Automatic Segmentation of the Human Ear Using Active Contour and GrabCut Synergy Based on the Superpixel Cluster Regions

Öz

The ear region is a region of the human body region containing valuable biometric information that is subjected to a few physiological changes depending on the individual’s age. Manual, semi-automatic, or fully automatic segmentation of the ear region in various methods related to the use of the ear region in obtaining biometric information is an important area of research. In our study, we present an approach that applies superpixel cluster regions, active contour detection based on geodesic information, and foreground separation by graph cutting, to segregate the human ear region from the image by fully automatic segmentation from the background. Thanks to this approach in our study, the ear foreground mask is created programmatically and fully automatically from the ear image. In the experiments with the ear images data set, the reference ear mask marked by the expert was compared with the automatically created foreground mask. It has been obtained hHigh performance values were obtained, considering the similarity rates (i.e., intersection over union) based on the Jaccard index metric. Our approach has quite good performance values (in the range of 84% to 92%) for the images in this dataset. In our study, the success of the proposed synergistic approach is demonstrated both qualitatively and quantitatively with experimental results.

Anahtar Kelimeler

• Superpixel
• Active contour
• Graph cut
• Image segmentation

Süperpiksel Küme Bölgeleri Tabanlı Aktif Çevrit Ve GrabCut Sinerjisini Kullanarak İnsan Kulağının Otomatik Bölütlenmesi

Öz

Kulak bölgesi bireyin yaşına bağlı olarak fizyolojik bakımdan çok az değişikliğe maruz kalan değerli biyometrik bilgi içeren bir insan vücut bölgesidir. Biyometrik bilgi elde etmede kulak bölgesinin kullanımıyla ilgili çeşitli yöntemlerde kulak bölgesinin elle, yarı otomatik veya tam otomatik olarak bölütlenmesi önemli bir araştırma alanıdır. Çalışmamızda, insan kulak bölgesinin görüntüden tam otomatik olarak bölütlenerek arka plandan ayrıştırılması için süperpiksel küme bölgeleri, jeodezik bilgiye dayanan aktif çevrit tespiti ve çizge kesme yoluyla ön plan ayrıştırma işlemleri uygulayan bir yaklaşım sunulmaktadır. Çalışmamızdaki bu yaklaşım sayesinde kulak ön plan maskesi programatik ve tam otomatik biçimde kulak görüntüsünden oluşturulmaktadır. Kulak görüntüleri veri kümesi ile yapılan deneylerde uzman tarafından işaretlenen referans kulak bölgesi maskesi otomatik olarak oluşturulan ön plan maskesi ile karşılaştırılmıştır. Jaccard endeksi ölçütüne dayalı benzerlik oranları (birleşim kesişimi) dikkate alındığında yüksek başarım değerleri elde edilmiştir. Yaklaşımımız bu veri kümesindeki görüntüler için %84 ilâ %92 aralığında oldukça iyi başarım değerlerine sahiptir. Çalışmamızda, önerilen sinerjik yaklaşımın başarımı hem niteliksel hem de niceliksel olarak deneysel sonuçlarla ortaya konulmaktadır..

Anahtar Kelimeler

• Süperpiksel
• Aktif çevrit
• Çizge kesme
• Görüntü bölütleme

Kaynakça

1. Achanta, R., Shaji, A., Smith, K., Lucchi, A., Fua, P. & Süsstrunk, S. (2012). SLIC Superpixels Compared to State-of-the-Art Superpixel methods. IEEE Transactions on Pattern Analysis and Machine Intelligence, 34(11), 2274–2282. http://dx.doi.org/10.1109/TPAMI.2012.120.
2. Banerjee, S. & Mery, D. (2016). Iris Segmentation Using Geodesic Active Contours and GrabCut. Revised Selected Papers of Image and Video Technology, PSIVT 2015 Workshops, LNCS 9555, (pp. 48-60). Auckland, New Zealand, (Eds., Huang, F., & Sugimoto, A.), Springer International Publishing Switzerland. http://dx.doi.org/10.1007/978-3-319-30285-0_5.
3. Chen, H., & Bhanu, B. (2005, January). Contour matching for 3D ear recognition. Proceedings of the Seventh IEEE Workshop on Applications of Computer Vision Motion and Video Computing (WACV/MOTION2005) (pp. 123-128). Breckenridge, CO, USA. http://dx.doi.org/10.1109/ ACVMOT.2005.38.
4. Cintas, C., Delriux, C., Navarro, P., Quinto-Sànchez, M., Pazos, B. & Gonzalez-Josè, R. (2019). Automatic Ear Detection and Segmentation over Partially Occluded Profile Face Images. Journal of Computer Science Technology, 19(1), 81-89. http://dx.doi.org/10.24215/16666038.19.e08.
5. Cohen, L. D. (1991). On Active Contour Models and Baloons. Computer Vision, Graphics, and Image Processing: Image Understanding, 53(2), 211-218. http://dx.doi.org/10.2016/1049-9660(91)90028-N.
6. El-Naggar, S., Abaza, A., & Bourlai, T. (2018, August). Ear detection in the wild using Faster R-CNN Deep Learning. Proceedings of the IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM2018) (pp. 1124-1130). Barcelona, Spain. http://dx.doi.org/10.1109/ASONAM.2018.8508487.
7. Emeršič, Ž., Gabriel, L. L., Štruc, V., & Peer, P. (2015). Convolutional Encoder-Decoder Networks for Pixel-wise Ear Detection and Segmentation. IET Biometrics, Special İssue: Unconstrained Ear Recognition, 7(3), 175-184. http://dx.doi.org/10.1049/iet-bmt.2017.0240.
8. Emeršič, Ž., Štruc, V., & Peer, P. (2017). Ear Recognition: More than a Survey. Neurocomputing, 255, 26-39. http://dx.doi.org/10.1016/j.neucom.2016.08.139.

