Comparation Analysis of Otsu Method for Image Braille Segmentation : Python Approaches

Ardi Anugerah Wicaksana; Anik Nur Handayani

doi:10.56705/ijodas.v6i2.268

Authors

Ardi Anugerah Wicaksana Universitas Negeri Malang
Anik Nur Handayani Universitas Negeri Malang

DOI:

https://doi.org/10.56705/ijodas.v6i2.268

Keywords:

Braille, Image Segmentation, Otsu Method, Python

Abstract

Braille plays a crucial role in supporting literacy for individuals with visual impairments. However, converting Braille documents into digital text remains a technical challenge, particularly in accurately segmenting Braille dots from scanned images. This study aims to evaluate and compare the effectiveness of several classical image segmentation techniques—namely Otsu, Otsu Inverse, Otsu Morphology, and Otsu Inverse Morphology—in enhancing Braille image pre-processing. The methods were tested using a set of Braille image datasets and evaluated based on six quantitative image quality metrics: Peak Signal-to-Noise Ratio (PSNR), Mean Squared Error (MSE), Mean Absolute Error (MAE), Structural Similarity Index (SSIM), Feature Similarity Index (FSIM), and Edge Similarity Index (ESSIM). The results show that the Otsu Morphology method achieved the highest PSNR (27.6798) and SSIM (0.5548), indicating superior image fidelity and structural preservation, while the standard Otsu method yielded the lowest MSE (113.3485).These findings demonstrate that applying morphological operations in combination with thresholding significantly enhances the segmentation quality of Braille images, supporting better accuracy in subsequent recognition tasks. This approach offers a practical and efficient alternative to deep learning models, particularly for resource-constrained systems such as portable Braille readers.

Downloads

Download data is not yet available.

References

R. A. D. Cahya, A. N. Handayani, and A. P. Wibawa, “Mobile Braille Touch Application for Visually Impaired People using Double Diamond Approach,” MATEC Web Conf., vol. 197, p. 15007, 2018, doi: 10.1051/matecconf/201819715007.

M. A. D. Widyadara, A. P. Wibawa, and A. N. Handayani, “Enhanced Braille Character Recognition Using Mask Region-Convolutional Neural Network (MRCNN),” 2024. doi: 10.2139/ssrn.4951503.

F. A. Rahman et al., “Assistive Device for Visual Impaired Person Based on Real Time Object Detection,” in 2020 4th International Conference on Vocational Education and Training (ICOVET), Malang, Indonesia: IEEE, Sep. 2020, pp. 190–194. doi: 10.1109/ICOVET50258.2020.9230285.

P. Yang, W. Song, X. Zhao, R. Zheng, and L. Qingge, “An improved Otsu threshold segmentation algorithm,” Int. J. Comput. Sci. Eng., vol. 22, no. 1, p. 146, 2020, doi: 10.1504/IJCSE.2020.107266.

S. Husham et al., “Comparative Analysis between Active Contour and Otsu Thresholding Segmentation Algorithms in Segmenting Brain Tumor Magnetic Resonance Imaging,” J. Inf. Technol. Manag., vol. 12, no. Special Issue: Deep Learning for Visual Information Analytics and Management., Dec. 2020, doi: 10.22059/jitm.2020.78889.

J. Xing, P. Yang, and L. Qingge, “Robust 2D Otsu’s Algorithm for Uneven Illumination Image Segmentation,” Comput. Intell. Neurosci., vol. 2020, pp. 1–14, Aug. 2020, doi: 10.1155/2020/5047976.

Z. Peng and J. Fan, “Median-type Otsu threshold segmentation based on energy curve,” in 2023 6th International Conference on Artificial Intelligence and Pattern Recognition (AIPR), Xiamen China: ACM, Sep. 2023, pp. 140–148. doi: 10.1145/3641584.3641605.

Z. Jing and B. Tang, “Improved image segmentation method based on Otsu thresholding and level set techniques,” J. Phys. Conf. Ser., vol. 2813, no. 1, p. 012017, Aug. 2024, doi: 10.1088/1742-6596/2813/1/012017.

