Multi-focus image fusion for multiple images using adaptable size windows and parallel programming

The multi-focus image fusion technique is to extract the focus regions from source images and compose them together to form a clear image in the full field of view. In order to further improve the accuracy of focus region detection and ensure its efficiency, a novel multi-focus image fusion method in spatial domain, based on guided filter and mixed focus measure, is proposed in this paper. Firstly, a guided filter is employed as an edge-preserving smoothing operator to process the source images, and the difference operator is used between the filtered images and the source images to extract salient feature. Subsequently, the salient feature maps are measured by the mixed focus measure, combining the sum of energy of edge (SEOE) and the sum of local variance (SLV), to detect the focus regions, and the initial decision map is obtained. For holes of different sizes in the initial decision map, the closing operation and the small area removal strategy are used to fill and connect the truncated regions, and then the opening operation and the guide filter are used to optimize the decision map boundary to obtain the final decision map. Finally, the multi-focus fusion image is obtained by the pixel-wise weighted-averaging rule according to the final decision map. Simulation results demonstrate that the method is superior to some existing fusion methods on both subjective visual perception and objective evaluation metrics.

The multi-focus image fusion with deep learning methods is mostly regarded as a two or three-category problem. Current systems utilize sliding windows to classify each pixel into focused or defocused, which is time consuming and requires post-processing such as denoising. In this paper, we propose a novel network architecture for multi-focus image fusion based on the latent decision map. For a regression task instead of a classification problem, we focus on learning the latent spatial decision map. This decision map indicates the degree of each focused pixel. To further improve the fusion result, we utilize the ResNet blocks to extract image features, and then combine low-level features with high-level semantic information. Our apporach makes the learning process easier and has better robustness and efficiency as well. Experimental results demonstrate that our framework has ability of achieving the state-of-the-art in terms of both qualitative and quantitative measures.

As an important multisensor data fusion technology, multifocus image fusion (MFIF) integrates all focused information from source images to provide a comprehensive and objective interpretation. However, current MFIF algorithms have limitations on blurred edges and oversharpening of the fused images, resulting in loss of details or introduction of artifacts. In this article, we propose a novel MFIF scheme based on multiscale cross-difference and focus detection. First, to extract the pixel information at different scales, we express the source images at different scales using multiscale-guided filtering. Subsequently, we proposed a multiscale cross-difference strategy for obtaining the salient map, which accurately highlights the pixels within the focused regions. Meanwhile, we designed an effective two-scale decision map generation model to accurately refine the focus decision maps. Finally, we introduce guided filter (GF) and consistency verification operations to optimize and obtain the final decision maps and the fused result. The proposed model can effectively address edge blur and detail loss and improve the clarity and visual quality of fused images. Experiments were performed on two popular public datasets and the subjective and objective evaluations indicate that the proposed method has a better performance than 28 state-of-the-art (SOTA) methods. The code of this work was available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/ixilai/MCFDF</uri> .

Multi-focus image fusion is a technique that integrates the focused areas in a pair or set of source images with the same scene into a fully focused image. Inspired by transfer learning, this paper proposes a novel color multi-focus image fusion method based on deep learning. First, color multi-focus source images are fed into VGG-19 network, and the parameters of convolutional layer of the VGG-19 network are then migrated to a neural network containing multilayer convolutional layers and multilayer skip-connection structures for feature extraction. Second, the initial decision maps are generated using the reconstructed feature maps of a deconvolution module. Third, the initial decision maps are refined and processed to obtain the second decision maps, and then the source images are fused to obtain the initial fused images based on the second decision maps. Finally, the final fused image is produced by comparing the QABF metrics of the initial fused images. The experimental results show that the proposed method can effectively improve the segmentation performance of the focused and unfocused areas in the source images, and the generated fused images are superior in both subjective and objective metrics compared with most contrast methods.

As a powerful assistance technique for computer vision, multi-focus images fusion has attracted extensive attention in recent years. However, how to accurately detect the focused region from the focused source image is a key problem. To address the weak performance of current fusion methods, in this paper, we proposed a new multi-focus images fusion method. Firstly, the encoder based on VGG-16 aims to extract multi-scale features of the source images. Then, the cross features attention fusion module (CFAFM) integrates multi-scale features for subsequent decoding. Further, the refinement module (RM) aims to refine the predicted coarse decision map. Finally, an all-in focus image is obtained by using the decision map and source images according to the designed fusion rules. Extensive experiments on ‘Lytro’ dataset demonstrate that the proposed method significantly outperforms 5 typical image fusion models and achieves the new state-of-the-art.

