Multi-focus Image Fusion Algorithm Research Articles

Conditional Random Field Model for Robust Multi-Focus Image Fusion.

In this paper, a novel multi-focus image fusion algorithm based on conditional random field optimization (mf-CRF) is proposed. It is based on an unary term that includes the combined activity estimation of both high and low frequencies of the input images, while a spatially varying smoothness term is introduced, in order to align the graph-cut solution with boundaries of focused and defocused pixels. The proposed model retains the advantages of both spatial-domain methods and multi-spectral methods and by solving an energy minimization problem and finds an optimal solution for the multi-focus image fusion problem. Experimental results demonstrate the effectiveness of the proposed method that outperforms current state-of-the-art multi-focus image fusion algorithms in both qualitative and quantitative comparisons. In this paper, the successful application of the mf-CRF model in multi-modal image fusion (visible-infrared and medical) is also presented.

Nonwovens structure measurement based on NSST multi-focus image fusion

In the digital optical microscope, the depth of field cannot clearly display all fibers in the same image, due to the thickness of nonwovens. A new multi-focus image fusion algorithm based on non-subsampled shearlet transform (NSST) is proposed to improve the quality of fused image, which realizes the fusion of a series of images taken from the same perspective and makes all fibers clearly within a single image. The rule of large absolute value is used to fuse the high frequency sub-band and the rule of large regional variance is used to fuse the low frequency sub-band. Comparing the method with other methods, the superiority of the method can be seen from several indicators of image quality evaluation. Based on the fused image, the diameter and orientation are measured by Hough transform and image preprocessing, and automatic measurement is realized. The porosity is measured by identifying pores, which is fast and convenient. Experiments show that the measurement of nonwoven fabric structure can be quickly achieved based on image processing.

Research on multi-focus image fusion algorithm based on total variation and quad-tree decomposition

In order to get the focus region from the two or more source image more effectively and to represent the source image completely and effectively, a decomposition strategy based on the combination of total variation and quad-tree and an improved fusion method of focus region detection are proposed. The theory of total variation and quad-tree is applied to the fusion of multi-focus images. Firstly, two registered experimental images are decomposed into the optimal block decomposition graph by total variation and quad-tree decomposition, respectively. For each block, the initial focus region decision map of the source image is found by using improved Sum-Modified-Laplacian, and the final focus region decision map is obtained by consistency test and morphological processing for the initial focus region decision map. Furthermore, compared with other algorithms, the improved algorithm has more advantages in extracting the focus area, because of improved focus evaluation function and more accurate detection of the focus area. According to the fusion source image of the final focus region decision map, the results of four sets of experiments show that the fusion quality and effect are significantly improved compared with the existing algorithm.

Structural characterization and measurement of nonwoven fabrics based on multi-focus image fusion

In the microscopic imaging process of multi-layered materials whose thickness is greater than the depth of the microscope, image blurring often occurs, so it is necessary to present some new methods to solve this problem. In this paper, a novel multi-focus image fusion algorithm and the related imaging system is proposed to improve the quality of fused image, which can be used to characterize the structure of the nonwoven fabrics. One set of single focus images captured with the same imaging geometry at different focus depth is merged into a well-focused image using the self-developed image fusion algorithm; it contributes to the subsequent investigation of structural characterization and measurement of nonwoven fabrics. The high and low frequency components of the image are filtered and combined using different fusion rules, the fusion image of the initial fabric is obtained after the fusion of multi-wavelets and the inverse transformation. Later, a set of image analysis algorithm is developed to measure the fiber diameter, orientation and porosity of nonwoven fabric. Our experimental results show that image-based measurements are effective compared to manual operation.

