• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.38A no.2
• /
• pp.174-182
• /
• 2013

Most methods for fusion-based finger vein recognition were to fuse different features or matching scores from more than one trait to improve performance. To overcome the shortcomings of "the curse of dimensionality" and additional running time in feature extraction, in this paper, we propose a finger vein recognition technology based on matching score-level fusion of a single trait. To enhance the quality of finger vein image, the contrast-limited adaptive histogram equalization (CLAHE) method is utilized and it improves the local contrast of normalized image after ROI detection. Gabor features are then extracted from eight channels based on a bank of Gabor filters. Instead of using the features for the recognition directly, we analyze the contributions of Gabor feature from each channel and apply a weighted matching score-level fusion rule to get the final matching score, which will be used for the last recognition. Experimental results demonstrate the CLAHE method is effective to enhance the finger vein image quality and the proposed matching score-level fusion shows better recognition performance.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.8 no.11
• /
• pp.4118-4136
• /
• 2014

To preserve the spatial consistency of low-level features, generalized Riesz-wavelet transform (GRWT) is adopted for fusing multi-modality images. The proposed method can capture the directional image structure arbitrarily by exploiting a suitable parameterization fusion model and additional structural information. Its fusion patterns are controlled by a heuristic fusion model based on image phase and coherence features. It can explore and keep the structural information efficiently and consistently. A performance analysis of the proposed method applied to real-world images demonstrates that it is competitive with the state-of-art fusion methods, especially in combining structural information.

• Nuclear Engineering and Technology
• /
• v.55 no.1
• /
• pp.222-228
• /
• 2023

This study aimed to analyze the applicability of the improved median filter in positron emission tomography (PET)/magnetic resonance (MR) fusion images based on parallel imaging using generalized autocalibrating partially parallel acquisition (GRAPPA). In this study, a PET/MR fusion imaging system based on a 3.0T magnetic field and ¹⁸F radioisotope were used. An improved median filter that can set a mask of the median value more efficiently than before was modeled and applied to the acquired image. As quantitative evaluation parameters of the noise level, the contrast to noise ratio (CNR) and coefficient of variation (COV) were calculated. Additionally, no-reference-based evaluation parameters were used to analyze the overall image quality. We confirmed that the CNR and COV values of the PET/MR fusion images to which the improved median filter was applied improved by approximately 3.32 and 2.19 times on average, respectively, compared to the noisy image. In addition, the no-reference-based evaluation results showed a similar trend for the noise-level results. In conclusion, we demonstrated that it can be supplemented by using an improved median filter, which suggests the problem of image quality degradation of PET/MR fusion images that shortens scan time using GRAPPA.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.1334-1336
• /
• 2003

On the basis of comprehensive analysis and summarization of the image fusion algorithms provided by PCI Geomatica software, deficiencies in image fusion processing functions of this software are put forwarded in this paper. This limitation could be improved by further developing PCI Geomatica on the user’ side. Five effective algorithms could be added into PCI Geomatica. In this paper, the detailed description of how to customize and further develop PCI Geomatica by using Microsoft Visual C++ 6.0, PCI SDK Kit and GDB technique is also given. Through this way, the remote sensing imagery fusion functions of PCI Geomatica software can be extended.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.5
• /
• pp.2253-2272
• /
• 2018

We propose a deep learning method for multi-focus image fusion. Unlike most existing pixel-level fusion methods, either in spatial domain or in transform domain, our method directly learns an end-to-end fully convolutional two-stream network. The framework maps a pair of different focus images to a clean version, with a chain of convolutional layers, fusion layer and deconvolutional layers. Our deep fusion model has advantages of efficiency and robustness, yet demonstrates state-of-art fusion quality. We explore different parameter settings to achieve trade-offs between performance and speed. Moreover, the experiment results on our training dataset show that our network can achieve good performance with subjective visual perception and objective assessment metrics.