Multi-focus image fusion is an important method used to combine the focused parts from source multi-focus images into a single full-focus image. Currently, to address the problem of multi-focus image fusion, the key is on how to accurately detect the focus regions, especially when the source images captured by cameras produce anisotropic blur and unregistration. This paper proposes a new multi-focus image fusion method based on the multi-scale decomposition of complementary information. Firstly, this method uses two groups of large-scale and small-scale decomposition schemes that are structurally complementary, to perform two-scale double-layer singular value decomposition of the image separately and obtain low-frequency and high-frequency components. Then, the low-frequency components are fused by a rule that integrates image local energy with edge energy. The high-frequency components are fused by the parameter-adaptive pulse-coupled neural network model (PA-PCNN), and according to the feature information contained in each decomposition layer of the high-frequency components, different detailed features are selected as the external stimulus input of the PA-PCNN. Finally, according to the two-scale decomposition of the source image that is structure complementary, and the fusion of high and low frequency components, two initial decision maps with complementary information are obtained. By refining the initial decision graph, the final fusion decision map is obtained to complete the image fusion. In addition, the proposed method is compared with 10 state-of-the-art approaches to verify its effectiveness. The experimental results show that the proposed method can more accurately distinguish the focused and non-focused areas in the case of image pre-registration and unregistration, and the subjective and objective evaluation indicators are slightly better than those of the existing methods.

Parallel programs have traditionally been implemented on distributed systems using conventional programming languages, such as Fortran or C, plus a library with support for communication, such as, for instance, PVM [11]. Also, some effort has been put into developing parallel programming languages [13]. Usually, the different development platforms are compared as to application execution time or parallel efficiency. However, as pointed out in [4], when measuring the performance of a parallel application or programming tool, different metrics may need to be taken into consideration. The ease of construction of an application and the time a programmer spends to implement it may in some cases be more important than the final execution time. Working under this assumption, this work argues that the use of interpreted languages as a basis for parallel programming tools should be further investigated. As support for our argument, we show an example of use of an interpreted language in a classical application in parallel distributed programming, namely, that of detecting program termination. Two different algorithms for termination detection are implemented in Lua, an extension language developed at PUC-Rio [5].

To improve the quality of multi-focus image fusion result, a focused regions detection based fusion method was proposed in this paper. Firstly, a multi-scale morphological focus-measure strategy was used to generate the rough boundary between the focused and unfocused regions. Then some morphology processes were adopt to improve the boundary. After that the focused regions can be obtained and the fused image can be got by using the focused regions as decision map. Experiment results demonstrate the proposed method achieved best quality in terms of both visual and objective evaluation.

PurposeThe more precise decision map is important to generate better-fused image. Guided filter can preserve edge information effectively. The purpose of his study is to use guided filter to form the precise decision map and highly informatively fused image.Design/methodology/approachThe dual tree complex wavelet transform is adopted to decompose the source images into high frequency and low frequency coefficients. Sum of modified Laplacian method is introduced as the focus metric in dual tree complex wavelet coefficients. The guided filter is guided by the dual tree complex wavelet coefficient when the sum of modified Laplacian is used as the input image. The output image of guided filter is used to produce the decision map to fuse dual tree complex wavelet coefficient of source images.FindingsThe sum of modified Laplacian of dual tree complex wavelet coefficient can be used as the guided image in guided filter to generate better decision map. Comparison with the other state-of-the-art methods illustrates that the proposed approach is more effective in fusing the multifocus images both visual performance and objective evaluation.Originality/valueThe sum of modified Laplacian of dual tree complex wavelet coefficient is introduced to be used as the guided image in guided filter to generate better decision map. This method is fast and effect to fuse the source images. Comparison with the other state-of-the-art methods illustrates that the proposed approach is more effective in fusing the multifocus images both visual performance and objective evaluation.

Speeding up the communications on a cluster using MPI by means of Software Defined Networks

Accurate identification and quantification of microvascular patterns are important for clinical diagnosis and therapeutic monitoring using optical-resolution photoacoustic microscopy (OR-PAM). Due to its limited depth of field, conventional OR-PAM may not fully reveal microvascular patterns with enough details in depth range, which affects the segmentation and quantification. Here, we propose a robust vascular quantification approach via combining multi-focus image fusion with enhancement filtering (MIFEF). The multi-focus image fusion is constructed based on multi-scale gradients and image matting to improve image fusion quality by considerably achieving accurate focus measurement for initial segmentation as well as decision map refinement. The enhancement filtering identifies the vessels and handles noise without deforming microvasculature. The performance of the MIFEF were evaluated employing a leaf phantom, mouse livers and brains. The proposed method for OR-PAM can significantly facilitate the clinical provision of optical biopsy of vascular-related diseases.

