Plant leaf vein and outline feature extraction using fractal and computer vision approaches DOI Creative Commons
Nadia Tabassum

Lahore Garrison University Research Journal of Computer Science and Information Technology, Journal Year: 2024, Volume and Issue: 8(1)

Published: March 25, 2024

The study focuses on utilizing plant leaf characteristics for identification and disease detection. Leaves are pivotal gathering information about plants. Leveraging computer vision smart agricultural technologies, the proposed model discerns venation texture features in various leaves. This research utilized a modified dataset derived from Flavia image dataset, comprising images of 32 different species. was divided into two subsets (one with 1907 another 1000 images) to differentiate between tuned untuned processing. Techniques such as GLCM, LBP, Gabor filters, Fractal Dimension, box counting were employed extract features, including patterns. conducted four experiments training testing splits 70/30 80/20. A novel method combining SVM fractal dimension analysis benchmarked against six classifiers (Random Forest, KNN, DNN, Naïve Bayes, Decision Tree, SVM), achieving an impressive accuracy 88% Dimension 1.8709. holds significant potential advancing digital modern agriculture, particularly early detection diseases accurate identification.

Language: Английский

Assessment of forest fragmentation and ecological dynamics in Western Himalayan Region over three decades (1990–2020) DOI
Adeel Ahmad, Sajid Rashid Ahmad, Hammad Gilani

et al.

Environmental Monitoring and Assessment, Journal Year: 2025, Volume and Issue: 197(2)

Published: Jan. 30, 2025

Language: Английский

Citations

0
Evaluation of Conservation Efficiency: Metrics for the Management of Permanent Preservation Areas and Legal Reserves in Brazil DOI Open Access

Iracema Alves Manoel Degaspari,

Dionne Cavalcante Monteiro,

Dorleta García

et al.

Sustainability, Journal Year: 2025, Volume and Issue: 17(5), P. 1819 - 1819

Published: Feb. 21, 2025

The Brazilian Forest Code regulates Permanent Preservation Areas (PPA) and Legal Reserves (LR) across all federative states. These areas support the maintenance of ecological functions are essential for biodiversity conservation environmental balance. However, implementing these initiatives faces significant challenges, particularly in supporting expansion agribusiness. Effective management is economic development while also preserving natural habitats. Our study relies on data from Rural Environmental Registry (RER), managed by Federal Government, to assess PPA LR São Paulo. We apply geometric metrics Circularity Index, Edge Factor, Fractal Dimension, Compactness Index evaluate protected areas’ shape physical characteristics, individually as groups. results underscore relationship between morphology their functions, including susceptibility edge effects habitat degradation. Moreover, large-scale analysis correlating several revealed complexity landscapes, characterized differing degrees connectivity, vulnerability, efficiency, assessing 645 districts. In conclusion, provide a framework that ecosystem conservation, enhancing agricultural productivity.

Language: Английский

Citations

0
Fractal Measures as Predictors of Histopathological Complexity in Breast Carcinoma Mammograms DOI Creative Commons
Abhijeet Das, Ramray Bhat, Mohit Kumar Jolly

et al.

bioRxiv (Cold Spring Harbor Laboratory), Journal Year: 2025, Volume and Issue: unknown

Published: April 16, 2025

Abstract Breast carcinoma remains the most commonly diagnosed malignancy and a leading cause of cancer-related mortality among women worldwide. While mammography is gold standard for early detection, challenges such as high breast density often obscure malignancies, reducing diagnostic sensitivity. Conventional parenchymal texture analysis methods have limitations due to struggles with spatial interpretation noise This study investigates efficacy fractal-based global features distinguishing between malignant normal mammograms assessing their potential molecular subtype differentiation. Digital were analyzed using standardized preprocessing techniques, fractal measures computed capture complexity connectivity properties within tissue structures. Fractal dimension, multifractality strength, succolarity reservoir found effectively characterize specific mammographic texture; however, incorporation into machine learning models yielded moderate discriminatory performance categories. We introduced novel parameter accounting tissues’ latent connectivity. In addition, while exhibits differentiating Luminal B from other subtypes, its overall discriminative power limited. proof-of-concept underscores non-invasive biomarker in diagnosis.

