Skip to content
SDGs Center UDINUS

Evidence record · UDINUS · SDGs

Impact of Integrating Local Binary Patterns Feature Extraction Methodologies into a Convolutional Neural Network Framework for Detecting Pollutant Debris in Aquatic Environments

Rektorat UDINUS 2025 Published 2026-10-30

Evidence record · UDINUS · SDGs

Unit
Rektorat UDINUS
Period
2025
Goals
Record
23e1c7a4-c9ea-469b-8bd6-8d0513330f34
Published
2026-10-30

Universitas Dian Nuswantoro conducted a study examining the integration of Local Binary Patterns, or LBP, as a feature extraction technique within a Convolutional Neural Network, or CNN, framework for detecting pollutant debris in aquatic environments. The activity involved Indriani, Heny; Andono, Pulung Nurtantio; Santoso, Heru Agus; Affandy; and Kurdianto as researchers from Universitas Dian Nuswantoro.

The study addressed the prevalence of contaminant debris in aquatic ecosystems. The source identifies such debris as a significant risk to marine biodiversity and human health. It states that the identification and categorization of pollutants are essential for environmental surveillance and remediation strategies. Accordingly, the activity focused on detecting pollutant debris and distinguishing it from non-pollutant materials in images.

The examined method used LBP as a texture-oriented feature descriptor. The source describes LBP as computationally efficient and resilient in capturing localized patterns within images. LBP was embedded in the feature extraction process before the data were processed by a CNN classifier. The stated purpose of this integration was to augment the model's capacity to distinguish pollutant debris from non-pollutant materials. The source does not provide measured findings, comparative performance, or completed remediation outcomes.

Through this research activity, Universitas Dian Nuswantoro addressed pollutant debris detection in aquatic environments using an image-based LBP and CNN approach. The activity therefore presents an institutional research focus on environmental surveillance and the identification of materials associated with risks to aquatic ecosystems, marine biodiversity, and human health.

Reference https://www.scopus.com/pages/publications/105031577070?origin=resultslist