Novel Thermal Image Classification Based on Techniques Derived from Mathematical Morphology: Case of Breast Cancer

Mambou, Sebastien; Krejcar, Ondřej; Selamat, Ali; Dobrovolny, Michal; Kuča, Kamil

doi:10.1007/978-3-030-45385-5_61

Cited by 7 publications

(2 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One of the basic problems in this area is the quality of the input data, which directly affects the result of the model. Algorithms of DL can search and represent both structured and not structured data -for instance, natural language processing, time series or image data (Abdel-Nasser & Mahmoud, 2019;Pena-Barragan et al, 2011) In image data processing can be found examples about fixing an image (Wolterink et al, 2017;Yang, et al, 2018), compression (Sun et al, 2020), superresolution (Dobrovolny et al, 2020;Christian, et al, 2017), image classification (Ciresan et al, doi: 10.36689/uhk/hed/2022-01-038 2012 ;Mambou, et al, 2020), forecasting (Dobrovolný et al, 2020) session based recommendations. (Dobrovolny et al, 2020) The article (Sedhain et al, 2015) describes the AutoRec model.…”

Section: Introductionmentioning

confidence: 99%

An Empirical Test of Stacked Autoencoder as Recommendation Model

Langer¹,

Dobrovolny²,

Krejcar³

2022

Proceedings of the International Scientific Conference Hradec Economic Days 2022

Self Cite

View full text Add to dashboard Cite

The Autoencoder method can be used for multiple scenarios, as it is very variable.In this case, the method is used for suggesting actions. This paper describes the theoretical aspects of the recommendation models. The next section describes the use of the autoencoder.There will be provided two experiments. The first one, recommendations for movie lens dataset with process of transformation datasets and proper model dimension setting included. The results of the first experiment are favorable. The second experiment for suggesting actions from custom workflow inspired dataset. In this experiment, two ways of preparing a dataset for a model will be tested. Unfortunately, results are worse than model example. The article concludes with a discussion of the results achieved in comparison with other authors where results with movie datasets.

show abstract

Section: Introductionmentioning

confidence: 99%

An Empirical Test of Stacked Autoencoder as Recommendation Model

Langer¹,

Dobrovolny²,

Krejcar³

2022

Proceedings of the International Scientific Conference Hradec Economic Days 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…An essential objective of computer vision is to extract information within an image to enhance the perception of the world while satisfying the visual effect [1][2][3][4][5][6]. According to the effect of the glass on the light, there is a significant difference in characteristic information in the obtained images that are captured through a glass [7].…”

Section: Introductionmentioning

confidence: 99%

Transmission Removal from a Single Glass Scene and Its Application in Photographer Identification

Yao

Shi

et al. 2022

Applied Sciences

View full text Add to dashboard Cite

In daily life, when taking photos of scenes containing glass, the images of the dominant transmission layer and the weak reflection layer are often blended, which are difficult to be uncoupled. Meanwhile, because the reflection layer contains sufficient important information about the surrounding scene and the photographer, the problem of recovering the weak reflection layer from the mixture image is of importance in surveillance investigations. However, most of the current studies mainly focus on extracting the transmission layer while often ignoring the merit of the reflection layer. To fill that gap, in this paper, we propose a network framework that aims to accomplish two tasks: (1) for general scenes, we attempt to recover reflection layer images that are as close as possible to the ground truth ones, and (2) for scenes containing portraits, we recover the basic contour information of the reflection layer while improving the defects of dim portraits in the reflection layer. Through analyzing the performance exhibited by different levels of feature maps, we present the first transmission removal network based on an image-to-image translation architecture incorporating residual structures. The quality of generated reflection layer images is improved via tailored content and style constraints. We also use the patch generative adversarial network to increase the discriminator’s ability to perceive the reflection components in the generated images. Meanwhile, the related information such as edge and color distribution of transmission layer in the mixture image is used to assist the overall reflection layer recovery. In the large-scale experiments, our proposed model outperforms reflection removal-based SOTAs by more than 5.356 dB in PSNR, 0.116 in SSIM, and 0.057 in LPIPS.

show abstract