How nexarobs/image-to-keyword-prediction works
This is an image-to-description coursework project: it preprocesses PASCAL VOC images and XML labels, trains five multi-label classifiers, compares their results, and aims to generate a template caption. The README documents these stages, but no source excerpts are available, so the graph reflects documented workflow only; notebook-level implementation details and exact runtime calls cannot be verified.
Main entry points: project-imageandxmlpreprocessing.ipynb Feature-label CSV · models Model comparison · XGBoost-Model.ipynb XGBoost · projet-iti-knn-model.ipynb KNN
Components 14
Data preprocessing
- Image preparation
notebooks/preprocessing/project-imageandxmlpreprocessing.ipynb - SIFT features
notebooks/preprocessing/project-imageandxmlpreprocessing.ipynb - BoW and PCA
notebooks/preprocessing/project-imageandxmlpreprocessing.ipynb - XML label preparation
notebooks/preprocessing/project-imageandxmlpreprocessing.ipynb - Feature-label CSV
notebooks/preprocessing/project-imageandxmlpreprocessing.ipynb
Model training
- XGBoost
notebooks/models/XGBoost-Model.ipynb - KNN
notebooks/models/projet-iti-knn-model.ipynb - Perceptron
notebooks/models/percpetron (2).ipynb - SVM
notebooks/models/svm.ipynb - Decision trees
notebooks/models/DecisionTrees.ipynb
Evaluation and captions
- Model comparison
notebooks/models - Template caption
notebooks
Other components
- Project user
- PASCAL VOC 07/12
Connections 19
- Project user → PASCAL VOC 07/12: selects dataset
README.md - PASCAL VOC 07/12 → Image preparation: provides images
README.md - PASCAL VOC 07/12 → XML label preparation: provides XML labels
README.md - Image preparation → SIFT features: prepares images
README.md - SIFT features → BoW and PCA: extracts descriptors
README.md - BoW and PCA → Feature-label CSV: contributes features
README.md - XML label preparation → Feature-label CSV: joins labels
README.md - Feature-label CSV → XGBoost: trains on data
README.md - Feature-label CSV → KNN: trains on data
README.md - Feature-label CSV → Perceptron: trains on data
README.md - Feature-label CSV → SVM: trains on data
README.md - Feature-label CSV → Decision trees: trains on data
README.md - XGBoost → Model comparison: compares results
README.md - KNN → Model comparison: compares results
README.md - Perceptron → Model comparison: compares results
README.md - SVM → Model comparison: compares results
README.md - Decision trees → Model comparison: compares results
README.md - Model comparison → Template caption: followed by captioning
README.md - Template caption → Project user: describes image
README.md