0552810 20250123085701.020220204235959.9 85182934075 000777569400080 10.5220/0000156800003124 8 s. P cav_un_epca*0552809978-989-758-555-52184-4321722-729SetúbalScitepress - Science and Technology Publications, Lda2022FarinellaG.M.RadevaP.BouatouchK. Skin Cancer Recognition Melanoma Detection Circular Markov Random Field Model cav_un_auth*0101093 Haindl Michal UTIA-B Rozpoznávání obrazu Department of Pattern Recognition RO RO Department of Pattern Recognition A Ústav teorie informace a automatizace AV ČR, v. v. i. cav_un_auth*0101239 Žid Pavel UTIA-B Rozpoznávání obrazu Department of Pattern Recognition RO RO Department of Pattern Recognition Ústav teorie informace a automatizace AV ČR, v. v. i. http://library.utia.cas.cz/separaty/2022/RO/haindl-0552810.pdf GA19-12340S GA ČR CZ cav_un_auth*0376011 Early and reliable melanoma detection is one of today's significant challenges for dermatologists to allow successful cancer treatment. This paper introduces multispectral rotationally invariant textural features of the Markovian type applied to effective skin cancerous lesions classification. Presented texture features are inferred from the descriptive multispectral circular wide-sense Markov model. Unlike the alternative texture-based recognition methods, mainly using different discriminative textural descriptions, our textural representation is fully descriptive multispectral and rotationally invariant. The presented method achieves high accuracy for skin lesion categorization. We tested our classifier on the open-source dermoscopic ISIC database, containing 23 901 benign or malignant lesions images, where the classifier outperformed several deep neural network alternatives while using smaller training data. cav_un_auth*0423777 International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) /17./ 20220206 20220208 Setúbal - online PT BD 20000 20200 20205 2022 2 4 A sml 4as 20231122150333.5 PR RVO:67985556 http://hdl.handle.net/11104/0327904 S Consent to publish and coypright transfer 20211227 268 8 3.17 2022 Soubory v repozitáři: haindl-0552810-22VISAPP_copyright.pdf 85182934075 SCOPUS PUBMED 000777569400080 WOS cav_un_epca*0552809 Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications Scitepress - Science and Technology Publications, Lda 2022 Setúbal 722 729 978-989-758-555-5 2184-4321 Farinella G.M. 340 Radeva P. 340 Bouatouch K. 340