Pas-Mef: Multi-Exposure Image Fusion Based On Principal Component Analysis, Adaptive Well-Exposedness And Saliency Map

Karakaya, Diclehan; Ulucan, Oguzhan; Türkan, Mehmet

doi:10.1109/icassp43922.2022.9746779

Cited by 16 publications

(7 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The first feature utilizes PCA which has already been used in image fusion and multi-exposure fusion studies, e.g., [7], to give more weight to the dominant pixels of an image. PCA weight maps are extracted for each color channel through their corresponding crosschannel histogram matched channels.…”

Section: Proposed Methodsmentioning

confidence: 99%

“…The second feature, well-exposedness, is initially used by Mertens et al [10] and then adaptively adjusted by Ulucan et al [7] to eliminate over-and/or under-exposed parts of an image, thus to highlight the best exposed parts of it. In this study, the adaptive well-exposedness is utilized given in Eqn.…”

Section: Proposed Methodsmentioning

confidence: 99%

“…To this end, this study proposes a fast and efficient image processing solution to achieve professional-like outputs without destroying image details. The developed method builds upon principal component analysis (PCA) and adaptive wellexposedness [7] feature maps through cross-channel histogram matching, as well as Laplacian [8] and non-local means filtering [9]. Experimental results demonstrate that it is possible to perform lowcost and easier medical imaging in research centers, hospitals and laboratories.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Microscale Image Enhancement Via PCA and Well-Exposedness Maps

Yayci

Dura

Kaya

et al. 2022

2022 IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

The restrictions of accessing high-end microscopes, microscale cameras and high-tech imaging lenses result in a high demand on low-cost microscopes. However, low-cost microscopes are facing with many image capture and quality limitations due to incompatible equipped instrumentation. This study aims at overcoming illumination and contrast problems, color aberration issues, and blur and noise corruption in low-cost microscopes at high image magnification rates. The three color channels of the input image are enhanced via principal component analysis and well-exposedness feature maps by means of cross-channel histogram matching, Laplacian and non-local means filtering. The proposed approach produces sharper, and better color and illumination fixed outputs when compared to existing methods in literature.

show abstract

Section: Proposed Methodsmentioning

confidence: 99%

Section: Proposed Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Microscale Image Enhancement Via PCA and Well-Exposedness Maps

Yayci

Dura

Kaya

et al. 2022

2022 IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

show abstract

“…A comparative analysis was made to compare the method and commonly exposed image fusion methods of this method with common images. The comparison methods include Mertens's classic pyramid exposure fusion, Lee [10] self -adaptal value fusion method, Wang [11] yuv color space the details of the details and the calculation method of the improvement weight calculation of Karakaya [12] and others. The experimental results are shown in Table 4.…”

Section: Image Fusion Comparative Analysismentioning

confidence: 99%

Multi-Exposure Fusion Method for Space Target Images Based on Multi-Feature Weights

Huang,

Zhang

2024

Advances in Transdisciplinary Engineering

View full text Add to dashboard Cite

Aiming at the characteristics of low brightness of space target image, low contrast with space background and uneven image exposure, a multi-exposure fusion method of space target image based on multi-feature weight was proposed. In this method, contrast features, adaptive optimal brightness features and salience features are used as the basic weights of image fusion weights, and the final weights of image fusion are calculated from these three weights. At the same time, aiming at the low brightness of space target image, local color correction technology is further used to improve the overall brightness of fused image. The experimental results show that compared with the four commonly used multi-exposure fusion methods, the proposed method can achieve better multi-exposure fusion effect on space target images, and the information entropy, spatial frequency and average gradient indexes are improved by 103.8%, 7.69% and 33.72%, singly. IL-Niqe, PIQE and BRISQUE had an increase of 33.99%, 13.57% and 19.07%, respectively.

show abstract

“…There are several methods to solve the dimensionality reduction problem. Examples of feasible methods are principal component analysis [11], factor analysis [12], and others. For our task of malware identification, we will use principal component analysis.…”

Section: Reduction Of Input Parameters Using Pcamentioning

confidence: 99%

Detection of Malicious Network Activity by Artificial Neural Network

Turčaník

Barath

2023

AiMT

View full text Add to dashboard Cite

This paper presents a deep learning approach to detect malicious communication in a computer network. The intercepted communication is transformed into behavioral feature vectors that are reduced (using principal component analysis and stepwise selection methods) and normalized to create training and test sets. A feed-forward artificial neural network is then used as a classifier to determine the type of malicious communication. Three training algorithms were used to train the neural network: the Levenberg-Marquardt algorithm, Bayesian regularization, and the scaled conjugate gradient backpropagation algorithm. The proposed artificial neural network topology after reducing the size of the training and test sets achieves a correct classification probability of 81.5 % for each type of malicious communication and of 99.6 % (and better) for normal communication.

show abstract

Pas-Mef: Multi-Exposure Image Fusion Based On Principal Component Analysis, Adaptive Well-Exposedness And Saliency Map

Cited by 16 publications

References 19 publications

Microscale Image Enhancement Via PCA and Well-Exposedness Maps

Microscale Image Enhancement Via PCA and Well-Exposedness Maps

Multi-Exposure Fusion Method for Space Target Images Based on Multi-Feature Weights

Detection of Malicious Network Activity by Artificial Neural Network

Contact Info

Product

Resources

About