502.175

Проведён комплексный сравнительный анализ распознавательных способностей всех 14 признаков Харалика. В ходе исследования была дана для каждого из 14 признаков полная характеристика по 14 ключевым параметрам и одинаковым для всех признаков (зависимость от поворота и ротационная инвариантность). Каждый из признаков Харалика был охарактеризован с примерами успешного использования в задачах дистанционного зондирования (обнаружение лесных пожаров, мониторинг морских аномалий, классификация растительности, сегментация радиолокационных изображений и т.д.). Полученные результаты позволят исследователям осознанно выбирать наиболее подходящие текстурные признаки, опираясь на детально обоснованные свойства каждого из них.

A comprehensive comparative analysis of the discriminative capabilities of all 14 Haralik features was carried out. For each of the 14 features, a complete characterization was based on 14 key parameters that were the same for all the features (dependence on rotation and rotational invariance). Each Haralick feature was characterized with the examples of successful use in remote sensing tasks (forest fire detection, monitoring of marine anomalies, vegetation classification, radar image segmentation, etc.). The obtained results will let researchers make informed choices of the most appropriate texture features, based on the thoroughly justified properties of each.

аспирант, преподаватель кафедры космического мониторинга и экологии, Московский государственный университет геодезии и картографии

Haralick R.M., Shanmugam K., Denstien I. «Textural features for image classification». IEEE Trans Syst Man Cybern. Vol. 3. No. 6. Pp. 610-621. 1973.

Mhangara P., Odindi J. (2013). Potential of texture-based classification in urban landscapes using multispectral aerial photos. South African Journal of Science. 109. 8. 10.1590/sajs.2013/1273.

Fedorovskyi O.D., Khyzhniak A.V., Filimonov V.Yu. Justification of the dual-use of aerospace geomonitoring of the offshore shelf: Exploration of hydrocarbon deposits and «highlighting» the marine situation. Space Sci. & Technol. 2021. 27;(2):38-44.

Лоссов К.К., Малинников В.А. Верификация методики обнаружения явления апвеллинга на морской поверхности по материалам космических съемок с использованием признаков Харалика // Мониторинг. Наука и технологии. 2026. №1 (67).

Лоссов К.К., Малинников В.А. Разработка методики использования признаков Харалика для детектирования зон апвеллинга на морской поверхности по материалам космических съемок // Мониторинг. Наука и технологии. 2025. №4 (66).

Chehade N., Boureau J.-G.,Vidal C., Zerubia J. (2009). Multi-class SVM for forestry classification. 1673-1676.

J.J. J., Kumar T., Koliwad S. (2012). Comparative Analysis of Image Fusion Techniques in Remote Sensing. Communications in Computer and Information Science. 322. 111-117.

Umaselvi M., Kumar S. & Athithya M. (2012). Color Based Urban and Agricultural Land Classification by GLCM Texture Features. IET Chennai 3rd International on Sustainable Energy and Intelligent Systems (SEISCON 2012). Tiruchengode. 2012. Pp. 1-4.

Rees W.G., Lin I.-I. Texture-based classification of cloud and ice-cap surface features. Annals of Glaciology. No. 17. Pp. 250-254. 1993.

Adhikari A., Garg R.D., Pundir S.K., Singhal A. Delineation of agricultural fields in arid regions from Worldview-2 datasets based on image textural properties. Environ Monit Assess. 2023 Apr 24;195(5):605.

Parikesit S.O., Muhamad D., Harashina K., Takeuchi K., & Umezaki M. (2010). Land use/cover classification of a complex agricultural landscape using single-dated very high spatial resolution satellite-sensed imagery. Canadian Journal of Remote Sensing, 36(6). 722-736.

Lofstedt T., Brynolfsson P., Asklund T., Nyholm T., Garpebring A. (2019). Gray-level invariant Haralick texture features. PLOS ONE. 14.

Oprisan S.A., Oprisan A. Scaling laws for Haralick texture features of linear gradients. PeerJ Comput Sci. 2025 Apr 30;11:e2856.

Oprisan A, Oprisan SA. Scaling of Haralick features with image bit depth and gray level co-occurrence matrix displacement vector for linear gradients. Comput Biol Med. 2025 Sep;196(Pt C):110880.

Saladin A.M., Jiao L., Zhang X. «GPU-accelerated computation for texture features using OpenCL framework». 2014 11th International Conference on Electrical Engineering/Electronics. Computer, Telecommunications and Information Technology (ECTI-CON). Nakhon Ratchasima. Thailand. 2014. Pp. 1-6.

Hong H., Zheng L., Pan S. (2018). Computation of Gray Level Co-occurrence Matrix Based on CUDA and Optimization for Medical Computer Vision Application. IEEE Access.

