owing to its difficulty to model mathematically. In this paper, we present a novel approach for image deblurring with the help of the sharp reference image, which utilizes the reference image for high-quality and high-frequency detail results. To better utilize the clear reference image, we develop an encoder-decoder network and two novel modules are designed to guide the network for better image restoration. The proposed Reference Extraction and Aggregation Module can effectively establish the correspondence between blurry image and reference image and explore the most relevant features for better blur removal and the proposed Spatial Feature Fusion Module enables the encoder to perceive blur information at different spatial scales. In the final, the multi-scale feature maps from the encoder and cascaded Reference Extraction and Aggregation Modules are integrated into the decoder for a global fusion and representation. Extensive quantitative and qualitative experimental results from the different benchmarks show the effectiveness of our proposed method.

• Journal of Korea Multimedia Society
• /
• v.23 no.12
• /
• pp.1540-1551
• /
• 2020

Aiming at the problem that the existing human behavior recognition algorithm cannot fully utilize the multi-level spatio-temporal information of the network, a human behavior recognition algorithm based on a dense three-dimensional residual network is proposed. First, the proposed algorithm uses a dense block of three-dimensional residuals as the basic module of the network. The module extracts the hierarchical features of human behavior through densely connected convolutional layers; Secondly, the local feature aggregation adaptive method is used to learn the local dense features of human behavior; Then, the residual connection module is applied to promote the flow of feature information and reduced the difficulty of training; Finally, the multi-layer local feature extraction of the network is realized by cascading multiple three-dimensional residual dense blocks, and use the global feature aggregation adaptive method to learn the features of all network layers to realize human behavior recognition. A large number of experimental results on benchmark datasets KTH show that the recognition rate (top-l accuracy) of the proposed algorithm reaches 93.52%. Compared with the three-dimensional convolutional neural network (C3D) algorithm, it has improved by 3.93 percentage points. The proposed algorithm framework has good robustness and transfer learning ability, and can effectively handle a variety of video behavior recognition tasks.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.45 no.5
• /
• pp.15-24
• /
• 2008

For high-dimensional classification tasks, such as face recognition, the number of samples is smaller than the dimensionality of the samples. In such cases, a problem encountered in linear discriminant analysis-based methods for dimension reduction is what is known as the small sample size (SSS) problem. Recently, to solve the SSS problem, a way of employing a dissimilarity-based classification(DBC) has been investigated. In DBC, an object is represented based on the dissimilarity measures among representatives extracted from training samples instead of the feature vector itself. In this paper, we propose a new method of optimizing DBCs using multi-level fusion strategies(MFS), in which fusion strategies are employed to represent features as well as to design classifiers. Our experimental results for benchmark face databases demonstrate that the proposed scheme achieves further improved classification accuracies.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.1
• /
• pp.51-73
• /
• 2023

Social media play a significant role in communicating information across the globe, connecting with loved ones, getting the news, communicating ideas, etc. However, a group of people uses social media to spread fake information, which has a bad impact on society. Therefore, minimizing fake news and its detection are the two primary challenges that need to be addressed. This paper presents a multi-modal deep learning technique to address the above challenges. The proposed modal can use and process visual and textual features. Therefore, it has the ability to detect fake information from visual and textual data. We used EfficientNetB0 and a sentence transformer, respectively, for detecting counterfeit images and for textural learning. Feature embedding is performed at individual channels, whilst fusion is done at the last classification layer. The late fusion is applied intentionally to mitigate the noisy data that are generated by multi-modalities. Extensive experiments are conducted, and performance is evaluated against state-of-the-art methods. Three real-world benchmark datasets, such as MediaEval (Twitter), Weibo, and Fakeddit, are used for experimentation. Result reveals that the proposed modal outperformed the state-of-the-art methods and achieved an accuracy of 86.48%, 82.50%, and 88.80%, respectively, for MediaEval (Twitter), Weibo, and Fakeddit datasets.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.7
• /
• pp.1888-1906
• /
• 2024