9. Gonzalez-Sànchez, E. (2008). Biometria de la Oreja. (Doctoral Dissertation, Universidad de Las Palmas de Gran Canaria, Spain). Mathematical Analysis of Images Database (AMIDB). http://ctim.ulpgc.es/reseach_works/ami_ear_database.
10. Jacob, L., & Raju, G. (2011). Automatic Ear Localization Using An Effective Skin Segmentation Algorithm And Correlation Coefficient in 2D Images. International Journal of Machine Intelligence (IJMI). 3(4), 327-332.
11. Joshi, K. V., & Chauhan, N. C. (2011). Edge Detection and Template Matching Approaches for Human Ear Detection. International Journal of Computer Applications, Special Issue for International Conference on Intelligent Systems and Data Processing (ICISD2011), 1(1), 50-55.
12. Khattab, D., Ebied, H. M., Husein, A. S., & Tolba, M. F. (2014). Color Image Segmentation Based on Different Color Space Models Using Automatic GrabCut. The Scientific World Journal, 2014, 126025,1-10. http://dx.doi.org/10.1155/2014/126025.
13. Màrquez-Neila, P., Baumela, L., & Alvarez, L. (2014). A Morphological Approach to Curvature-based Evolution of Curves and Surfaces. IEEE Transactions on Pattern Analysis and Machine Intelligence, 36(1), 2-17. http://dx.doi.org/TPAMI.2013.106.
14. Pflug, A., & Busch, C. (2012). Ear Biometrics: A Survey of detection, feature extraction and recognition methods. IET Biometrics, 1(2), 114-129. http://dx.doi.org/10.1049/iet-bmt.2011.0003.
15. Schuckers, M. E., (2010). Computational Methods in Biometric Authentication, Statistical Methods for Performance Evaluation. Information Science and Statistics. Springer-Verlag London Limited.
16. Tomczyk, A., & Szczepaniak, P. S. (2019). Ear Detection using Convolutional Neural Network on Graphs with Filter Rotation. Sensors (MDPI), 19, 5510, 1-21. http://dx.doi.org/10.3390/s19245510.
17. Tushar, F. I., (2018). Automatic Skin Lesion Segmentation Using GrabCut in HSV Colour Space. Computer Vision and Pattern Recognition (cs.cv), ArXiv. 1-3. Retrieved from: https://arxiv.org/abs/1810.00871.
18. University of Notre Dame. UND Face Database. (2015). Erişim adresi: http://www.nd.edu/cvrl/CVRL/DataSets.html. (Erişim zamanı: 12.03.2021).
19. University of Science and Technology Beijing. Ear Recognition Laboratory USTB Database. (2002). Erişim adresi: http://www1.ustb.edu.cn/resb/en/doc/Imagedb_123_intro_en.pdf. (Erişim zamanı: 12.03.2021).
20. Walt, S. V. D., Schönberger, J. L., Nunez-Iglesias, J., Boulogne, F., Warner, J. D., Yager, N., Gouillart, E., & Yu., T. (2014). Sckit-Image: Image Processing in Python. Peer J. Life & Enivronment. 2(e453), 1-18. http://dx.doi.org/10.7717/peerj.453
21. Wang, Z., Yang, J., & Zhu, Y. (2021). Review of Ear Biometrics. Archives of Computational Methods in Engineering. 28, 149-180. http://dx.doi.org/10.1007/s11831-019-09376-2.