A Novel Local Adaptive Percentage Split Distribution Method for Image Binarization and Classification

PDF (1843KB), PP.29-46

Views: 0 Downloads: 0

Author(s)

Joy Christy A. 1 Umamakeswari A. 1,* Shanthi P. 1 Srilakshmi A. 1 Siva Chandrasekaran 2

1. SASTRA Deemed to be University, Thanjavur, India

2. Swimburne University of Technology, Melbourne, Australia

* Corresponding author.

DOI: https://doi.org/10.5815/ijigsp.2025.02.02

Received: 15 Jun. 2023 / Revised: 5 Sep. 2023 / Accepted: 31 Oct. 2024 / Published: 8 Apr. 2025

Index Terms

Binary thresholding, global thresholding, local adaptive thresholding, PSNR, SSIM, MSE

Abstract

Binary thresholding methods separate image pixels into two groups as 0s or 1s. The two types of binary thresholding methods are global thresholding and local thresholding. Global thresholding methods are appropriate for binarizing the images that has smooth and contrast distribution of pixels. The performance of global thresholding struggles with distorted and tampered images as it introduces additional noise and causes variation in contrast and illumination. Local adaptive thresholding methods address the issue with every pixel a threshold based on the contrast distribution of neighboring pixels. This paper introduces Local Adaptive Percentage Split Distribution (LAPSD) method for binarization. LAPSD computes threshold based on percentage wise split of neighboring pixels. The performance of LAPSD is compared with benchmark binary thresholding methods such Bradley’s, Niblack’s, and Sauvola’s against PSNR, SSIM and MSE metrics. The accuracy of LAPSD image binarization is measured using Convolution Neural Network (CNN) models and the results prove that the performance of the proposed method surpasses traditional methods in all means.  

Cite This Paper

Joy Christy A., Umamakeswari A., Shanthi P., Srilakshmi A., Siva Chandrasekaran, "A Novel Local Adaptive Percentage Split Distribution Method for Image Binarization and Classification", International Journal of Image, Graphics and Signal Processing(IJIGSP), Vol.17, No.2, pp. 29-46, 2025. DOI:10.5815/ijigsp.2025.02.02

