Deep-CNN-and-geometric-features-based-gastrointestinal-tract

Deep CNN and geometric features-based gastrointestinal tract diseases detection and classification from wireless capsule endoscopy images
49 descargas
Actualizado 11 Jun 2022

Deep-CNN-and-geometric-features-based-gastrointestinal-tract-diseases-detection-and-classification-f

Deep CNN and geometric features-based gastrointestinal tract diseases detection and classification from wireless capsule endoscopy images Muhammad Sharif, Muhammad Attique Khan, Muhammad Rashid, Mussarat Yasmin, Farhat Afza, Urcun John Tanik (Journal of Experimental & Theoretical Artificial Intelligence: IF 2.11 | 02-02-2019)

image
Figure 1: Sample collected WCE images

Proposed Model

image
Proposed Model

Contrast Elongating

image
Sample Image

image
Contrast Elongated Images

Lesion Detection

image

image
Figure 5: Proposed probability based color features clustering effects

image


Figure 6: Results after morphological operations

Deep CNN Features Extraction

image


Figure 7: Utilized architecture of VGG16 for deep CNN features extraction

image
Figure 8: Employed architecture of VGG19 for features extraction

image


Figure 9: Proposed features fusion and selection approach

image

image

Results and Discussion

image

image

image

image

image

image

Citar como

Muhammad Rashid (2024). Deep-CNN-and-geometric-features-based-gastrointestinal-tract (https://github.com/rashidrao-pk/Deep-CNN-and-geometric-features-based-gastrointestinal-tract-diseases-detection-and-classification-f), GitHub. Recuperado .

Compatibilidad con la versión de MATLAB
Se creó con R2020a
Compatible con cualquier versión
Compatibilidad con las plataformas
Windows macOS Linux

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

No se pueden descargar versiones que utilicen la rama predeterminada de GitHub

Versión Publicado Notas de la versión
1.0.0

Para consultar o notificar algún problema sobre este complemento de GitHub, visite el repositorio de GitHub.
Para consultar o notificar algún problema sobre este complemento de GitHub, visite el repositorio de GitHub.