A New Multi-Focus Image Fusion Algorithm and Its Efficient Implementation

Wavelet transform using Haar filter is a fast process for decomposing an image into low and high frequency sub-bands, which is an important step in multi-focus image fusion. This transformation alone is usually not sufficient to produce satisfying fused images, and therefore additional tools like focused region decision map and feature extraction are needed to enhance the fusion quality. In this paper, we propose a multi-focus image fusion algorithm that is suitable for efficient hardware implementation. The algorithm speed is significantly improved by utilizing Haar wavelet and computationally simple fusion rules. To further improve the circuit power and delay, we limit the logic operations to additions, subtractions, and multiplications only. Experiments on different benchmarks demonstrate that our proposed algorithm can reduce the fusion time by up to 99.97% compared with the state-of-the-art competing methods without compromising the fusion quality. In addition, the hardware implementation of the proposed algorithm reduces the circuit area and delay by 79.5% and 92.5%, respectively, when compared to the most competitive algorithm in this paper while maintaining similar fusion quality.

Image Fusion Algorithm of Focal Region Detection and TAM-SCM Based on SHT Domain

The selection of texture information and block ringing effect in multi-focus fusion process, a new multi-focus image fusion algorithm based on Three Activity Measures (TAM) excitation Spiking Cortical Model, (SCM) in shearlet (SHT) domain is proposed. Firstly, in SHT domain, using local spatial frequency (SF), local energy of gradient (EOG) and different measurements (SF, EOG, and local laplace energy sum (SML)) motivated SCM selected the texture information and construct the initial fusion image (P). Then, the focal region was extracted from the significant feature of the difference between the image P and the original image. Finally, the joint focus area produces fusion images. To verify the superiority of the proposed algorithm, compare the results of this paper with seven competing methods. Experimental results show that the algorithm can produce clear edges, good visual perception and less distortion.

Multi-Focus Image Fusion Based on Residual Network in Non-Subsampled Shearlet Domain

In order to obtain a panoramic image which is clearer, and has more layers and texture features, we propose an innovative multi-focus image fusion algorithm by combining with non-subsampled shearlet transform (NSST) and residual network (ResNet). First, NSST decomposes a pair of input images to produce subband coefficients of different frequencies for subsequent feature processing. Then, ResNet is applied to fuse the low frequency subband coefficients, and improved gradient sum of Laplace energy (IGSML) perform high frequency feature information processing. Finally, the inverse NSST is performed on the fused coefficients of different frequencies to obtain the final fused image. In our method, we fully consider the low frequency global features and high frequency detail information in image by using NSST. For low-frequency coefficients fusion, we can also obtain the spatial information features of low-frequency coefficient images by using ResNet, which has a deep network structure. IGSML can use different directional gradients to process high-frequency subband coefficients of different levels and directions, which is more conducive to the fusion of the coefficients. The experiment results show that the proposed method has been improved in the structural features and edge texture in the fusion images.

Fusion of multi-focus images via a Gaussian curvature filter and synthetic focusing degree criterion.

The aim of multi-focus image fusion technology is to acquire an image of every scene all focused on the same visual point at different focal settings. To achieve this goal, we propose an improved multi-focus image fusion algorithm based on a Gaussian curvature filter and synthetic focusing degree criterion. First, in order to realize the salient feature extraction, a Gaussian curvature filter is applied to obtain the most sharpness regions. Then we obtain a coarse fusion map by composing a synthetic focusing degree criterion, which is a combination of the spatial frequency and the local variance of image. The coarse fusion map is further processed by morphological filters and median filters to acquire an optimized fusion map. Finally, the fusion image is obtained via a weighted fusion operation. Experimental results demonstrate that our proposed algorithm can be competitive with, or even outperform, many existing fusion methods on both qualitative and quantitative measures.

Multi-focus image fusion using deep support value convolutional neural network

A novel multi-focus image fusion algorithm based on deep support value convolutional neural network (DSVCNN) is proposed for multi-focus image fusion. First, a deep support value training network is presented by replacing the empirical risk minimization-based loss function by a loss function based on structural risk minimization during the training of convolutional neural network (CNN). Then, to avoid the loss of information, max-pooling/subsampling of the feature mapping layer of a conventional convolutional neural network, which is employed in all conventional CNN frameworks to reduce the dimensionality of the feature map, is replaced by standard convolutional layers with a stride of two. The experimental results demonstrate that the suggested DSVCNN-based method is competitive with current state-of-the-art approaches and superior to those that use traditional CNN methods.

Multi-focus image fusion algorithm based on focus detection in spatial and NSCT domain.