Hall-Beyer M. (2017). Practical guidelines for choosing GLCM textures to use in landscape classification tasks over a range of moderate spatial scales. International Journal of Remote Sensing. 38(5). 1312-1338.

Wang H., Zhao Y., Pu R., Zhang Z. Mapping Robinia Pseudoacacia Forest Health Conditions by Using Combined Spectral, Spatial, and Textural Information Extracted from IKONOS Imagery and Random Forest Classifier. Remote Sensing. 2015. Vol. 7. No. 7. Pp. 9020-9044.

Дмитриев Е.В., Зотов С.А., Мельник П.Г. Определение состава смешанных древостоев на основе спектрально-текстурной классификации спутниковых изображений высокого разрешения // Resour. Technol. 2020. №4.

Родионова Н.В. (2014). Текстурная RGB - сегментация одноканальных TerraSAR-X изображений // Современные проблемы дистанционного зондирования Земли из космоса. 11(1). C. 301-307.

Rodionova N.V. (2016). Evaluation of Sentinel 1 imagery for burned area detection in southern Siberia in spring and summer 2015. Current problems in remote sensing of the Earth from space.

Nguemhe Fils S.C., Bekele Mongo C.H., Nkouathio D.G., Mimba M.E., Etouna J., Nouck P.N., Nyeck B. Radarsat-1 image processing for regional-scale geological mapping with mining vocation under dense vegetation and equatorial climate environment, Southwestern Cameroon. The Egyptian Journal of Remote Sensing and Space Science. Volume 21. Supplement 1. 2018. Pages S43-S54.

Зотов С.А., Дмитриев Е.В., Мельник П.Г., Кондранин Т.В. Повышение информативности мультиспектральных спутниковых изображений с использованием данных текстурного анализа // Известия ВУЗов. Лесной журнал. 2022. №2.

Balling J., Herold M., Reiche J. How textural features can improve SAR-based tropical forest disturbance mapping. International Journal of Applied Earth Observation and Geoinformation. Volume 124. 2023.

Fedorovskyi O., Sedlerova O., Khyzhniak A. (2023). Improvement of the Information Technology Basis for Aerospace Monitoring of the Sea Shelf for the Search for Hydrocarbon Deposits in the Optical Spectral Range. In: Urbach H.P., Jiang H. (eds) Proceedings of the 7th International Symposium of Space Optical Instruments and Applications. ISSOIA 2022. Springer Proceedings in Physics. Vol 295. Springer. Singapore.

Zhou J., Guo R., Sun M., Di T., Wang S., Zhai J., Zhao Z. (2017). The Effects of GLCM parameters on LAI estimation using texture values from Quickbird Satellite Imagery. Scientific Reports.

Donnini J. Remote Sensing of Forest Composition and Diversity: Assessing Spectral Predictors and Long-Term Changes in Quebecs Forests: Masters thesis. J. Donnini; Concordia University. Montreal. 2025.

Boland Michael V., Quantitative Description and Automated Classification of Cellular Protein Localization Patterns in Fluorescence Microscope Images of Mammalian Cells : A Dissertation Submitted to the Graduate School in Partial Fulfillment of the Requirements for the Degree of Doctor of Philosophy in Bioengineering Boland Michael V.: defended on 07.1999; Pittsburgh. PA. USA. Pittsburgh. 1999.

Cavalcanti G.G.B. de O. et al. Comparing the Use of Sum and Difference Histograms and Gray Levels Occurrence Matrix for Texture Descriptors. 2018 International Joint Conference on Neural Networks (IJCNN). Rio de Janeiro. Brazil: IEEE. 2018. Pp. 1-8.

Brynolfsson P., Nilsson D., Torheim T., et al. Haralick texture features from apparent diffusion coefficient (ADC) MRI images depend on imaging and pre-processing parameters. Scientific Reports. 2017. Vol. 7. article id 4041.

Plate A., et al. Towards guidelines to harmonize textural features in PET: Haralick textural features vary with image noise, but exposure-invariant domains enable comparable PET radiomics. PLOS ONE. 2020.

Webel J., Gola J., Britz D., Mucklich F., A new analysis approach based on Haralick texture features for the characterization of microstructure on the example of low-alloy steels. Materials Characterization. Volume 144. 2018. Pages 584-596, ISSN 1044-5803.

Oprisan A., Oprisan SA. (2023) Bounds for Haralick features in synthetic images with sinusoidal gradients. Front. Sig. Proc. 3:1271769.

Zubair A.R.A. Grey Level Co-occurrence Matrix (GLCM) Based Second Order Statistics for Image Texture Analysis. A.R.A. Zubair O.A. Alo. October 2019.