Image Segmentation Using Spiking Neural Network Based Edge Detection and Seeded Region Growing

Abstract

Digital image segmentation is a critical step in image analysis, pattern recognition, and computer vision applications. In this study, a hybrid method is proposed to improve the accuracy and efficiency of the segmentation process by combining Spiking Neural Network-based edge detection with the Seeded Region Growing algorithm. Initially, the edges of the image are detected by leveraging the biologically inspired structure of Spiking Neural Networks, allowing for more precise localization of object boundaries. The resulting edge map is then used to guide the Seeded Region Growing algorithm. After edge detection, the remaining homogeneous regions are expanded using Seeded Region Growing, completing the segmentation process. The proposed method has been tested on various images, and the results demonstrate superior performance in terms of edge detection accuracy and region consistency.

Keywords

• Image Segmentation
• Seeded Region Growing
• Spiking Neural Network
• Conducted Integrated and Fire.

Ethical Statement

This study does not involve human participants or animals. All data used in this research were obtained from publicly available datasets and processed in accordance with relevant academic and ethical standards. The authors declare that this work complies with publication ethics and contains no plagiarism, fabrication, falsification, or inappropriate data manipulation.

Thanks

The authors gratefully acknowledge the Editor and the Reviewers for their professional evaluation, valuable feedback, and constructive recommendations. Their comments have helped us to enhance the scientific quality and presentation of the manuscript.

İğnecikli Sinir Ağı Tabanlı Kenar Algılama ve Tohumlu Alan Genişletme Kullanılarak Görüntü Bölütleme

Abstract

Dijital görüntü segmentasyonu, görüntü analizi, desen tanıma ve bilgisayarlı görme uygulamalarında kritik bir adımdır. Bu çalışmada, Spiking Sinir Ağı tabanlı kenar algılama ile Tohumlu Bölge Büyütme algoritmasını birleştirerek segmentasyon sürecinin doğruluğunu ve verimliliğini artırmak için hibrit bir yöntem önerilmiştir. Başlangıçta, görüntünün kenarları Spiking Sinir Ağlarının biyolojik olarak ilham alan yapısından yararlanılarak tespit edilir ve bu da nesne sınırlarının daha hassas bir şekilde belirlenmesini sağlar. Elde edilen kenar haritası daha sonra Tohumlu Bölge Büyütme algoritmasına rehberlik etmek için kullanılır. Kenar tespitinden sonra, kalan homojen bölgeler Tohumlu Bölge Büyütme kullanılarak genişletilerek segmentasyon süreci tamamlanır. Önerilen yöntem çeşitli görüntüler üzerinde test edilmiş ve sonuçlar kenar algılama doğruluğu ve bölge tutarlılığı açısından üstün performans göstermiştir.

Keywords

• Tohumlu Bölge Büyütme
• Çivileme Sinir Ağı
• İletilen Entegre ve Ateşleme
• Görüntü Bölütleme

Ethical Statement

Bu çalışma insan katılımcıları veya hayvanları içermemektedir. Bu araştırmada kullanılan tüm veriler, kamuya açık veri setlerinden elde edilmiş ve ilgili akademik ile etik standartlara uygun şekilde işlenmiştir. Yazarlar, bu çalışmanın yayın etiği ilkelerine uygun olduğunu; intihal, uydurma, tahrifat veya uygunsuz veri manipülasyonu içermediğini beyan eder.

Thanks

Yazarlar, profesyonel değerlendirmeleri, değerli geri bildirimleri ve yapıcı önerileri için Editöre ve Hakemlere içten teşekkür eder. Yorumları, makalenin bilimsel niteliğini ve sunum kalitesini geliştirmemize katkı sağlamıştır.

References

1. [1] Brar, K. K., et al. (2024). Image segmentation review: Theoretical background and recent advances. Information Fusion, 102608, https://doi.org/10.1016/j.inffus.2024.102608.
2. [2] Davies, E. R. (2012). Computer and machine vision: Theory, algorithms, practicalities . Academic Press.
3. [3] Sonka, M., Hlavac, V., & Boyle, R. (2013). Image processing, analysis and machine vision . Springer.
4. [4] Gonzalez, R. C. (2009). Digital image processing . Pearson Education India.
5. [5] Dong, B., Weng, G., Bu, Q., Zhu, Z., & Ni, J. (2024). An active contour model based on shadow image and reflection edge for image segmentation. Expert Systems with Applications, 238, 122330, https://doi.org/10.1016/j.eswa.2023.122330.
6. [6] Shelei, L., & Mengxing, H. (2018). Research of underwater image segmentation algorithm based on the improved geometric active contour models. In 2018 International Conference on Intelligent Autonomous Systems (ICoIAS) (pp. 44–50). IEEE.
7. [7] Kass, M., Witkin, A., & Terzopoulos, D. (1988). Snakes: Active contour models. International Journal of Computer Vision, 1 (4), 321–331.
8. [8] Kumar, A., Tewari, N., & Kumar, R. (2022). A comparative study of various techniques of image segmentation for the identification of hand gesture used to guide the slide show navigation. Multimedia Tools and Applications, 81 (10), 14503–14515, https://doi.org/10.1007/s11042-022-12203-9

