Skinny: A Lightweight U-Net For Skin Detection And Segmentation

The use of deep-learned features has recently allowed for improving the performance of skin detection and segmentation. In particular, fully-convolutional U-Nets, proposed for segmenting medical images, occurred to be extremely effective here. However, the spatial context, which is rather narrow for U-Nets, may be more important for skin segmentation than for segmenting other image structures. We propose Skinny—a lightweight U-Net-based architecture that extends the range of multi-scale analysis. The results of our experiments indicate that Skinny outperforms the state-of-the-art skin segmentation techniques, rendering the F-score of 92.3% and 94.9% for the ECU and HGR datasets, respectively.

[1]  Erik Blasch,et al.  Combining Convolutional and Recurrent Neural Networks for Human Skin Detection , 2017, IEEE Signal Processing Letters.

[2]  James F. Peters,et al.  Multi-manifold-based skin classifier on feature space Voronoï regions for skin segmentation , 2016, J. Vis. Commun. Image Represent..

[3]  Hung-Ming Sun,et al.  Skin detection for single images using dynamic skin color modeling , 2010, Pattern Recognit..

[4]  James M. Rehg,et al.  Statistical Color Models with Application to Skin Detection , 2004, International Journal of Computer Vision.

[5]  Sergey Ioffe,et al.  Rethinking the Inception Architecture for Computer Vision , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[6]  Nikolaos G. Bourbakis,et al.  A survey of skin-color modeling and detection methods , 2007, Pattern Recognit..

[7]  Yi He,et al.  Semi-Supervised Skin Detection by Network With Mutual Guidance , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[8]  Peter H. N. de With,et al.  Application and evaluation of texture-adaptive skin detection in TV image enhancement , 2013, 2013 IEEE International Conference on Consumer Electronics (ICCE).

[9]  Axel Krieger,et al.  Adaptation and Evaluation of Deep Learning Techniques for Skin Segmentation on Novel Abdominal Dataset , 2019, 2019 IEEE 19th International Conference on Bioinformatics and Bioengineering (BIBE).

[10]  Nam Ik Cho,et al.  Convolutional neural networks and training strategies for skin detection , 2017, 2017 IEEE International Conference on Image Processing (ICIP).

[11]  Abdesselam Bouzerdoum,et al.  Skin segmentation using color pixel classification: analysis and comparison , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[12]  William Puech,et al.  Selective Encryption of Human Skin in JPEG Images , 2006, 2006 International Conference on Image Processing.

[13]  Kilian Q. Weinberger,et al.  Densely Connected Convolutional Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[14]  Pau-Choo Chung,et al.  Naked image detection based on adaptive and extensible skin color model , 2007, Pattern Recognit..

[15]  Jakub Nalepa,et al.  Skin detection using spatial analysis with adaptive seed , 2013, 2013 IEEE International Conference on Image Processing.

[16]  Dong-Seog Han,et al.  A hardware skin-segmentation IP for vision based smart ADAS through an FPGA prototyping , 2017, 2017 Ninth International Conference on Ubiquitous and Future Networks (ICUFN).

[17]  Jakub Nalepa,et al.  Skin Detection and Segmentation in Color Images , 2014 .

[18]  Rini Akmeliawati,et al.  Dynamic approach for real-time skin detection , 2012, Journal of Real-Time Image Processing.

[19]  Loris Nanni,et al.  Learning morphological operators for skin detection , 2019, ArXiv.

[20]  Roman Starosolski.  Skipping Selected Steps of DWT Computation in Lossless JPEG 2000 for Improved Bitrates , 2016, PloS one.

[21]  Loris Nanni,et al.  Fair comparison of skin detection approaches on publicly available datasets , 2018, Expert Syst. Appl..

[22]  M. A. Chyad,et al.  The Landscape of Research on Skin Detectors: Coherent Taxonomy, Open Challenges, Motivations, Recommendations and Statistical Analysis, Future Directions , 2019, IEEE Access.

[23]  Stefano Tubaro,et al.  Deep skin detection on low resolution grayscale images , 2020, Pattern Recognit. Lett..

[24]  A. Lynn Abbott,et al.  Universal Skin Detection Without Color Information , 2017, 2017 IEEE Winter Conference on Applications of Computer Vision (WACV).

[25]  Martin Fleury,et al.  Skin detection and lightweight encryption for privacy protection in real-time surveillance applications , 2020, Image Vis. Comput..

[26]  Jakub Nalepa,et al.  Spatial-based skin detection using discriminative skin-presence features , 2014, Pattern Recognit. Lett..

[27]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[28]  Jakub Nalepa,et al.  Self-adaptive algorithm for segmenting skin regions , 2014, EURASIP J. Adv. Signal Process..

[29]  Huang-Chia Shih,et al.  Human Skin Segmentation Using Fully Convolutional Neural Networks , 2018, 2018 IEEE 7th Global Conference on Consumer Electronics (GCCE).

[30]  Rajiv Ranjan Sahay,et al.  Deep Learning Based Hand Detection in Cluttered Environment Using Skin Segmentation , 2017, 2017 IEEE International Conference on Computer Vision Workshops (ICCVW).

[31]  Shanq-Jang Ruan,et al.  Statistical skin color detection method without color transformation for real-time surveillance systems , 2012, Eng. Appl. Artif. Intell..

[32]  Hamid A. Jalab,et al.  A survey on skin detection in colored images , 2018, Artificial Intelligence Review.

[33]  Kang Ryoung Park,et al.  OR-Skip-Net: Outer residual skip network for skin segmentation in non-ideal situations , 2020, Expert Syst. Appl..