Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{190106,
        author = {SNEHAL DILEEP GURUPHALE and ATHIRA PRADEEP K and MATHIVANAN K and NITHYA R},
        title = {Skin Disease Detection using Convolutional Neural Network: A Hybrid Approach Combining Image Preprocessing and Feature Extraction Techniques},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {8},
        pages = {1963-1972},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=190106},
        abstract = {A persistent inflammatory skin condition called psoriasis results in red, white, and scaly areas of skin. The Psoriasis Area and Severity Index (PASI), which is calculated, is often used to determine the severity of psoriasis. The severity of the erythema parameter is classified subjectively by doctors into many levels. The ability to diagnose and categorise psoriasis using simply clinical evaluation is, however, constrained. Convolutional neural networks (CNN) powered by deep learning have recently made advancements that have increased the accuracy of illness categorization. Therefore, the goal of this work is to classify and identify the erythema of psoriasis lesions using CNN architectures, especially CNN and ResNet 50. These two skin illnesses are eczema and psoriasis. A 10-fold cross-validation was performed to examine the performance of five distinct cutting-edge CNN architectures. The analysis reveals that the Kirsch's template and Inception ResNet 50 architecture combined for a maximum validation accuracy of 98.4%. The suggested approach may be used to quantitatively evaluate the erythema of a psoriasis lesion, and the performance matrices indicate that it performs very well in terms of diagnosing skin conditions. With limited restrictions on the acquisition technique, the proposed strategy has the potential to be an affordable, quick, reliable, and simple method in a dermatological setting.},
        keywords = {Psoriasis Disease, Resnet-50, Kirsch’s Template, Image Processing Techniques},
        month = {January},
        }