9. [9] Wang, X.-G., & Chen, S.-H. (2012). An improved image segmentation algorithm based on two-dimensional Otsu method. Information Sciences Letters, 1 (2), 77–83.
10. [10] Badran, E. F., Mahmoud, E. G., & Hamdy, N. (2010). An algorithm for detecting brain tumors in MRI images. In The 2010 International Conference on Computer Engineering & Systems (pp. 368–373). IEEE.
11. [11] Palconit, M. G. B., et al. (2021). Counting of uneaten floating feed pellets in water surface images using ACF detector and Sobel edge operator. In 2021 IEEE 9th Region 10 Humanitarian Technology Conference (R10-HTC) (pp. 1–5). IEEE.
12. [12] Pratt, W. K. (2007). Digital image processing: PIKS Scientific inside . Wiley Online Library.
13. [13] Jia, Z., & Huang, Q. (2022). Image interpolation with regional gradient estimation. Applied Sciences, 12 (15), 7359, https://doi.org/10.3390/app12157359
14. [14] İncetaş, M. O. (2023). Image interpolation based on spiking neural network model. Applied Sciences, 13 (4), 2438, https://doi.org/10.3390/app13042438
15. [15] İncetaş, M. O. (2022). Anisotropic diffusion filter based on spiking neural network model. Arabian Journal for Science and Engineering, 47 (8), 9849–9860, https://doi.org/10.1007/s13369-021-06404-x
16. [16] İncetaş, M. O., Kılıçaslan, M., & Farshi, T. R. (2022). Image retrieval with SNN-based multi-level thresholding. Gümüşhane Üniversitesi Fen Bilimleri Dergisi , 98–108, https://doi.org/10.17714/gumusfenbil.1002577
17. [17] Xue, J., et al. (2023). EdgeMap: An optimized mapping toolchain for spiking neural network in edge computing. Sensors, 23 (14), 6548, https://doi.org/10.3390/s23146548
18. [18] Vemuru, K. V. (2020). Image edge detector with Gabor type filters using a spiking neural network of biologically inspired neurons. Algorithms, 13 (7), 165, https://doi.org/10.3390/a13070165
19. [19] Meftah, B., Lezoray, O., & Benyettou, A. (2010). Segmentation and edge detection based on spiking neural network model. Neural Processing Letters, 32 , 131–146, https://doi.org/10.1007/s11063-010-9149-6
20. [20] İncetaş, M. O., & Arslan, R. U. (2019). Edge detection using integrate and fire neuron. Süleyman Demirel Üniversitesi Fen Bilimleri Enstitüsü Dergisi, 23 (2), 611–616, https://doi.org/10.19113/sdufenbed.570597
21. [21] İncetas, M. O., & Arslan, R. U. (2025). Spiking neural network-based edge detection model for content-based image retrieval. Signal, Image and Video Processing, 19 (1), 169, https://doi.org/10.1007/s11760-024-03799-6
22. [22] Park, S. S., & Choi, Y.-S. (2024). Spiking neural networks for physiological and speech signals: A review. Biomedical Engineering Letters, 14 (5), 943–954, https://doi.org/10.1007/s13534-024-00404-0
23. [23] Chen, L., Xiong, X., & Liu, J. (2022). A survey of intelligent chip design research based on spiking neural networks. IEEE Access, 10 , 89663–89686, https://doi.org/10.1109/ACCESS.2022.3200454
24. [24] Yu, J., Lu, X., Guo, L., Wang, C., Li, G., & Qian, J. (2025). Event-based video reconstruction via spatial-temporal heterogeneous spiking neural network. IEEE Transactions on Circuits and Systems for Video Technology , https://doi.org/10.1109/TCSVT.2025.3550901
25. [25] Incetas, M. O., Demirci, R., & Yavuzcan, H. G. (2014). Automatic segmentation of color images with transitive closure. AEU - International Journal of Electronics and Communications, 68 (3), 260–269, https://doi.org/10.1016/j.aeue.2013.09.001
26. [26] İncetaş, M. O., & Tanyeri, U. (2019). The effects of noise filters on segmentation based seeded region growing. Mühendislik Bilimleri ve Tasarım Dergisi, 7 (4), 725–735, https://doi.org/10.21923/jesd.420101
27. [27] Argun, M. Ş., Türk, F., & Civelek, Z. (2024). U2-Net segmentation and multi-label CNN classification of wheat varieties. Konya Journal of Engineering Sciences, 12 (2), 358–372, https://doi.org/10.36306/konjes.1364509
28. [28] Argun, M. Ş., Türk, F., & Kurt, A. (2023). Non-destructive prediction of bread staling using artificial intelligence methods. Bitlis Eren Üniversitesi Fen Bilimleri Dergisi, 12 (4), 985–993, https://doi.org/10.17798/bitlisfen.1308493