• Current Optics and Photonics
• /
• v.8 no.3
• /
• pp.215-224
• /
• 2024

In medium- and long-range optical imaging systems, atmospheric turbulence causes blurring and distortion of images, resulting in loss of image information. An image-restoration method based on an adaptive feature-fusion multi-input-multi-output (MIMO) dense U-shaped network (Unet) is proposed, to restore a single image degraded by atmospheric turbulence. The network's model is based on the MIMO-Unet framework and incorporates patch-embedding shallow-convolution modules. These modules help in extracting shallow features of images and facilitate the processing of the multi-input dense encoding modules that follow. The combination of these modules improves the model's ability to analyze and extract features effectively. An asymmetric feature-fusion module is utilized to combine encoded features at varying scales, facilitating the feature reconstruction of the subsequent multi-output decoding modules for restoration of turbulence-degraded images. Based on experimental results, the adaptive feature-fusion MIMO dense U-shaped network outperforms traditional restoration methods, CMFNet network models, and standard MIMO-Unet network models, in terms of image-quality restoration. It effectively minimizes geometric deformation and blurring of images.

• Proceedings of the IEEK Conference
• /
• 2000.09a
• /
• pp.915-918
• /
• 2000

In this paper, we propose an efficient feature vector extraction and decision fusion methods for the automatic classification of power system disturbances. Here, FFT and WPT(wavelet packet transform) are und to extract an appropriate feature for classifying power quality disturbances with variable properties. In particular, the WPT can be utilized to develop an adaptable feature extraction algorithm using best basis selection. Furthermore. the extracted feature vectors are applied as input to the decision fusion system which combines the decisions of several classifiers having complementary performances, leading to improvement of the classification performance. Finally, the applicability of the proposed approach is demonstrated using some simulations results obtained by analyzing power quality disturbances data generated by using Matlab.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.5 no.2
• /
• pp.157-163
• /
• 2005

In this paper, we present the multimodal system based on the fusion of two user-friendly biometric modalities: Iris and Face. In order to reach robust identification and verification we are going to combine two different biometric features. we specifically apply 2-D discrete wavelet transform to extract the feature sets of low dimensionality from iris and face. And then to obtain Reduced Joint Feature Vector(RJFV) from these feature sets, Direct Linear Discriminant Analysis (DLDA) is used in our multimodal system. In addition, the Synergetic Neural Network(SNN) is used to obtain matching score of the preprocessed data. This system can operate in two modes: to identify a particular person or to verify a person's claimed identity. Our results for both cases show that the proposed method leads to a reliable person authentication system.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.2
• /
• pp.544-564
• /
• 2022

Underwater images often suffer from color distortion, blurring and low contrast, which is caused by the propagation of light in the underwater environment being affected by the two processes: absorption and scattering. To cope with the poor quality of underwater images, this paper proposes a multiscale fusion underwater image enhancement method based on channel attention mechanism and local binary pattern (LBP). The network consists of three modules: feature aggregation, image reconstruction and LBP enhancement. The feature aggregation module aggregates feature information at different scales of the image, and the image reconstruction module restores the output features to high-quality underwater images. The network also introduces channel attention mechanism to make the network pay more attention to the channels containing important information. The detail information is protected by real-time superposition with feature information. Experimental results demonstrate that the method in this paper produces results with correct colors and complete details, and outperforms existing methods in quantitative metrics.

• Journal of Information Processing Systems
• /
• v.19 no.5
• /
• pp.673-687
• /
• 2023

Convolutional neural network-based deep learning technology is the most commonly used in image identification, but it requires large-scale data for training. Therefore, application in specific fields in which data acquisition is limited, such as in the military, may be challenging. In particular, the identification of ground weapon systems is a very important mission, and high identification accuracy is required. Accordingly, various studies have been conducted to achieve high performance using small-scale data. Among them, the ensemble method, which achieves excellent performance through the prediction average of the pre-trained models, is the most representative method; however, it requires considerable time and effort to find the optimal combination of ensemble models. In addition, there is a performance limitation in the prediction results obtained by using an ensemble method. Furthermore, it is difficult to obtain the ensemble effect using models with imbalanced classification accuracies. In this paper, we propose a transfer learning-based feature fusion technique for heterogeneous models that extracts and fuses features of pre-trained heterogeneous models and finally, fine-tunes hyperparameters of the fully connected layer to improve the classification accuracy. The experimental results of this study indicate that it is possible to overcome the limitations of the existing ensemble methods by improving the classification accuracy through feature fusion between heterogeneous models based on transfer learning.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.31B no.12
• /
• pp.59-71
• /
• 1994

This paper proposes a motion estimation method in video sequences based on the feature based matching and anistropic propagation. It measures translation and rotation parameters using a relaxation scheme at feature points and object orinted anistropic propagation in continuous and discontinuous regions. Also an iterative improvement motion extimation based on the strongly coupled module fusion and adaptive smoothing is proposed. Computer simulation results show the effectiveness of the proposed algorithm.