New technological advancements in synchrotron light sources enable data acquisitions at unprecedented levels. This emergent trend affects not only the size of the generated data but also the need for larger computational resources. Although beamline scientists and users have access to local computational resources, these are typically limited and can result in extended execution times. Applications that are based on iterative processing as in tomographic reconstruction methods require high-performance compute clusters for timely analysis of data. Here, time-sensitive analysis and processing of Advanced Photon Source data on geographically distributed resources are focused on. Two main challenges are considered: (i) modeling of the performance of tomographic reconstruction workflows and (ii) transparent execution of these workflows on distributed resources. For the former, three main stages are considered: (i) data transfer between storage and computational resources, (i) wait/queue time of reconstruction jobs at compute resources, and (iii) computation of reconstruction tasks. These performance models allow evaluation and estimation of the execution time of any given iterative tomographic reconstruction workflow that runs on geographically distributed resources. For the latter challenge, a workflow management system is built, which can automate the execution of workflows and minimize the user interaction with the underlying infrastructure. The system utilizes Globus to perform secure and efficient data transfer operations. The proposed models and the workflow management system are evaluated by using three high-performance computing and two storage resources, all of which are geographically distributed. Workflows were created with different computational requirements using two compute-intensive tomographic reconstruction algorithms. Experimental evaluation shows that the proposed models and system can be used for selecting the optimum resources, which in turn can provide up to 3.13× speedup (on experimented resources). Moreover, the error rates of the models range between 2.1 and 23.3% (considering workflow execution times), where the accuracy of the model estimations increases with higher computational demands in reconstruction tasks.

High-Performance Computing (HPC) has become a powerful tool to solve highly complex projects that could not otherwise be addressed. However, developing parallel programs to take advantage of its benefits, making a proper and effective use of the available computing resources, can be a difficult task for beginners or scientists of specific branches of science which have very little to do with computer programming. For this purpose, a transcompiler for automatic parallelization of sequential codes was developed to train beginners in parallel programming and achieve better performances in HPC centers. Current efforts are focused on expanding the transcompiler with an additional module for optimizing sequential and parallel code fragments with the objective of speeding up their execution times. To accomplish this, several techniques for writing efficient code have been evaluated with a view to integrate them into the transcompiler in the future. This manuscript discusses the importance of these techniques to decrease running times of HPC programs. In addition, a set of tests have been developed for analysing and measuring the improvements achieved when applying each of these techniques, all of them with a significant impact on the execution times.

Active remotely sensed data can be used to perform a variety of forestry tasks including stand characterization, inventory, and management of forest and fire behavior modeling. The present work investigates the potential of Airborne Laser Scanning (ALS) derived methods applied in the deciduous forest by processing an individual tree detection (ITD) based on canopy Height model (CHM) and tree segmentation of larger-area point clouds. Different algorithms are tested and their performances are evaluated to show which of them can provide the most adequate number of trees compared with the ground truth. Tree scale information is used in order to determine stand age. The forest height, structure, and density are specified by applying individual tree Detection (ITD) to calculate some forest attributes such as stem volume, forest uniformity, and biomass estimation. The major aim of this post is to examine the state of the forest to monitor it in real-time. We assume that utilizing the LM algorithm, which was originally built for ITD from LiDAR data, trees should be automatically distinguished from the ALS-derived CHM with reasonable accuracy. As a result, the present research work studies the fixed treetop window size (FWS), fixed smoothing window size (SWS), and variable window (VW) effect on ITD performance (RMSE=3.4% and R=0.88). It is obvious, from the obtained results that smaller window sizes result in more trees. In fact, the smallest trees obscured by the largest trees containing the highest points in the neighborhood are often ignored by large windows. Crown delineation is also explored to extract the height of the trees, radius crown and, 3D coordinates and to compare them to those detected by a Low Bluetooth sensor “iBeacon.”.

Time is the most important feature that counts for an executing process. Nowadays, applications are more focused to reduce the computational time and thus to increase the speed. Therefore, there is a need to redesign the fundamental algorithms especially for searching methods to achieve this objective. Targeting this, approach of memorization is proposed in this paper to optimize the time of searching during execution. It is an optimization technique used to eliminate re-execution time for pure function. A novel approach of memoized Quadratic Search Algorithm is presented in this paper. Results show remarkable improvement in the performance in terms of time leading to achieve the said objective. This will help to optimize the time in other respective areas of computation processes. Keywords: Binary Search, Quadratic Search, Optimization, Memoization, Execution Time.