Multi-focus image fusion for different datasets with super-resolution using gradient-based new fusion rule

Aymaz, Samet; Köse, Cemal; Aymaz, Şeyma

doi:10.1007/s11042-020-08670-7

Cited by 22 publications

(11 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Specifically, the best deep learning-based methods, namely DPRL, only ranks the fifth on the whole dataset. Apart from Lytro, the MFIFB dataset also contains other subsets such as MFFW and those proposed by Savic et al [49] and Aymaz et al [50]. In other words, the whole MFIFB dataset is more challenging than the Lytro dataset.…”

Section: A Results On the Lytro Datasetmentioning

confidence: 99%

“…Since this paper aims to create a benchmark in the field of MFIF, thus to maximize its value, this test set consists of existing datasets which do not have code library and results. Specifically, the test set is collected from Lytro [33], MFFW [36], the dataset of Savic et al [49], Aymaz et al [50], and Tsai et al 1 . By doing this, we not only provide benchmark results on the whole dataset, but also give benchmark results for these existing datasets, which will make it more convenient for researchers who are familiar with these datasets to compare results.…”

Section: A Datasetmentioning

confidence: 99%

See 1 more Smart Citation

Multi-focus Image Fusion: A Benchmark

Zhang

2020

Preprint

View full text Add to dashboard Cite

Multi-focus image fusion (MFIF) has attracted considerable interests due to its numerous applications. While much progress has been made in recent years with efforts on developing various MFIF algorithms, some issues significantly hinder the fair and comprehensive performance comparison of MFIF methods, such as the lack of large-scale test set and the random choices of objective evaluation metrics in the literature. To solve these issues, this paper presents a multi-focus image fusion benchmark (MFIFB) which consists a test set of 105 image pairs, a code library of 30 MFIF algorithms, and 20 evaluation metrics. MFIFB is the first benchmark in the field of MFIF and provides the community a platform to compare MFIF algorithms fairly and comprehensively. Extensive experiments have been conducted using the proposed MFIFB to understand the performance of these algorithms. By analyzing the experimental results, effective MFIF algorithms are identified. More importantly, some observations on the status of the MFIF field are given, which can help to understand this field better.

show abstract

Section: A Results On the Lytro Datasetmentioning

confidence: 99%

Section: A Datasetmentioning

confidence: 99%

Multi-focus Image Fusion: A Benchmark

Zhang

2020

Preprint

View full text Add to dashboard Cite

show abstract

“…Since the synthetic dataset simulating real focused images was used in our training, in order to reasonably prove that our method could achieve good results on real public datasets, we selected public datasets ”Lytro” [17] and ”Aymaz” [39], respectively, to test our method. Among them, the ”Lytro” dataset contains 20 pairs of color multi‐focus images with the size of 520× 520 pixels and four multi‐focus image series with three sources, while the ”Aymaz” dataset contains 27 pairs of images with the size of 512× 512, including 25 pairs of grayscale multi‐focus images and 2 pairs of color multi‐focus images.…”

Section: Methodsmentioning

confidence: 99%

“…In the training process, we did not directly input full-focus or fully defocus images into the network like many existing methods, but combined them in the initial stage of the network, which also improved the challenge of network training. Since the synthetic dataset simulating real focused images was used in our training, in order to reasonably prove that our method could achieve good results on real public datasets, we selected public datasets "Lytro" [17] and "Aymaz" [39], FIGURE 4 The synthetic dataset we generated for training purposes FIGURE 5 Display of a dataset used to test the fusion effect. The left half is the "Lytro" dataset, and the right half is the "Aymaz" dataset respectively, to test our method.…”

Section: Datasets and Experimental Environmentmentioning

confidence: 99%

Two‐stage progressive residual learning network for multi‐focus image fusion

Wang

Hua

2021

IET Image Processing

View full text Add to dashboard Cite

Boundary artifacts and color detail distortion are easily caused by the common multi‐focus image fusion methods. In order to solve this problem, we propose a two‐stage progressive residual learning network for multi‐focus image fusion. The proposed network can progressively learn color information and detail features through end‐to‐end mapping. The whole network is composed of two sub‐networks: the initial fusion block network and the enhanced fusion block network. First, the color information in the source image is fused by the initial fusion block network to generate the initial fusion image. Then on the basis of the initial fusion image, the detailed features of the source image are further fused by enhanced the fusion network to form the final fusion image. In order to solve the problem of lack of groundtruth when multi‐focus image fusion is carried out with supervised method, the multi‐focus image fusion problem is compared to the easy‐to‐solve image restoration problem. A synthetic dataset for network training is generated by ”degenerating” the VOC2012 dataset according to the set rules. After training, the method works well for fusion tasks without further processing. Experimental results show that the proposed method is superior to the existing methods in subjective visual perception and objective quantitative evaluation.

show abstract

“…The technique is widely used in visual sensor networks, such as military defense, security monitoring, and image inpainting. In digital photography, it is difficult for the single-lens reflex camera to take an image that can present all objects into focus [4,5]. To obtain all-in-focus images, multisource images from the same scene with different focuses are fused into one signal image, which is named the multi-focus image fusion [6].…”

Section: Introductionmentioning

confidence: 99%

Multi-Sensor Image Fusion Using Optimized Support Vector Machine and Multiscale Weighted Principal Component Analysis

et al. 2020

View full text Add to dashboard Cite

Multi-sensor image fusion is used to combine the complementary information of source images from the multiple sensors. Recently, conventional image fusion schemes based on signal processing techniques have been studied extensively, and machine learning-based techniques have been introduced into image fusion because of the prominent advantages. In this work, a new multi-sensor image fusion method based on the support vector machine and principal component analysis is proposed. First, the key features of the source images are extracted by combining the sliding window technique and five effective evaluation indicators. Second, a trained support vector machine model is used to extract the focus region and the non-focus region of the source images according to the extracted image features, the fusion decision is therefore obtained for each source image. Then, the consistency verification operation is used to absorb a single singular point in the decisions of the trained classifier. Finally, a novel method based on principal component analysis and the multi-scale sliding window is proposed to handle the disputed areas in the fusion decision pair. Experiments are performed to verify the performance of the new combined method.

show abstract

Multi-focus image fusion for different datasets with super-resolution using gradient-based new fusion rule

Cited by 22 publications

References 29 publications

Multi-focus Image Fusion: A Benchmark

Multi-focus Image Fusion: A Benchmark

Two‐stage progressive residual learning network for multi‐focus image fusion

Multi-Sensor Image Fusion Using Optimized Support Vector Machine and Multiscale Weighted Principal Component Analysis

Contact Info

Product

Resources

About