Reference

[1]Lu, T. and Dooms, A., 2021. Probabilistic homogeneity for document image segmentation. Pattern Recognition, 109, p.107591.
[2]Mittal, M., Arora, M., Pandey, T. and Goyal, L.M., 2020. Image segmentation using deep learning techniques in medical images. In Advancement of machine intelligence in interactive medical image analysis (pp. 41-63). Springer, Singapore.
[3]Kaur, S., Kaur, N. and Kaur, K., 2020. Image segmentation: techniques and its applications. Journal of Natural Remedies, 21(2), pp.79-87.
[4]Tomchuk, K.K. and Volkov, V.Y., 2020, June. Analysis of the Quality of Thresholding for Object Detection in Images. In 2020 Wave Electronics and its Application in Information and Telecommunication Systems (WECONF) (pp. 1-5). IEEE.
[5]Mehta, N., Braun, P.X., Gendelman, I., Alibhai, A.Y., Arya, M., Duker, J.S. and Waheed, N.K., 2020. Repeatability of binarization thresholding methods for optical coherence tomography angiography image quantification. Scientific reports, 10(1), pp.1-11.
[6]Minaee, S., Boykov, Y.Y., Porikli, F., Plaza, A.J., Kehtarnavaz, N. and Terzopoulos, D., 2021. Image segmentation using deep learning: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence.
[7]Adegun, A. and Viriri, S., 2021. Deep learning techniques for skin lesion analysis and melanoma cancer detection: a survey of state-of-the-art. Artificial Intelligence Review, 54(2), pp.811-841.
[8]Aslam, Y., Santhi, N., Ramasamy, N. and Ramar, K., 2020. Localization and segmentation of metal cracks using deep learning. Journal of Ambient Intelligence and Humanized Computing, pp.1-9.
[9]Yamni, M., Daoui, A., Karmouni, H., Sayyouri, M., Qjidaa, H. and Flusser, J., 2020. Fractional Charlier moments for image reconstruction and image watermarking. Signal Processing, 171, p.107509.
[10]Volkov, V.Y., Bogachev, M.I. and Kayumov, A.R., 2020. Object selection in computer vision: from multi-thresholding to percolation based scene representation. In Computer Vision in Advanced Control Systems-5 (pp. 161-194). Springer, Cham.
[11]Nichele, L., Persichetti, V., Lucidi, M. and Cincotti, G., 2020. Quantitative evaluation of ImageJ thresholding algorithms for microbial cell counting. OSA Continuum, 3(6), pp.1417-1427.
[12]Michalak, H. and Okarma, K., 2020. Optimization of Degraded Document Image Binarization Method Based on Background Estimation.
[13]Abdusalomov, A., Mukhiddinov, M., Djuraev, O., Khamdamov, U. and Whangbo, T.K., 2020. Automatic salient object extraction based on locally adaptive thresholding to generate tactile graphics. Applied Sciences, 10(10), p.3350.
[14]Rani, N.S., Karthik, U. and Ranjith, S., 2020. Extraction of Gliomas from 3D MRI Images using Convolution Kernel Processing and Adaptive Thresholding. Procedia Computer Science, 167, pp.273-284.
[15]Li, J., Hu, B. and Cao, Z., 2020, August. A new QR Code Recognition Method using Deblurring and Modified Local Adaptive Thresholding Techniques. In 2020 IEEE 16th International Conference on Automation Science and Engineering (CASE) (pp. 1269-1274). IEEE.
[16]Liang, J. and Liu, D., 2020. A local thresholding approach to flood water delineation using Sentinel-1 SAR imagery. ISPRS Journal of Photogrammetry and Remote Sensing, 159, pp.53-62.
[17]Ganem, J., Thureau, S., Gardin, I., Modzelewski, R., Hapdey, S. and Vera, P., 2018. Delineation of lung cancer with FDG PET/CT during radiation therapy. Radiation Oncology, 13(1), pp.1-8.
[18]Rahimi-Nasrabadi, H., Jin, J., Mazade, R., Pons, C., Najafian, S. and Alonso, J.M., 2021. Image luminance changes contrast sensitivity in visual cortex. Cell reports, 34(5), p.108692.
[19]Zhou, F., Jia, Z., Yang, J. and Kasabov, N., 2017. Method of improved fuzzy contrast combined adaptive threshold in NSCT for medical image enhancement. BioMed research international, 2017.
[20]Singh, P., 2020. A neutrosophic-entropy based adaptive thresholding segmentation algorithm: A special application in MR images of Parkinson's disease. Artificial Intelligence in Medicine, 104, p.101838.
[21]Yahya, A.A., Tan, J., Su, B., Liu, K. and Hadi, A.N., 2019. Image noise reduction based on adaptive thresholding and clustering. Multimedia Tools and Applications, 78(11), pp.15545-15573.
[22]Wang, C., Chen, Z., Wang, Y. and Wang, Z., 2018. Denoising and 3D reconstruction of CT images in extracted tooth via wavelet and bilateral filtering. International Journal of Pattern Recognition and Artificial Intelligence, 32(05), p.1854010.
[23]Cheremkhin, P.A. and Kurbatova, E.A., 2019. Comparative appraisal of global and local thresholding methods for binarisation of off-axis digital holograms. Optics and Lasers in Engineering, 115, pp.119-130.
