EUVIMEDEUVIMED entdecken
Crossref

Modified LeNet Architecture Trained on Pattern and Texton Features for Video Surveillance

Kancharla Shilpa, Battula KrishnaPrasad, Vamsidhar Talasila

New Mathematics and Natural Computation · 07.07.2026 · 1-26

DOI: 10.1142/s1793005728500676 ↗

Kurz gefasst

Fachartikel in der Zeitschrift New Mathematics and Natural Computation, online erschienen am 07.07.2026. Verfasst von Kancharla Shilpa und 2 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In Computer Vision (CV), object detection is a basic visual recognition issue that has been extensively researched in recent decades, especially in security surveillance. In recent years, there have been several studies on DL-based object recognition algorithms due to their enormous success in image classification. Accordingly, a new WMDSCBN-MLNet model is proposed in this work for object detection in Video Surveillance (VS). Initially, input videos are decomposed into individual frames, which are pre-processed using a Wiener filter to enhance quality. Next, the Modified Correlation-based Improved BIRCH (MC-IBIRCH) algorithm is employed for frame segmentation. Feature extraction is then carried out using a combination of Weight Parameter-based Local Gabor Increasing Pattern (WP-LGIP), Median Binary Pattern (MBP), and Multi-Texon features. The aggregated features are fed into the detection module. Finally, object detection is done using weighted MDSC-Batch normalization-based Modified LeNet (WMDSCBN-MLNet). From the study, it is observed that the proposed WMDSCBN-MLNet reached a better specificity of 0.975%, which is higher than prevailing methods.

Zitieren

APA

Shilpa, K., KrishnaPrasad, B., & Talasila, V. (2026). Modified LeNet Architecture Trained on Pattern and Texton Features for Video Surveillance. New Mathematics and Natural Computation, 1-26. https://doi.org/10.1142/s1793005728500676

Vancouver

Shilpa K, KrishnaPrasad B, Talasila V. Modified LeNet Architecture Trained on Pattern and Texton Features for Video Surveillance. New Mathematics and Natural Computation. 2026:1-26. doi:10.1142/s1793005728500676

BibTeX
@article{Shilpa2026,
  author = {Shilpa, Kancharla and KrishnaPrasad, Battula and Talasila, Vamsidhar},
  title = {Modified LeNet Architecture Trained on Pattern and Texton Features for Video Surveillance},
  journal = {New Mathematics and Natural Computation},
  year = {2026},
  pages = {1--26},
  doi = {10.1142/s1793005728500676}
}
Kostenlos starten →