Hair Removal Combining Saliency, Shape and Color

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.

[1]  Qaisar Abbas,et al.  Hair removal methods: A comparative study for dermoscopy images , 2011, Biomed. Signal Process. Control..

[2]  Vittoria Bruni,et al.  Automatic Perceptual Color Quantization of Dermoscopic Images , 2015, VISAPP.

[3]  Giuliana Ramella,et al.  Automatic Skin Lesion Segmentation based on Saliency and Color , 2020, VISIGRAPP.

[4]  Huiyu Zhou,et al.  A State-of-the-Art Survey on Lesion Border Detection in Dermoscopy Images , 2015 .

[5]  T Lee,et al.  Dullrazor®: A software approach to hair removal from images , 1997, Comput. Biol. Medicine.

[6]  N. Otsu.  A threshold selection method from gray level histograms , 1979 .

[7]  Manuel González-Hidalgo,et al.  Comparative Study of Dermoscopic Hair Removal Methods , 2019 .

[8]  Gabriella Sanniti di Baja,et al.  From Color Quantization to Image Segmentation , 2016, 2016 12th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS).

[9]  Sabine Süsstrunk,et al.  Frequency-tuned salient region detection , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[10]  Vittoria Bruni,et al.  Perceptual-Based Color Quantization , 2017, ICIAP.

[11]  Manuel González Hidalgo,et al.  Skin Hair Removal in Dermoscopic Images Using Soft Color Morphology , 2017, AIME.

[12]  Christof Koch,et al.  A Model of Saliency-Based Visual Attention for Rapid Scene Analysis , 2009 .

[13]  D. Chandler.  Seven Challenges in Image Quality Assessment: Past, Present, and Future Research , 2013 .

[14]  Ester Zumpano,et al.  Image pre-processing in computer vision systems for melanoma detection , 2018, 2018 IEEE International Conference on Bioinformatics and Biomedicine (BIBM).

[15]  Pierre Soille,et al.  Morphological Image Analysis: Principles and Applications , 2003 .

[16]  N. Kavitha,et al.  A Study on Pre-processing Techniques for Automated Skin Cancer Detection , 2020 .

[17]  Saeid Nahavandi,et al.  Realistic Hair Simulator for Skin lesion Images Using Conditional Generative Adversarial Network , 2018 .

[18]  Weisi Lin,et al.  Perceptual visual quality metrics: A survey , 2011, J. Vis. Commun. Image Represent..

[19]  Alexandru Telea,et al.  Effcient and Effective Automated Digital Hair Removal from Dermoscopy Images , 2016 .

[20]  João Paulo Papa,et al.  Computational methods for pigmented skin lesion classification in images: review and future trends , 2018, Neural Computing and Applications.

[21]  Adam Huang,et al.  A robust hair segmentation and removal approach for clinical images of skin lesions , 2013, 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[22]  Mohammed Hossny,et al.  Digital hair segmentation using hybrid convolutional and recurrent neural networks architecture , 2019, Comput. Methods Programs Biomed..

[23]  I. S. Zaqout,et al.  An Efficient Block-Based Algorithm for Hair Removal in Dermoscopic Images , 2020, Computer Methods and Programs in Biomedical Signal and Image Processing.

[24]  Ammara Masood,et al.  Computer Aided Diagnostic Support System for Skin Cancer: A Review of Techniques and Algorithms , 2013, Int. J. Biomed. Imaging.

[25]  Konstantinos N. Plataniotis,et al.  Towards a Full-Reference Quality Assessment for Color Images Using Directional Statistics , 2015, IEEE Transactions on Image Processing.

[26]  Gabriella Sanniti di Baja,et al.  A New Method for Color Quantization , 2016, 2016 12th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS).

[27]  Manuel González Hidalgo,et al.  An Encoder-Decoder CNN for Hair Removal in Dermoscopic Images , 2020, ArXiv.

[28]  Hamid Reza Pourreza,et al.  An effective hair removal algorithm for dermoscopy images , 2013, Skin research and technology : official journal of International Society for Bioengineering and the Skin (ISBS) [and] International Society for Digital Imaging of Skin (ISDIS) [and] International Society for Skin Imaging.

[29]  Mehmet Türkan,et al.  A survey on automated melanoma detection , 2018, Eng. Appl. Artif. Intell..

[30]  Ke Gu,et al.  Perceptual Reduced-Reference Visual Quality Assessment for Contrast Alteration , 2017, IEEE Transactions on Broadcasting.

[31]  Lucia Maddalena,et al.  SDI+: A Novel Algorithm for Segmenting Dermoscopic Images , 2019, IEEE Journal of Biomedical and Health Informatics.

[32]  A. Tannenbaum,et al.  Despeckling of medical ultrasound images , 2006, IEEE Transactions on Ultrasonics, Ferroelectrics and Frequency Control.

[33]  Gabriella Sanniti di Baja,et al.  A New Technique for Color quantization Based on Histogram Analysis and Clustering , 2013, Int. J. Pattern Recognit. Artif. Intell..

[34]  Xinhua Zhuang,et al.  Image Analysis Using Mathematical Morphology , 1987, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[35]  K. S. Ravichandran,et al.  A Survey on Color Image Segmentation Techniques for Melanoma Diagnosis , 2015 .

[36]  Giuliana Ramella.  Saliency-based segmentation of dermoscopic images using color information , 2021, Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization.

[37]  Giuliana Ramella.  Evaluation of quality measures for color quantization , 2020, ArXiv.

[38]  J. Serra,et al.  An overview of morphological filtering , 1992 .

[39]  Theophano Mitsa,et al.  Evaluation of contrast sensitivity functions for the formulation of quality measures incorporated in halftoning algorithms , 1993, 1993 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[40]  Shi-Yin Qin,et al.  PDE-based unsupervised repair of hair-occluded information in dermoscopy images of melanoma , 2009, Comput. Medical Imaging Graph..