Language: Английский

Citations

0
Fractal Metrics and Connectivity Analysis for Forest and Deforestation Fragmentation Dynamics DOI Open Access
Isiaka Lukman Alage, Yumin Tan,

Ahmed Wasiu Akande

et al.

Forests, Journal Year: 2025, Volume and Issue: 16(2), P. 314 - 314

Published: Feb. 11, 2025

Forests are critical ecosystems that regulate climate, preserve biodiversity, and support human livelihoods by providing essential resources. However, they increasingly vulnerable due to the growing impacts of deforestation habitat fragmentation, which endanger their value long-term sustainability. Assessing forest fragmentation is vital for promoting sustainable logging, guiding ecosystem restoration, biodiversity conservation. This study introduces an advanced approach integrates Local Connected Fractal Dimension (LCFD) with near real-time (NRT) land use cover (LULC) data from Dynamic World dataset (2017–2024) enhance monitoring landscape analysis. By leveraging high-frequency, high-resolution satellite imagery imaging techniques, this method employs two fractal indices, namely Fragmentation Index (FFI) Disorder (FFDI), analyze spatiotemporal changes in monitoring, a dynamic, quantitative assessing connectivity real time. LCFD provides refined assessment spatial complexity, localized connectivity, self-similarity fragmented landscapes, improving understanding dynamics. Applied Nigeria’s Okomu Forest, analysis revealed significant transformations, peak observed 2018 substantial recovery 2019. FFI FFDI metrics indicated heightened disturbances 2018, increasing 75.2% non-deforested areas 61.1% deforested before experiencing rapid declines 2019 (82.6% 87%, respectively), suggesting improved connectivity. Despite minor fluctuations, cumulative trends showed 160.5% rise 2017 2024, reflecting stabilization. patterns highlighted persistent variability, recovering 12% 2024 after 38% reduction These findings reveal complex interplay between recovery, emphasizing need targeted conservation strategies ecological resilience indices offer potential generate valuable insights across multiple scales, thereby informing preservation adaptive management.

Language: Английский

Citations

0
Evaluation of forest loss data using fractal algorithms: case study Eastern Carpathians–Romania DOI Creative Commons
Daniel Constantin Diaconu, Ion Andronache, Andrei Rafael Gruia

et al.

Frontiers in Forests and Global Change, Journal Year: 2024, Volume and Issue: 7

Published: July 1, 2024

Logging causes the fragmentation of areas with direct implications for hydrological processes, landslides, or habitats. The assessment this process plays an important role in planning future logging, reconstruction, and protection measures whole ecosystem. methodology used includes imaging techniques applying two fractal indices: Fractal Fragmentation Index (FFI) Disorder (FFDI). results showed annual evolution disposition deforested areas. Only 3% deforestation resulted splitting forest plots. remaining 97% reduction existing compact stands without fragmentation. method has many advantages quantifying spatial forests, estimating capture carbon emissions establishing sustainability bird animal analysis took place Eastern Carpathians, Romania, time period 2001–2022.

Language: Английский

Citations

1
Plant leaf vein and outline feature extraction using fractal and computer vision approaches DOI Creative Commons
Nadia Tabassum

Lahore Garrison University Research Journal of Computer Science and Information Technology, Journal Year: 2024, Volume and Issue: 8(1)

Published: March 25, 2024

The study focuses on utilizing plant leaf characteristics for identification and disease detection. Leaves are pivotal gathering information about plants. Leveraging computer vision smart agricultural technologies, the proposed model discerns venation texture features in various leaves. This research utilized a modified dataset derived from Flavia image dataset, comprising images of 32 different species. was divided into two subsets (one with 1907 another 1000 images) to differentiate between tuned untuned processing. Techniques such as GLCM, LBP, Gabor filters, Fractal Dimension, box counting were employed extract features, including patterns. conducted four experiments training testing splits 70/30 80/20. A novel method combining SVM fractal dimension analysis benchmarked against six classifiers (Random Forest, KNN, DNN, Naïve Bayes, Decision Tree, SVM), achieving an impressive accuracy 88% Dimension 1.8709. holds significant potential advancing digital modern agriculture, particularly early detection diseases accurate identification.

Language: Английский

Citations

0