• Journal of Institute of Control, Robotics and Systems
• /
• v.19 no.12
• /
• pp.1081-1088
• /
• 2013

Hyperspectral cameras acquire reflectance values at many different wavelength bands. Dimensions tend to increase because spectral information is stored in each pixel. Several attempts have been made to reduce dimensional problems such as the feature selection using Adaboost and dimension reduction using the Simulated Annealing technique. We propose a novel material detection method that consists of four steps: feature band selection, feature extraction, SVM (Support Vector Machine) learning, and target and specific region detection. It is a combination of the band ratio method and Simulated Annealing algorithm based on detection rate. The experimental results validate the effectiveness of the proposed feature selection and band ratio method.

• Journal of Information Processing Systems
• /
• v.20 no.4
• /
• pp.535-549
• /
• 2024

Facial expressions (FEs) serve as fundamental components for human emotion assessment and human-computer interaction. Traditional convolutional neural networks tend to overlook valuable information during the FE feature extraction, resulting in suboptimal recognition rates. To address this problem, we propose a deep learning framework that incorporates hierarchical feature fusion, contextual data, and an attention mechanism for precise FE recognition. In our approach, we leveraged an enhanced VGGNet16 as the backbone network and introduced an improved group convolutional channel attention (GCCA) module in each block to emphasize the crucial expression features. A partial decoder was added at the end of the backbone network to facilitate the fusion of multilevel features for a comprehensive feature map. A reverse attention mechanism guides the model to refine details layer-by-layer while introducing contextual information and extracting richer expression features. To enhance feature distinguishability, we employed islanding loss in combination with softmax loss, creating a joint loss function. Using two open datasets, our experimental results demonstrated the effectiveness of our framework. Our framework achieved an average accuracy rate of 74.08% on the FER2013 dataset and 98.66% on the CK+ dataset, outperforming advanced methods in both recognition accuracy and stability.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.66 no.8
• /
• pp.1265-1271
• /
• 2017

In this paper, the speech parameter fusion method is studied to improve the performance of the conventional emotion recognition system. For this purpose, the combination of the parameters that show the best performance by combining the cepstrum parameters and the various pitch parameters used in the conventional emotion recognition system are selected. Various pitch parameters were generated using numerical and statistical methods using pitch of speech. Performance evaluation was performed on the emotion recognition system using Gaussian mixture model(GMM) to select the pitch parameters that showed the best performance in combination with cepstrum parameters. As a parameter selection method, sequential feature selection method was used. In the experiment to distinguish the four emotions of normal, joy, sadness and angry, fifteen of the total 56 pitch parameters were selected and showed the best recognition performance when fused with cepstrum and delta cepstrum coefficients. This is a 48.9% reduction in the error of emotion recognition system using only pitch parameters.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.10
• /
• pp.3729-3749
• /
• 2021

At present, deep convolution network-based salient object detection (SOD) has achieved impressive performance. However, it is still a challenging problem to make full use of the multi-scale information of the extracted features and which appropriate feature fusion method is adopted to process feature mapping. In this paper, we propose a new adjacency auxiliary network (AANet) based on multi-scale feature fusion for SOD. Firstly, we design the parallel connection feature enhancement module (PFEM) for each layer of feature extraction, which improves the feature density by connecting different dilated convolution branches in parallel, and add channel attention flow to fully extract the context information of features. Then the adjacent layer features with close degree of abstraction but different characteristic properties are fused through the adjacent auxiliary module (AAM) to eliminate the ambiguity and noise of the features. Besides, in order to refine the features effectively to get more accurate object boundaries, we design adjacency decoder (AAM_D) based on adjacency auxiliary module (AAM), which concatenates the features of adjacent layers, extracts their spatial attention, and then combines them with the output of AAM. The outputs of AAM_D features with semantic information and spatial detail obtained from each feature are used as salient prediction maps for multi-level feature joint supervising. Experiment results on six benchmark SOD datasets demonstrate that the proposed method outperforms similar previous methods.