Bolan Su, Shijian Lu, and Chew Lim Tan, “Robust Document Image Binarization Technique for Degraded Document Images,” IEEE Trans. Image Process., vol. 22, no. 4, pp. 1408–1417, Apr. 2013, doi: 10.1109/TIP.2012.2231089.

A. AlSalman, A. El-Zaart, S. Al-Salman, and A. Gumaei, “A novel approach for Braille images segmentation,” in 2012 International Conference on Multimedia Computing and Systems, Tangiers, Morocco: IEEE, May 2012, pp. 190–195. doi: 10.1109/ICMCS.2012.6320146.

W. A. H. Jumiawi and A. El-Zaart, “Otsu Thresholding Model Using Heterogeneous Mean Filters for Precise Images Segmentation,” in 2022 International Conference of Advanced Technology in Electronic and Electrical Engineering (ICATEEE), M’sila, Algeria: IEEE, Nov. 2022, pp. 1–6. doi: 10.1109/ICATEEE57445.2022.10093097.

H. Rahmi Fajrin, Y. Kim, and S. Dong Min, “A Comparative Study of Image Segmentation Techniques in Mammograms (Otsu Thresholding, FCM, and U-Net),” in 2024 International Conference on Information Technology and Computing (ICITCOM), Yogyakarta, Indonesia: IEEE, Aug. 2024, pp. 334–339. doi: 10.1109/ICITCOM62788.2024.10762244.

M. Alkalai and A. Lawgali, “Image-Preprocessing and Segmentation Techniques for Vehicle-Plate Recognition,” in 2020 IEEE 4th International Conference on Image Processing, Applications and Systems (IPAS), Genova, Italy: IEEE, Dec. 2020, pp. 40–45. doi: 10.1109/IPAS50080.2020.9357430.

H. Singh, S. Kaur, and P. Sharma, “Utilizing Various Filtering Methodologies in Digital Image Processing,” in 2024 International Conference on Electrical Electronics and Computing Technologies (ICEECT), Greater Noida, India: IEEE, Aug. 2024, pp. 1–6. doi: 10.1109/ICEECT61758.2024.10738905.

T. G. Debelee, F. Schwenker, S. Rahimeto, and D. Yohannes, “Evaluation of modified adaptive k-means segmentation algorithm,” Comput. Vis. Media, vol. 5, no. 4, pp. 347–361, Dec. 2019, doi: 10.1007/s41095-019-0151-2.

S. Sulma et al., “Adaptive threshold from the Sentinel-2 oil spill index for oil spill detection,” in Eighth Geoinformation Science Symposium 2023: Geoinformation Science for Sustainable Planet, C. M. Roelfsema, A. Besse Rimba, S. Arjasakusuma, and A. Blanco, Eds., Yogyakarta, Indonesia: SPIE, Jan. 2024, p. 14. doi: 10.1117/12.3009372.

M. Dublish, Dr. A. P. Mishra, V. Kumar, and R. Kumar, “MORPHOLOGICAL IMAGE PROCESSING AND IMAGE REGISTRATION,” in Futuristic Trends in Network & Communication Technologies Volume 2 Book 19, Dr. T. Srinivasarao, Dr. B. Somasekhar, Dr. R. P. Savanekar, Dr. Y. P. (Bhise), Dr. D. G. V, A. V. Durga, Dr. P. Karuppasamy, Dr. S. D. Bhopale, Dr. B. S. K. Reddy, Dr. Ch. V. M. S. N. P. Kumar, and Dr. H. K. Singh, Eds., Iterative International Publishers, Selfypage Developers Pvt Ltd, 2023, pp. 169–211. doi: 10.58532/V2BS19P2CH7.

R. A. Lotufo, R. Audigier, A. V. Saúde, and R. C. Machado, “Morphological Image Processing,” in Microscope Image Processing, Elsevier, 2023, pp. 75–117. doi: 10.1016/B978-0-12-821049-9.00012-5.

M. Shetty and R. Balasubramani, “Microscopic Image Noise Reduction Using Mathematical Morphology,” in International Conference on Innovative Computing and Communications, vol. 1166, D. Gupta, A. Khanna, S. Bhattacharyya, A. E. Hassanien, S. Anand, and A. Jaiswal, Eds., in Advances in Intelligent Systems and Computing, vol. 1166. , Singapore: Springer Singapore, 2021, pp. 585–594. doi: 10.1007/978-981-15-5148-2_52.