[24]Buayai, P., Kantanukul, T., Leung, C.K. and Runapongsa Saikaew, K., 2017. Boundary detection of pigs in pens based on adaptive thresholding using an integral image and adaptive partitioning.
[25]Thanh, D.N., 2020. An adaptive local thresholding roads segmentation method for satellite aerial images with normalized HSV and lab color models. In Intelligent Computing in Engineering (pp. 865-872). Springer, Singapore.
[26]Gan, H.S., Salam, B.A.J.A., Khaizi, A.S.A., Ramlee, M.H., Mahmud, W.M.W., Lee, Y.S., Sayuti, K.A. and Musa, A.T., 2019. Local mean based adaptive thresholding to classify the cartilage and background superpixels. Indonesian Journal of Electrical Engineering and Computer Science, 15(1), pp.221-230.
[27]Nandy, M. and Banerjee, M., 2017, October. A comparative analysis of application of niblack and sauvola binarization to retinal vessel segmentation. In 2017 3rd International Conference on Computational Intelligence and Networks (CINE) (pp. 105-109). IEEE.
[28]Saddami, K., Munadi, K., Muchallil, S. and Arnia, F., 2017, November. Improved thresholding method for enhancing Jawi binarization performance. In 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR) (Vol. 1, pp. 1108-1113). IEEE.
[29]Michalak, H. and Okarma, K., 2018, April. Fast adaptive image binarization using the region based approach. In Computer Science On-line Conference (pp. 79-90). Springer, Cham.
[30]Michalak, H. and Okarma, K., 2018, May. Region based adaptive binarization for optical character recognition purposes. In 2018 International Interdisciplinary PhD Workshop (IIPhDW) (pp. 361-366). IEEE.
[31]Michalak, H. and Okarma, K., 2019. Improvement of image binarization methods using image preprocessing with local entropy filtering for alphanumerical character recognition purposes. entropy, 21(6), p.562.
[32]Mustafa, W.A., Yazid, H. and Jaafar, M., 2018. An improved sauvola approach on document images binarization. Journal of Telecommunication, Electronic and Computer Engineering (JTEC), 10(2), pp.43-50.
[33]Kurniawan, M.R., 2021. Segmentasi dan Perhitungan Luas Bercak Putih Citra Rontgen Paru Penderita Covid-19 dengan Metode Sauvola Thresholding (Doctoral dissertation, Universitas Jenderal Soedirman).
[34]Kiran, M., Ahmed, I., Khan, N. and Reddy, A.G., 2019. Chest X-ray segmentation using Sauvola thresholding and Gaussian derivatives responses. Journal of Ambient Intelligence and Humanized Computing, 10(10), pp.4179-4195.
[35]Mustafa, W.A., Abdul-Nasir, A.S. and Mohamed, Z.E.E.H.A.I.D.A., 2018. Malaria parasites segmentation based on Sauvola algorithm modification. Malaysian Appl. Biol., 47(2), pp.71-76.
[36]Panagiotakis, C. and Argyros, A.A., 2018, October. Cell segmentation via region-based ellipse fitting. In 2018 25th IEEE International Conference on Image Processing (ICIP) (pp. 2426-2430). IEEE.
[37]Misra, N.N., Phalak, R. and Martynenko, A., 2018. A microscopic computer vision algorithm for autonomous bubble detection in aerated complex liquids. Journal of food engineering, 238, pp.54-60.
[38]Jamaluddin, M.I., Mustafa, W.A., Idrus, S.Z.S., Jamlos, M.A. and Khairunizam, W., 2020, April. Thresholding Comparison Display Using Graphical User Interface (GUI) with Mobile Notification. In Journal of Physics: Conference Series (Vol. 1529, No. 4, p. 042022). IOP Publishing.
[39]https://favpng.com/png_search/tree/
[40]Huynh-Thu, Q. and Ghanbari, M., 2008. Scope of validity of PSNR in image/video quality assessment. Electronics letters, 44(13), pp.800-801.
[41]Hore, A. and Ziou, D., 2010, August. Image quality metrics: PSNR vs. SSIM. In 2010 20th international conference on pattern recognition (pp. 2366-2369). IEEE.
[42]Wang, S., Rehman, A., Wang, Z., Ma, S. and Gao, W., 2011. SSIM-motivated rate-distortion optimization for video coding. IEEE Transactions on Circuits and Systems for Video Technology, 22(4), pp.516-529.
[43]Moll, M.A., Baird, H.S. and An, C., 2008, September. Truthing for pixel-accurate segmentation. In 2008 The Eighth IAPR International Workshop on Document Analysis Systems (pp. 379-385). IEEE.
[44]Garnavi, R., Aldeen, M., Celebi, M.E., Varigos, G. and Finch, S., 2011. Border detection in dermoscopy images using hybrid thresholding on optimized color channels. Computerized Medical Imaging and Graphics, 35(2), pp.105-115.
[45]Garnavi, R., Aldeen, M., Celebi, M.E., Bhuiyan, A., Dolianitis, C. and Varigos, G., 2010. Automatic segmentation of dermoscopy images using histogram thresholding on optimal color channels. International Journal of Medicine and Medical Sciences, 1(2), pp.126-134.
[46]Christy, A. Joy, and A. Umamakeswari. "A Novel Percentage Split Distribution Method for Image Thresholding." Optik 218 (2020): 164953.