• International Journal of Computer Science & Network Security
• /
• v.23 no.4
• /
• pp.39-47
• /
• 2023

This study compares various transformation techniques for multifocus image fusion. Multi-focus image fusion is a procedure of merging multiple images captured at unalike focus distances to produce a single composite image with improved sharpness and clarity. In this research, the purpose is to compare different popular frequency domain approaches for multi-focus image fusion, such as Discrete Wavelet Transforms (DWT), Stationary Wavelet Transforms (SWT), DCT-based Laplacian Pyramid (DCT-LP), Discrete Cosine Harmonic Wavelet Transform (DC-HWT), and Dual-Tree Complex Wavelet Transform (DT-CWT). The objective is to increase the understanding of these transformation techniques and how they can be utilized in conjunction with one another. The analysis will evaluate the 10 most crucial parameters and highlight the unique features of each method. The results will help determine which transformation technique is the best for multi-focus image fusion applications. Based on the visual and statistical analysis, it is suggested that the DCT-LP is the most appropriate technique, but the results also provide valuable insights into choosing the right approach.

• Journal of applied mathematics & informatics
• /
• v.41 no.5
• /
• pp.1115-1128
• /
• 2023

In this paper, a novel hybrid method for multi-focus image fusion is proposed. The method combines the advantages of wavelet transform-based methods and focus-measure-based methods to achieve an improved fusion result. The input images are first decomposed into different frequency sub-bands using the discrete wavelet transform (DWT). The focus measure of each sub-band is then calculated using the Laplacian of Gaussian (LoG) operator, and the sub-band with the highest focus measure is selected as the focused sub-band. The focused sub-band is sharpened using an unsharp masking filter to preserve the details in the focused part of the image.Finally, the sharpened focused sub-bands from all input images are fused using the maximum intensity fusion method to preserve the important information from all focus images. The proposed method has been evaluated using standard multi focus image fusion datasets and has shown promising results compared to existing methods.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.7
• /
• pp.1907-1928
• /
• 2024

In recent years, multi-focus image fusion has emerged as a prominent area of research, with transformers gaining recognition in the field of image processing. Current approaches encounter challenges such as boundary artifacts, loss of detailed information, and inaccurate localization of focused regions, leading to suboptimal fusion outcomes necessitating subsequent post-processing interventions. To address these issues, this paper introduces a novel multi-focus image fusion technique leveraging the Swin Transformer architecture. This method integrates a frequency layer utilizing Wavelet Transform, enhancing performance in comparison to conventional Swin Transformer configurations. Additionally, to mitigate the deficiency of local detail information within the attention mechanism, Convolutional Neural Networks (CNN) are incorporated to enhance region recognition accuracy. Comparative evaluations of various fusion methods across three datasets were conducted in the paper. The experimental findings demonstrate that the proposed model outperformed existing techniques, yielding superior quality in the resultant fused images.

• Journal of the Semiconductor & Display Technology
• /
• v.22 no.3
• /
• pp.149-154
• /
• 2023

This paper presents a novel approach to multi-focus image fusion using light field cameras. The proposed neural network, LFFCNN (Light Field Focus Convolutional Neural Network), is composed of three main modules: feature extraction, feature fusion, and feature reconstruction. Specifically, the feature extraction module incorporates SPP (Spatial Pyramid Pooling) to effectively handle images of various scales. Experimental results demonstrate that the proposed model not only effectively fuses a single All-in-Focus image from images with multi focus images but also offers more efficient and robust focus fusion compared to existing methods.

• Journal of Information Processing Systems
• /
• v.14 no.5
• /
• pp.1293-1300
• /
• 2018

For the disadvantages of multi-scale geometric analysis methods such as loss of definition and complex selection of rules in image fusion, an improved multi-focus image fusion method is proposed. First, the initial fused image is quickly obtained based on the lifting stationary wavelet transform, and a simple normalized cut is performed on the initial fused image to obtain different segmented regions. Then, the original image is subjected to NSCT transformation and the absolute value of the high frequency component coefficient in each segmented region is calculated. At last, the region with the largest absolute value is selected as the postfusion region, and the fused multi-focus image is obtained by traversing each segment region. Numerical experiments show that the proposed algorithm can not only simplify the selection of fusion rules, but also overcome loss of definition and has validity.

• 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.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.4
• /
• pp.1234-1257
• /
• 2023

In this paper, we propose a framework for multi-focus image fusion called PATN. In our approach, by aggregating deep features extracted based on the U-type Transformer mechanism and shallow features extracted using the PSA module, we make PATN feed both long-range image texture information and focus on local detail information of the image. Meanwhile, the edge-preserving information value of the fused image is enhanced using a dense residual block containing the Sobel gradient operator, and three loss functions are introduced to retain more source image texture information. PATN is compared with 17 more advanced MFIF methods on three datasets to verify the effectiveness and robustness of PATN.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.7 no.7
• /
• pp.1671-1689
• /
• 2013

The key issue of block-based multi-focus image fusion is to determine the size of the sub-block because different sizes of the sub-block will lead to different fusion effects. To solve this problem, this paper presents a novel genetic algorithm (GA) based multi-focus image fusion method, in which the block size can be automatically found. In our method, the Sum-modified-Laplacian (SML) is selected as an evaluation criterion to measure the clarity of the image sub-block, and the edge information retention is employed to calculate the fitness of each individual. Then, through the selection, crossover and mutation procedures of the GA, we can obtain the optimal solution for the sub-block, which is finally used to fuse the images. Experimental results show that the proposed method outperforms the traditional methods, including the average, gradient pyramid, discrete wavelet transform (DWT), shift invariant DWT (SIDWT) and two existing GA-based methods in terms of both the visual subjective evaluation and the objective evaluation.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.9 no.1
• /
• pp.75-87
• /
• 2009

We propose in this paper a novel approach to image fusion in which the fusion rule is guided by optimizing an image clarity function. A Genetic Algorithm is used to stochastically select, comparative to the clarity function, the optimum block from among the source images. A novel nested Genetic Algorithm with gifted individuals found through bombardment of genes by the mutation operator is designed and implemented. Convergence of the algorithm is analytically and empirically examined and statistically compared (MANOVA) with the canonical GA using 3 test functions commonly used in the GA literature. The resulting GA is invariant to parameters and population size, and a minimal size of 20 individuals is found to be sufficient in the tests. In the fusion application, each individual in the population is a finite sequence of discrete values that represent input blocks. Performance of the proposed technique applied to image fusion experiments, is characterized in terms of Mutual Information (MI) as the output quality measure. The method is tested with C=2 input images. The results of the proposed scheme indicate a practical and attractive alternative to current multi-focus image fusion techniques.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.9 no.4
• /
• pp.59-68
• /
• 2009

This paper addresses a hybrid multi-focus image fusion scheme using the recent curvelet transform constructions. Hybridization is obtained by combining the MS fusion rule with a novel "copy" method. The proposed scheme use MS rule to fuse the m most significant terms in spectrum of an image at each decomposition level. The scheme is dubbed in this work as m-term fusion in adherence to its use of the MSC (most significant coefficients) in the transform set at any given scale, orientation, and translation. We applied the edge-sensitive objective quality measure proposed by Xydeas and Petrovic to evaluate the method. Experimental results show that the proposed scheme is a potential alternative to the redundant, shift-invariant Dual-Tree Complex Wavelet transforms. In particular, it was confirmed that a 50% m-term fusion produces outputs with no visible quality degradation.