Multi-focus image fusion is an effective approach to obtain the all-in-focus image. Focus detection is the key issue of multi-focus image fusion. Aiming at the shortcoming of spatial domain and transform domain algorithms for multi-focus image fusion, a novel multi-focus image fusion algorithm is proposed by combing focus detection in spatial domain and non-subsampled contourlet transform (NSCT) domain. At first, the focused pixels are detected by the sum-modified-Laplacian algorithm in spatial domain. At the same time, the focus detection method is proposed in NSCT domain, namely by MPCNN and voting fusion methods for high-frequency subbands of NSCT. Then, the morphological operation is utilized to correct the focus detection results in spatial domain and NSCT domain. At last, synthesis of detection results is implemented and the fused image can be obtained. Experimental results verified that the proposed algorithm outperformed some state-of-the-art fusion algorithms in terms of both subjective observation and objective evaluations.

An effective image fusion algorithm based on grey relation of similarity and morphology

Considering the problems of the limited energy in wireless multi-media sensor networks (WMSNs) and the focused regions discontinuity of the fused image obtained using traditional multi-scale analysis tools (MST)-based methods, an effective multi-focus image fusion algorithm is proposed in this paper. In this method, the original fused image is obtained based on wavelet transform where the low-frequency coefficients are fused by average scheme, whereas the high-frequency coefficients are fused by the proposed merging rule consisting of the grey relation analysis of similarity and local area energy. Then, grey absolute relation analysis is again utilized as measurement indicator to estimate the similarities between the initial fused image and source images, during which the initial map is acquired and then corrected by the mathematical morphological opening and closing. Finally, the fused image is obtained with the guidance of the corrected map, namely the decision map. Experiment results demonstrate that the fused image using the proposed algorithm is more continuous in focused region and more similar to source images in brightness compared with state-of-art multi-focus image fusion algorithms, such as Curvelet transform, lifting stationary wavelet transform (LSWT), non-subsampled contourlet transform (NSCT) and non-subsampled shearlet transform (NSST). Meanwhile, the proposed method shows better superiority in term of the computational complexity.

Multi-focus image fusion algorithm based on Laplacian pyramids.

In this paper, we propose a method named region mosaicking on Laplacian pyramids (RMLP) to fuse multi-focus images that are captured by microscope. First, we apply the sum-modified Laplacian to measure the focus of multi-focus images. Then the density-based region growing algorithm is utilized to segment the focused region mask of each image. Finally, the mask is decomposed into a mask pyramid to supervise region mosaicking on a Laplacian pyramid. The region level pyramid keeps more original information than the pixel level. The experiment results show that RMLP has the best performance in quantitative comparison with other methods. In addition, RMLP is insensitive to noise and can reduce the color distortion of the fused images on two datasets.

A multi-focus image fusion algorithm in 5G communications

In this paper, we first build a mobile cloud platform that users can upload multi-focus images or download full-focus images through the 5G network. Then we design a method named Region Mosaicking on Contrast Pyramid (RMCP) for image fusion on the cloud platform. In the RMCP method, we apply the Sum-Modified-Laplacian to measure the focus of the multi-focus image, and use the density-based region growth algorithm to segment the focus region mask for each image. Finally, the mask is decomposed into a mask pyramid to monitor the mosaic region of the contrast pyramid. The experimental results show that RMCP based on 5G network outperforms other methods. In addition, RMCP is suitable for mobile devices.

Focus measure method based on the modulus of the gradient of the color planes for digital microscopy

The modulus of the gradient of the color planes (MGC) is implemented to transform multichannel information to a grayscale image. This digital technique is used in two applications: (a) focus measurements during autofocusing (AF) process and (b) extending the depth of field (EDoF) by means of multifocus image fusion. In the first case, the MGC procedure is based on an edge detection technique and is implemented in over 15 focus metrics that are typically handled in digital microscopy. The MGC approach is tested on color images of histological sections for the selection of in-focus images. An appealing attribute of all the AF metrics working in the MGC space is their monotonic behavior even up to a magnification of 100×. An advantage of the MGC method is its computational simplicity and inherent parallelism. In the second application, a multifocus image fusion algorithm based on the MGC approach has been implemented on graphics processing units (GPUs). The resulting fused images are evaluated using a nonreference image quality metric. The proposed fusion method reveals a high-quality image independently of faulty illumination during the image acquisition. Finally, the three-dimensional visualization of the in-focus image is shown.

