Multi-focus Image Fusion Using Deep Belief Network
25 Mar 2017-pp 233-241
TL;DR: An innovative way to fuse multi-focus images by calculating weights indicating the sharp regions of input images with the help of Deep Belief Network and then fuses input images using weighted superimposition fusion rule is proposed.
Abstract: Multi-focus images may be fused to get the relevant information of a particular scene. Due to the limited depth of field of a convex lens of a camera, some objects in the image may not be focused. These images are fused to get all-in-focus image. This paper proposes an innovative way to fuse multi-focus images. The proposed algorithm calculates weights indicating the sharp regions of input images with the help of Deep Belief Network (DBN) and then fuses input images using weighted superimposition fusion rule. The proposed algorithm is analyzed and examined using various parameters like entropy, mutual information, SSIM, IQI etc.
Citations
More filters
Posted Content•
TL;DR: 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 is presented which provides the community a platform to compareMFIF algorithms fairly and comprehensively.
Abstract: 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.
15 citations
Cites background from "Multi-focus Image Fusion Using Deep..."
...[48] proposed to use deep belief network (DBN) to calculate weights indicating the sharp regions of input images....
[...]
TL;DR: A novel multi-focus image fusion algorithm is proposed by combing focus detection in spatial domain and non-subsampled contourlet transform transform (NSCT) domain and outperformed some state-of-the-art fusion algorithms in terms of both subjective observation and objective evaluations.
Abstract: 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.
8 citations
01 Jan 2020
TL;DR: This chapter made an effort to present machine learning- and deep learning-based fusion in a simple manner for fundamental understanding.
Abstract: Machine learning and deep learning are finding applications in various computer vision problems such as object recognition, detection, and visual tracking. In addition, in computer vision, it is quite common to fuse information acquired in different spectral ranges, focusing, and lighting conditions to know more details of a particular scene. Hence, image fusion using machine learning especially deep learning would be a hot research topic in upcoming years due to recent advancements in both software and computing capabilities. In this chapter, we made an effort to present machine learning- and deep learning-based fusion in a simple manner for fundamental understanding. In Sect. 7.1, a general introduction to AI and its general classification is presented. Section 7.2 gives an overview of machine learning from basic definitions to advanced concepts. Image fusion based on machine learning is explained in Sect. 7.3. In Sect. 7.4, important and useful concepts of deep learning are described. Section 7.5 gives an overview of state-of-the-art deep learning based image fusion. Section 7.6 presents the future scope. Finally, Sect. 7.7 concludes the chapter.
4 citations
1 citations
References
More filters
Book•
12 Jun 2014TL;DR: This monograph provides an overview of general deep learning methodology and its applications to a variety of signal and information processing tasks, including natural language and text processing, information retrieval, and multimodal information processing empowered by multi-task deep learning.
Abstract: This monograph provides an overview of general deep learning methodology and its applications to a variety of signal and information processing tasks. The application areas are chosen with the following three criteria in mind: (1) expertise or knowledge of the authors; (2) the application areas that have already been transformed by the successful use of deep learning technology, such as speech recognition and computer vision; and (3) the application areas that have the potential to be impacted significantly by deep learning and that have been experiencing research growth, including natural language and text processing, information retrieval, and multimodal information processing empowered by multi-task deep learning.
2,817 citations
TL;DR: The state-of-the-art in deep learning algorithms in computer vision is reviewed by highlighting the contributions and challenges from over 210 recent research papers, and the future trends and challenges in designing and training deep neural networks are summarized.
1,733 citations
TL;DR: Experimental results show that the proposed method outperforms the discrete wavelet transform based approach, particularly when there is a movement in the objects or misregistration of the source images.
272 citations
TL;DR: Experimental results show the presented method outperforms existing methods, in both visual effect and objective evaluation criteria, and some practical applications are given further.
210 citations
TL;DR: A multifocus image fusion algorithm based on combination of wavelet and curvelet transform is proposed, which exhibits clear advantages over any individual transform alone.
200 citations