Hair Removal Combining Saliency, Shape and Color
Source abstract
Abstract
In a computer-aided system for skin cancer diagnosis, hair removal is one of the main challenges to face before applying a process of automatic skin lesion segmentation and classification. In this paper, we propose a straightforward method to detect and remove hair from dermoscopic images. Preliminarily, the regions to consider as candidate hair regions and the border/corner components located on the image frame are automatically detected. Then, the hair regions are determined using information regarding the saliency, shape and image colors. Finally, the detected hair regions are restored by a simple inpainting method. The method is evaluated on a publicly available dataset, comprising 340 images in total, extracted from two commonly used public databases, and on an available specific dataset including 13 images already used by other authors for evaluation and comparison purposes. We propose also a method for qualitative and quantitative evaluation of a hair removal method. The results of the evaluation are promising as the detection of the hair regions is accurate, and the performance results are satisfactory in comparison to other existing hair removal methods.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: melanin and skin pigmentation · Skin Protection and Aging · Cutaneous Melanoma Detection and Management
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
National Research Council (CNR), Institute for the Applications of Calculus, 80131 Naples, Italy
References (45)
Show source-provided references
1. A survey on automated melanoma detection10.1016/j.engappai.2018.04.028 ↗
2. Computational methods for pigmented skin lesion classification in images: Review and future trends10.1007/s00521-016-2482-6 ↗
3. Masood, A., and Jumaily, A.A. (2013). A Computer Aided Diagnostic Support System for Skin Cancer: A Review of Techniques and Algorithms. Int. J. Biom. Imag.10.1155/2013/323268 ↗
4. Vocaturo, E., Zumpano, E., and Veltri, P. (2018, January 6). Image pre-processing in computer vision systems for melanoma detection. Proceedings of the 2018 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), Madrid, Spain.10.1109/BIBM.2018.8621507 ↗
5. Fiaidhi, J., Bhattacharyya, D., and Rao, N. (2020). A Study on Pre-Processing Techniques for Automated Skin Cancer Detection. Smart Technologies in Data Science and Communication, Springer. Lecture Notes in Networks and Systems.10.1007/978-981-15-2407-3 ↗
6. Despeckling of medical ultrasound images10.1109/TUFFC.2006.1588392 ↗
7. A new technique for color quantization based on histogram analysis and clustering
8. Automatic Perceptual Color Quantization of Dermoscopic Images
9. Ramella, G., and Sanniti di Baja, G. (December, January 28). A new method for color quantization. Proceedings of the 12th International Conference on Signal Image Technology & Internet-Based Systems—SITIS 2016, Naples, Italy.10.1109/SITIS.2016.10 ↗
10. Bruni, V., Ramella, G., and Vitulano, D. (2017). Perceptual-Based Color Quantization. Image Analysis and Processing—ICIAP 2017, Springer. Lecture Notes in Computer Science 10484.10.1007/978-3-319-68560-1_60 ↗
11. A Survey on Color Image Segmentation Techniques for Melanoma Diagnosis10.17485/ijst/2015/v8i22/79192 ↗
12. Ramella, G., and Sanniti di Baja, G. (2013). Image Segmentation Based on Representative Colors and Region Merging in Pattern Recognition, Springer. Lecture Notes in Computer Science 7914.10.1007/978-3-642-38989-4_18 ↗
13. Ramella, G., and Sanniti di Baja, G. (December, January 28). From color quantization to image segmentation. Proceedings of the 2016 12th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS), Naples, Italy.10.1109/SITIS.2016.131 ↗