Aiming at the problems that the edge of melanoma image is fuzzy, the contrast with the background is low, and the hair occlusion makes it difficult to segment accurately, this paper proposes a model MSCNet for melanoma segmentation based on U-net frame. Firstly, a multi-scale pyramid fusion module is designed to reconstruct the skip connection and transmit global information to the decoder. Secondly, the contextural information conduction module is innovatively added to the top of the encoder. The module provides different receptive fields for the segmented target by using the hole convolution with different expansion rates, so as to better fuse multi-scale contextural information. In addition, in order to suppress redundant information in the input image and pay more attention to melanoma feature information, global channel attention mechanism is introduced into the decoder. Finally, In order to solve the problem of lesion class imbalance, this paper uses a combined loss function. The algorithm of this paper is verified on ISIC 2017 and ISIC 2018 public datasets. The experimental results indicate that the proposed algorithm has better accuracy for melanoma segmentation compared with other CNN-based image segmentation algorithms.

• Journal of Korea Multimedia Society
• /
• v.17 no.3
• /
• pp.277-286
• /
• 2014

In this paper, we propose a texture feature-based language identification by fusion of Gabor, MDLC (multi-lag directional local correlation), and co-occurrence features. In the proposed method, for a test image, Gabor magnitude images are first obtained by Gabor transform followed by magnitude operator. Moments for the Gabor magniude images are then computed and vectorized. MDLC images are then obtained by MDLC operator and their moments are computed and vectorized. GLCM (gray-level co-occurrence matrix) is next calculated from the test image and co-occurrence features are computed using the GLCM, and the features are also vectorized. The three vectors of the Gabor, MDLC, and co-occurrence features are fused into a feature vector. In classification, the WPCA (whitened principal component analysis) classifier, which is usually adopted in the face identification, searches the training feature vector most similar to the test feature vector. We evaluate the performance of our method by examining averaged identification rates for a test document image DB obtained by scanning of documents with 15 languages. Experimental results show that the proposed method yields excellent language identification with rather low feature dimension for the test DB.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.37 no.3
• /
• pp.209-219
• /
• 2019

Satellite imagery occurs geometric and radiometric errors due to external environmental factors at the acquired time, which in turn causes false-alarm in change detection. These errors should be eliminated by geometric and radiometric corrections. In this study, we propose a methodology that automatically and simultaneously performs geometric and radiometric corrections by using the SURF (Speeded-Up Robust Feature) algorithm and the mask filter. The MPs (Matching Points), which show invariant properties between multi-temporal imagery, extracted through the SURF algorithm are used for automatic geometric correction. Using the properties of the extracted MPs, PIFs (Pseudo Invariant Features) used for relative radiometric correction are selected. Subsequently, secondary PIFs are extracted by generated mask filters around the selected PIFs. After performing automatic using the extracted MPs, we could confirm that geometric and radiometric errors are eliminated as the result of performing the relative radiometric correction using PIFs in geo-rectified images.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.7
• /
• pp.2328-2344
• /
• 2022

2D human pose estimation still faces difficulty in low-resolution images. Most existing top-down approaches scale up the target human bonding box images to the large size and insert the scaled image into the network. Due to up-sampling, artifacts occur in the low-resolution target images, and the degraded images adversely affect the accurate estimation of the joint positions. To address this issue, we propose a multi-resolution input feature fusion network for human pose estimation. Specifically, the bounding box image of the target human is rescaled to multiple input images of various sizes, and the features extracted from the multiple images are fused in the network. Moreover, we introduce a guiding channel which induces the multi-resolution input features to alternatively affect the network according to the resolution of the target image. We conduct experiments on MS COCO dataset which is a representative dataset for 2D human pose estimation, where our method achieves superior performance compared to the strong baseline HRNet and the previous state-of-the-art methods.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.12
• /
• pp.5087-5102
• /
• 2015

Rapid popularization of smart cell phone equipped with camera has led to a number of new legal and criminal problems related to multimedia such as digital image, which makes cell phone source identification an important branch of digital image forensics. This paper proposes a classifier combination based source identification strategy for cell phone images. To identify the outlier cell phone models of the training sets in multi-class classifier, a one-class classifier is orderly used in the framework. Feature vectors including color filter array (CFA) interpolation coefficients estimation and multi-feature fusion is employed to verify the effectiveness of the classifier combination strategy. Experimental results demonstrate that for different feature sets, our method presents high accuracy of source identification both for the cell phone in the training sets and the outliers.