J. Wang, S. Duan, and Q. Zhou, “An Adaptive Weighted Image Denoising Method Based on Morphology,” Int. J. Circuits Syst. Signal Process., vol. 15, pp. 271–279, Apr. 2021, doi: 10.46300/9106.2021.15.31.

V. K. Nassa and G. S. Wedpathak, “Thresholding Techniques Comparsion on Grayscale Image Segmentation,” in AGC 2023, vol. 2008, S. Dhar, S. Goswami, U. Dinesh Kumar, I. Bose, R. Dubey, and C. Mazumdar, Eds., in Communications in Computer and Information Science, vol. 2008. , Cham: Springer Nature Switzerland, 2024, pp. 136–146. doi: 10.1007/978-3-031-50815-8_9.

S. Dai, Z. He, and J. Liu, “Research on data-driven low-sampling-rate single-pixel imaging method,” Opt. Lett., vol. 48, no. 23, p. 6132, Dec. 2023, doi: 10.1364/OL.507670.

K. Chiranjeevi, M. S. R. Naidu, G. S. S. S. S. V. Krishna Mohan, V. Manohar, S. K. Gottapu, and A. K. Indugupalli, “A Novel Optimization Algorithm for Otsu’s Entropy-Based Multi-Level Thresholding for Image Segmentation,” Res. Rep. Comput. Sci., Aug. 2024, doi: 10.37256/rrcs.3220244958.

O. H. R. G. Sugiarto and Y. P. Santosa, “COMPARISON OF THRESHOLDING OTSU AND MORPHOLOGY OPENING PREPROCESSOR FOR IMAGE TEXT DETECTION USING TESSERACT,” Proxies J. Inform., vol. 5, no. 2, pp. 118–128, Aug. 2024, doi: 10.24167/proxies.v5i2.12449.

J. A. Baik, J. W. Choi, and J. J. Kim, “Segmentation Performance Analysis of the Otsu Algorithm for Spent Nuclear Fuel Cladding Image According to Morphological Operations,” J. Nucl. Fuel Cycle Waste Technol., vol. 22, no. 3, pp. 301–311, Sep. 2024, doi: 10.7733/jnfcwt.2024.031.

Z. Xie, J. Wu, W. Tang, and Y. Liu, “Advancing image segmentation with DBO-Otsu: Addressing rubber tree diseases through enhanced threshold techniques,” PLOS ONE, vol. 19, no. 3, p. e0297284, Mar. 2024, doi: 10.1371/journal.pone.0297284.

S. Hao and S. Li, “A Weighted Mean Absolute Error Metric for Image Quality Assessment,” in 2020 IEEE International Conference on Visual Communications and Image Processing (VCIP), Macau, China: IEEE, Dec. 2020, pp. 330–333. doi: 10.1109/VCIP49819.2020.9301889.

H. Gupta, H. Singh, A. Kumar, A. Vishwakarma, and G. K. Singh, “Variational mode decomposition based image denoising using semi-adaptive conductance function inspired diffusion filtering,” Multimed. Tools Appl., vol. 83, no. 3, pp. 7433–7456, Jan. 2024, doi: 10.1007/s11042-023-15863-3.

U. Sara, M. Akter, and M. S. Uddin, “Image Quality Assessment through FSIM, SSIM, MSE and PSNR—A Comparative Study,” J. Comput. Commun., vol. 07, no. 03, pp. 8–18, 2019, doi: 10.4236/jcc.2019.73002.

A. Shah et al., “Comparative analysis of median filter and its variants for removal of impulse noise from gray scale images,” J. King Saud Univ. - Comput. Inf. Sci., vol. 34, no. 3, pp. 505–519, Mar. 2022, doi: 10.1016/j.jksuci.2020.03.007.

M. Fernández Patón et al., “MR Denoising Increases Radiomic Biomarker Precision and Reproducibility in Oncologic Imaging,” J. Digit. Imaging, vol. 34, no. 5, pp. 1134–1145, Oct. 2021, doi: 10.1007/s10278-021-00512-8.