• Korean Journal of Remote Sensing
• /
• v.19 no.4
• /
• pp.329-339
• /
• 2003

In this study, an approach of image fusion in decision level has been proposed for unsupervised image classification using the images acquired from multiple sensors with different characteristics. The proposed method applies separately for each sensor the unsupervised image classification scheme based on spatial region growing segmentation, which makes use of hierarchical clustering, and computes iteratively the maximum likelihood estimates of fuzzy class vectors for the segmented regions by EM(expected maximization) algorithm. The fuzzy class vector is considered as an indicator vector whose elements represent the probabilities that the region belongs to the classes existed. Then, it combines the classification results of each sensor using the fuzzy class vectors. This approach does not require such a high precision in spatial coregistration between the images of different sensors as the image fusion scheme of pixel level does. In this study, the proposed method has been applied to multispectral SPOT and AIRSAR data observed over north-eastern area of Jeollabuk-do, and the experimental results show that it provides more correct information for the classification than the scheme using an augmented vector technique, which is the most conventional approach of image fusion in pixel level.

• Korean Journal of Remote Sensing
• /
• v.26 no.5
• /
• pp.581-591
• /
• 2010

In this paper, we proposed a new wavelet-based image fusion algorithm, which has advantages in both frequency and spatial domains for signal analysis. The developed algorithm compares the ratio of SAR image signal to optical image signal and assigns the SAR image signal to the fused image if the ratio is larger than a predefined threshold value. If the ratio is smaller than the threshold value, the fused image signal is determined by a weighted sum of optical and SAR image signal. The fusion rules consider the ratio of SAR image signal to optical image signal, image gradient and local variance of each image signal. We evaluated the proposed algorithm using Ikonos and TerraSAR-X satellite images. The proposed method showed better performance than the conventional methods which take only relatively strong SAR image signals in the fused image, in terms of entropy, image clarity, spatial frequency and speckle index.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.656-658
• /
• 2022

The purpose of infrared and visible image fusion is to integrate images of different modes with different details into a result image with rich information, which is convenient for high-level computer vision task. Considering many deep networks only work in a single scale, this paper proposes a novel image fusion based on three-scale dense network to preserve the content and key target features from the input images in the fused image. It comprises an encoder, a three-scale block, a fused strategy and a decoder, which can capture incredibly rich background details and prominent target details. The encoder is used to extract three-scale dense features from the source images for the initial image fusion. Then, a fusion strategy called l₁-norm to fuse features of different scales. Finally, the fused image is reconstructed by decoding network. Compared with the existing methods, the proposed method can achieve state-of-the-art fusion performance in subjective observation.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.248-250
• /
• 2003

An automatic approach and strategy for extracting building information from aerial images using combined image analysis and interpretation techniques is described in this paper. A dense DSM is obtained by stereo image matching. Multi-band classification, DSM, texture segmentation and Normalised Difference Vegetation Index (NDVI) are used to reveal building interest areas. Then, based on the derived approximate building areas, a shape modelling algorithm based on the level set formulation of curve and surface motion has been used to precisely delineate the building boundaries. Data fusion, based on the Dempster-Shafer technique, is used to interpret simultaneously knowledge from several data sources of the same region, to find the intersection of propositions on extracted information derived from several datasets, together with their associated probabilities. A number of test areas, which include buildings with different sizes, shape and roof colour have been investigated. The tests are encouraging and demonstrate that the system is effective for building extraction, and the determination of more accurate elevations of the terrain surface.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.13 no.6
• /
• pp.313-319
• /
• 2018

We propose a post-processing algorithm to improve the quality of the RGB image generated by deep learning based colorization from the gray-scale image of an infrared camera. Wavelet fusion is used to generate a new luminance component of the RGB image luminance component from the deep learning model and the luminance component of the infrared camera. PSNR is increased for all experimental images by applying the proposed algorithm to RGB images generated by two deep learning models of SegNet and DCGAN. For the SegNet model, the average PSNR is improved by 1.3906dB at level 1 of the Haar wavelet method. For the DCGAN model, PSNR is improved 0.0759dB on the average at level 5 of the Daubechies wavelet method. It is also confirmed that the edge components are emphasized by the post-processing and the visibility is improved.