TY - GEN
T1 - Machine Learning Techniques for the Detection of Melasma Disease
T2 - 1st International Conference on Computational Intelligence and Soft Computing, CISCom 2025
AU - Shetty, Mrunal
AU - Prabhu, Srikanth
AU - Bhandage, Venkatesh
AU - Chadaga, Krishnaraj
AU - Prabhu, Smitha
AU - Jalla, Varshith
N1 - Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2026.
PY - 2026
Y1 - 2026
N2 - Technology-driven systems for dermatological assessment constitute a crucial field of research. In this research article we are applying artificial intelligence mainly to detect whether the person is having Melasma or not along with the comparative analysis of other diseases. If we detect whether the person is having a high risk of melasma then we will be using machines to learn to diagnose the risk of Melasma using the following factors deeper complexion shade, hormonal responsiveness to estrogen and progesterone, implying contraceptive medication, gestation, and endocrine treatments may initiate hyperpigmentation tension, thyroid gland disorder, Repeated contact with ultraviolet radiation. This approach utilizes machine learning algorithms to diagnose Melasma along with the other kind of diseases. The research primarily explores the application of artificial intelligence and neural network techniques. This review emphasizes the key challenges associated with dermatological image analysis and categorization techniques when working with limited datasets. Also, we are focusing mainly on comparison of accuracy of various algorithms.
AB - Technology-driven systems for dermatological assessment constitute a crucial field of research. In this research article we are applying artificial intelligence mainly to detect whether the person is having Melasma or not along with the comparative analysis of other diseases. If we detect whether the person is having a high risk of melasma then we will be using machines to learn to diagnose the risk of Melasma using the following factors deeper complexion shade, hormonal responsiveness to estrogen and progesterone, implying contraceptive medication, gestation, and endocrine treatments may initiate hyperpigmentation tension, thyroid gland disorder, Repeated contact with ultraviolet radiation. This approach utilizes machine learning algorithms to diagnose Melasma along with the other kind of diseases. The research primarily explores the application of artificial intelligence and neural network techniques. This review emphasizes the key challenges associated with dermatological image analysis and categorization techniques when working with limited datasets. Also, we are focusing mainly on comparison of accuracy of various algorithms.
UR - https://www.scopus.com/pages/publications/105040664456
UR - https://www.scopus.com/pages/publications/105040664456#tab=citedBy
U2 - 10.1007/978-981-95-7289-2_9
DO - 10.1007/978-981-95-7289-2_9
M3 - Conference contribution
AN - SCOPUS:105040664456
SN - 9789819572885
T3 - Communications in Computer and Information Science
SP - 98
EP - 112
BT - Computational Intelligence and Soft Computing - 1st International Conference, CISCom 2025, Proceedings
A2 - Pathan, Sameena
A2 - Pokhrel, Shiva Raj
A2 - Li, Gang
A2 - Barata, Catarina
PB - Springer Science and Business Media Deutschland GmbH
Y2 - 26 November 2025 through 27 November 2025
ER -