EUVIMEDEUVIMED entdecken
Crossref

Low-Power FPGA-Based Real-Time Image Processing Architecture for Skin Cancer Detection Using Deep Learning

Dr. Venkata Reddy Adama, Dr. G. Koteswar Rao, Dr. K Venugopal Rao

International Journal of Advanced Research in Science Communication and Technology · 16.06.2026 · 1126

DOI: 10.48175/ijarsct-36096 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Advanced Research in Science Communication and Technology, online erschienen am 16.06.2026. Verfasst von Dr. Venkata Reddy Adama und 2 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 10 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Skin cancer is one of the most serious dermatological diseases, and early detection plays an important role in improving treatment outcomes. Manual diagnosis of skin lesions mainly depends on dermatologist expertise and may be affected by visual similarity among different lesion types. In recent years, image processing and deep learning techniques have shown strong potential for automated skin lesion analysis. However, software-based deep learning models often require high computational resources, large memory, and increased power consumption, which limit their use in portable and real-time medical screening systems. This paper proposes a low-power FPGA-based real-time image processing architecture for skin cancer detection using deep learning. The proposed system includes image acquisition, preprocessing, lesion segmentation, feature enhancement, lightweight CNN-based classification, and FPGA-based hardware acceleration. Image preprocessing techniques such as resizing, contrast enhancement, noise filtering, and normalization are applied to improve image quality. Lesion segmentation separates the affected region from the surrounding normal skin, and a lightweight convolutional neural network classifies lesions into benign and malignant categories. The CNN model is optimized using quantization, fixed-point representation, pipelining, parallel processing, and memory reuse for efficient FPGA implementation. Result analysis shows that the proposed architecture provides improved processing speed, reduced latency, lower power consumption, and acceptable classification accuracy compared with conventional software-based processing. The proposed approach is suitable for real-time, low-cost, and portable skin cancer screening applications

Zitieren

APA

Adama, D. V. R., Rao, D. G. K., & Rao, D. K. V. (2026). Low-Power FPGA-Based Real-Time Image Processing Architecture for Skin Cancer Detection Using Deep Learning. International Journal of Advanced Research in Science Communication and Technology, 1126. https://doi.org/10.48175/ijarsct-36096

Vancouver

Adama DVR, Rao DGK, Rao DKV. Low-Power FPGA-Based Real-Time Image Processing Architecture for Skin Cancer Detection Using Deep Learning. International Journal of Advanced Research in Science Communication and Technology. 2026:1126. doi:10.48175/ijarsct-36096

BibTeX
@article{Adama2026,
  author = {Adama, Dr. Venkata Reddy and Rao, Dr. G. Koteswar and Rao, Dr. K Venugopal},
  title = {Low-Power FPGA-Based Real-Time Image Processing Architecture for Skin Cancer Detection Using Deep Learning},
  journal = {International Journal of Advanced Research in Science Communication and Technology},
  year = {2026},
  pages = {1126},
  doi = {10.48175/ijarsct-36096}
}
Kostenlos starten →