Multi-focus image fusion using Content Adaptive Blurring

Multi-focus image fusion has emerged as an important research area in information fusion. It aims at increasing the depth-of-field by extracting focused regions from multiple partially focused images, and merging them together to produce a composite image in which all objects are in focus. In this paper, a novel multi-focus image fusion algorithm is presented in which the task of detecting the focused regions is achieved using a Content Adaptive Blurring (CAB) algorithm. The proposed algorithm induces non-uniform blur in a multi-focus image depending on its underlying content. In particular, it analyzes the local image quality in a neighborhood and determines if the blur should be induced or not without losing image quality. In CAB, pixels belonging to the blur regions receive little or no blur at all, whereas the focused regions receive significant blur. Absolute difference of the original image and the CAB-blurred image yields initial segmentation map, which is further refined using morphological operators and graph-cut techniques to improve the segmentation accuracy. Quantitative and qualitative evaluations and comparisons with current state-of-the-art on two publicly available datasets demonstrate the strength of the proposed algorithm.

基于快速有限剪切波变换与引导滤波的多聚焦图像融合算法

基于快速有限剪切波变换与引导滤波的多聚焦图像融合算法

一种基于深度学习的多聚焦图像融合算法

一种基于深度学习的多聚焦图像融合算法

Multi-Focus Image Fusion Algorithm in Sensor Networks

Most imaging systems have a limited depth-of-field in the sensor networks that consist of multiple visual sensors. Due to different object distances, not every object can be clearly imaged by a single sensor. This paper proposes a multi-focus image fusion algorithm in sensor networks. The algorithm combines the advantages of multi-scale analysis and image phase analysis. It uses dynamic window and phase stretch transform (PST) to extract the focused regions of each image accurately and performs multi-resolution analysis of images through the non-sub-sampled shearlet transform. Then, the images are fused according to the local standard deviation of PST feature maps. The results of the simulation experiments prove that our algorithm is effective and outperforms some state-of-the-art algorithms.

Multi-focus Image Fusion Algorithm Based on Motivated Pulse Coupled Neural Networks Using Nonsubsampled Contourlet Transform

In this paper, a multi-focus image fusion algorithm based on motivated pulse coupled neural networks using nonsubsampled contourlet transform (NSCT) is proposed. Firstly, NSCT is used to decompose the source image in multi scale and multi directions to obtain the low frequency coefficients and high frequency coefficients. Secondly, Fourier transform method is used for saliency detection. We choose the coefficients which have larger saliency for high frequency coefficients. In the process of choosing the low frequency, the spatial frequency is used as the input of the Pulse coupled neural network (PCNN) to obtain the firing times of the low frequency. If the firing times of two images are not the same, then we choose coefficients which have larger firing times. Otherwise, coefficients which have larger saliency will be chosen. Lastly, inverse transformation of NSCT is used to obtain the fused image. The proposed method is compared with four other common methods, and the experimental results show that the proposed method performs better on both subjective and objective evaluation indicators.

Multi-focus image fusion algorithm based on pulse coupled neural networks and modified decision map

In this paper, we present a new approach for the multi-focus image fusion, which utilizes Orientation Information(OI) Motivated Pulse Coupled Neural Networks(PCNN) and modified decision map. First, the source multi-focus images are fused using the Orientation Information Motivated Pulse Coupled Neural Networks (OI-PCNN), and the initial decision map is obtained. Second, after analyzing the decision map, we modified the decision map by employing a mathematical morphology post-processing technique. Finally, based on the modified decision map, the final fused image is obtained by selecting the pixels in the focus areas. Objective performance evaluation criteria and visual observation demonstrate that the proposed method is better than various existing spatial domain and transform domain fusion methods, including NSCT, PCNN-NSCT, SF-PCNN-NSCT, and EOE-PCNN-NSCT method.