14. Automatic Skin Lesion Segmentation based on Saliency and Color
15. Ramella, G. (2020). Saliency-based segmentation of dermoscopic images using color information. arXiv.
16. Celebi, M.E., Mendonca, T., and Marques, J.S. (2016). A state-of-the-art survey on lesion border detection in dermoscopy images. Dermoscopy Image Analysis, CRC Press.10.1201/b19107 ↗
17. Talavera-Martinez, L., Bibiloni, P., and Gonzalez-Hidalgo, M. (2019, January 16–18). Comparative Study of Dermoscopic Hair Removal Methods. Proceedings of the ECCOMAS Thematic Conference on Computational Vision and Medical Image Processing, Porto, Portugal.10.1007/978-3-030-32040-9_2 ↗
18. Dullrazor: A software approach to hair removal from images10.1016/S0010-4825(97)00020-6 ↗
19. PDE-based unsupervised repair of hair-occluded information in dermoscopy images of melanoma10.1016/j.compmedimag.2009.01.003 ↗
20. Hair removal methods: A comparative study for dermoscopy images10.1016/j.bspc.2011.01.003 ↗
21. Huang, A., Kwan, S.-Y., Chang, W.-Y., Liu, M.-Y., Chi, M.-H., and Chen, G.-S. (2013, January 3–7). A robust hair segmentation and removal approach for clinical images of skin lesions. Proceedings of the 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBS), Osaka, Japan.10.1109/EMBC.2013.6610250 ↗
22. An effective hair removal algorithm for dermoscopy images10.1111/srt.12015 ↗
23. Bibiloni, P., Gonzàlez-Hidalgo, M., and Massanet, S. (2017). Skin Hair Removal in Dermoscopic Images Using Soft Color Morphology. AIME 2017, Springer. Lecture Notes in Artificial Intelligence 10259.10.1007/978-3-319-59758-4_37 ↗
24. Efficient and Effective Automated Digital Hair Removal from Dermoscopy Images
25. An efficient block-based algorithm for hair removal in dermoscopic images10.18287/2412-6179-2017-41-4-521-527 ↗
26. Digital hair segmentation using hybrid convolutional and recurrent neural networks architecture10.1016/j.cmpb.2019.05.010 ↗
27. Talavera-Martınez, L., Bibiloni, P., and Gonzalez-Hidalgo, M. (2020). An Encoder-Decoder CNN for Hair Removal in Dermoscopic Images. arXiv.
28. Celebi, M.E., Mendonca, T., and Marques, J.S. (2015). PH2–A public database for the analysis of dermoscopic images. Dermoscopy Image Analysis, CRC Press.10.1201/b19107 ↗
29. ISIC 2016 (2016, January 05). ISIC Archive: The International Skin Imaging Collaboration: Melanoma Project, ISIC. Available online: https://isic-archive.com/#.
30. A model of saliency-based visual attention for rapid scene analysis10.1109/34.730558 ↗
31. Image Analysis Using Mathematical Morphology10.1109/TPAMI.1987.4767941 ↗
32. Soille, P. (2004). Morphological Image Analysis: Principles and Applications, Springer.10.1007/978-3-662-05088-0 ↗
33. An Overview of Morphological Filtering10.1007/BF01189221 ↗
34. SDI+: A Novel Algorithm for Segmenting Dermoscopic Images10.1109/JBHI.2018.2808970 ↗
35. A Threshold Selection Method from Gray-Level Histograms10.1109/TSMC.1979.4310076 ↗
36. Achanta, R., Hemami, S., Estrada, F., and Susstrunk, S. (2009, January 20–25). Frequency-tuned salient region detection. Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition, Miami, FL, USA.10.1109/CVPRW.2009.5206596 ↗
37. Dermaweb (2020, November 26). Available online: http://dermaweb.uib.es/.
38. Attia, M., Hossny, M., Zhou, H., Yazdabadi, A., Asadi, H., and Nahavandi, S. (2018). Realistic Hair Simulator for Skin lesion Images Using Conditional Generative Adversarial Network. Preprints, 2018100756.10.20944/preprints201810.0756.v1 ↗
39. (2020, November 26). HairSim by Hengameh Mirzaalian. Available online: http://creativecommons.org/licenses/by-nc-sa/3.0/deed.en_US.
40. Mitsa, T., and Varkur, K.L. (1993, January 27–30). Evaluation of contrast sensitivity functions for the formulation of quality measures incorporated in halftoning algorithms. Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Minneapolis, MN, USA.10.1109/ICASSP.1993.319807 ↗
41. Ramella, G. (2020). Evaluation of quality measures for color quantization. arXiv.
42. Seven Challenges in Image Quality Assessment: Past, Present, and Future Research10.1155/2013/905685 ↗
43. Towards a Full-Reference Quality Assessment for Color Images Using Directional Statistics10.1109/TIP.2015.2456419 ↗
44. Perceptual visual quality metrics: A survey10.1016/j.jvcir.2011.01.005 ↗
45. Perceptual Reduced-Reference Visual Quality Assessment for Contrast Alteration10.1109/TBC.2016.2597545 ↗