Skip to search formSkip to main contentSkip to account menu
DOI:10.1109/ACCESS.2020.3047258 - Corpus ID: 230997577
@article{TalaveraMartnez2021HairSA, title={Hair Segmentation and Removal in Dermoscopic Images Using Deep Learning}, author={Lidia Talavera-Mart{\'i}nez and Pedro Bibiloni and Manuel Gonz{\'a}lez-Hidalgo}, journal={IEEE Access}, year={2021}, volume={9}, pages={2694-2704}, url={https://api.semanticscholar.org/CorpusID:230997577}}
- Lidia Talavera-Martínez, P. Bibiloni, M. González-Hidalgo
- Published in IEEE Access 2021
- Computer Science, Medicine
This work presents a new approach for the task of hair removal on dermoscopic images based on deep learning techniques that relies on an encoder-decoder architecture, with convolutional neural networks, for the detection and posterior restoration of hair’s pixels from the images.
21 Citations
1
7
7
Figures and Tables from this paper
- figure 1
- figure 2
- table 2
- figure 3
- table 3
- figure 4
- table 4
- figure 5
- figure 6
- figure 7
- figure 8
Topics
Dermoscopic Images (opens in a new tab)Loss Function (opens in a new tab)Melanoma (opens in a new tab)Wilcoxon Signed Ranks Test (opens in a new tab)Encoder-decoder Architectures (opens in a new tab)Deep Learning (opens in a new tab)Skin Cancer (opens in a new tab)Non-melanoma (opens in a new tab)Hair Segmentation (opens in a new tab)
21 Citations
- Lidia Talavera-MartínezP. BibiloniA. GiacamanR. TabernerL. J. D. P. HernandoManuel González Hidalgo
- 2022
Computer Science, Medicine
Comput. Biol. Medicine
- M. Hajiarbabi
- 2023
Medicine, Computer Science
Journal of Medical Artificial Intelligence
Results shows the superiority of the proposed methods compare to other state-of-the arts methods for Melanoma lesions detection.
- Dalal BardouHamida BouazizLaishui LvTing Zhang
- 2022
Medicine, Computer Science
Skin research and technology : official journal…
Dermoscopy is a reliable medical technique used to detect melanoma by using a dermoscope to examine the skin and it is important to eliminate the hair to get accurate results.
- 7
- Highly Influenced
- PDF
- Youngchan LeeWonsang You
- 2023
Medicine, Computer Science
IEEE Access
Quantitative and qualitative evaluations show not only that the proposed multi-scale dual-modality strategy is much robust to reconstruct hair-shaped missing regions compared to the existing transformer-based image inpainting method called BAT-Fill, but also that the framework outperforms the state-of-the-art image inPainting models in removing hairs from hairy dermoscopic images.
- 2
- PDF
- E.D. RoshanR.T. HaripriyanM.Yoga NandhiniC. VikneshR. SeetharamanS. Gayathri
- 2023
Medicine, Computer Science
2023 International Conference on Sustainable…
The automatic identification of melanoma using digital image processing is the focus of this research study and the Black Hat filter, which recognizes and eliminates hair from dermoscopy images automatically is used.
- José Guillermo GuarnizoSebastián Riaño BordaEdgar Camilo Camacho PovedaArmando Mateus Rojas
- 2022
Medicine, Computer Science
Ciencia e Ingeniería Neogranadina
The purpose of this research was to design a Convolutional Neural Network with a high level of accuracy to help professionals in medicine with a melanoma diagnosis, in this case it was possible to get accuracy up to 88.75 %.
- 1
- PDF
- S. PoovizhiT. R. Ganesh BabuR. Praveena
- 2021
Medicine, Computer Science
Molecular & Cellular Biomechanics
Experimental result shows the improvement in classification accuracy, sensitivity and specificity compared with the state of art methods.
- 1
- PDF
- R. M. RaniB. DwarakanathM. KathiravanS. MurugesanN. BharathirajaM. V. Kumar
- 2024
Medicine, Computer Science
J. Intell. Fuzzy Syst.
The proposed approach achieved high accuracy, sensitivity, specificity, and F1 score parameters for liver segmentation and lesion identification and holds promise for improving the accuracy and speed of liver tumor detection and diagnosis, which could have significant implications for patient outcomes.
- P. KavithaV. Jayalakshmi
- 2022
Medicine, Computer Science
2022 4th International Conference on Smart…
The goal of this paper is to provide a skin cancer diagnosis system that can automatically identify lesions as malignant or benign, and some of the methods used in an automated melanoma diagnosis.
- Prabhakaran
- 2022
Medicine, Computer Science
The proposed optimization algorithm is suitable for extracting large and complex dermoscopic images to extract image features and it also stops preventing from the entire surface.
- PDF
...
...
46 References
- Q. AbbasM. E. CelebiI. Fondón
- 2011
Computer Science, Medicine
Biomed. Signal Process. Control.
- 157
- PDF
- A. HuangShun-Yuen KwanW. ChangMin-Yin LiuMin-Hsiu ChiGwo-Shing Chen
- 2013
Computer Science, Medicine
2013 35th Annual International Conference of the…
The preliminary results indicated the proposed method was able to remove more fine hairs and hairs in the shade, and lower false hair detection rate by 58% as compared to the DullRazor's approach.
- 43
- Feng-ying XieS. QinZhi-guo JiangRu-Song Meng
- 2009
Computer Science, Medicine
Comput. Medical Imaging Graph.
- 98
- P. BibiloniManuel González HidalgoS. Massanet
- 2017
Computer Science, Medicine
AIME
This work provides an effective hair removal algorithm for dermoscopic imagery employing soft color morphology operators able to cope with color images and compares it with other state-of-the-art algorithms.
- 24
- H. MirzaalianTim K. LeeG. Hamarneh
- 2014
Computer Science, Medicine
IEEE Transactions on Image Processing
This work proposes a novel method for simultaneously enhancing both light and dark hairs with variable widths, from dermoscopic images, without the prior knowledge of the hair color, and validate and compare it to other methods.
- 38
- PDF
- M. AttiaM. HossnyHailing ZhouS. NahavandiHamed AsadiA. Yazdabadi
- 2020
Medicine, Engineering
Artif. Intell. Medicine
- 12
- Tim K. LeeV. NgR. GallagherA. ColdmanD. McLean
- 1997
Computer Science, Medicine
Comput. Biol. Medicine
- 421
- Lidia Talavera-MartínezP. BibiloniM. González-Hidalgo
- 2019
Medicine, Computer Science
VipIMAGE 2019
A hair removal benchmark of six state-of-the-art algorithms, each with a different approach to segment and inpaint the hair pixels, and a series of performance measures that evaluate the similarity between the original hairless image and the one obtained by each of the algorithms.
- 12
- I. BakkouriK. Afdel
- 2019
Medicine, Computer Science
Multimedia Tools and Applications
A robust CAD system based on transfer learning and multi-layer feature fusion network to diagnose complex skin diseases and demonstrates that the proposed approach can dramatically improve the performance of CAD systems based on the conventional recognition and classification algorithms for skin lesion recognition in dermoscopic data.
- 82
- S. MenziesChristian IngvarK. CrottyWilliam H. McCarthy
- 1996
Medicine
Archives of dermatology
Surface microscopy does not allow 100% sensitivity in diagnosing invasive melanoma and therefore cannot be used as the sole indicator for excision.
- 428
...
...
Related Papers
Showing 1 through 3 of 0 Related Papers