Sketch Classification with Convolutional Neural Networks¶
A deep learning approach to classifying hand-drawn sketches across 250 object categories, achieving 58.7% top-k accuracy on the TU-Berlin dataset using a custom CNN architecture.
Abstract¶
We present a deep learning model to recognize hand-drawn sketches. This is an image recognition task and part of multi-class classification using deep learning. We show an overall 58.7% top-k categorical accuracy and that the dataset is well suited for image classification using deep learning. Furthermore, we show that tuning the model parameters -- i.e., layers, filter size, and preprocessing -- significantly impacts the results.
Key Contributions¶
- Designed a 14-layer CNN architecture (8.6M parameters) for 250-class sketch classification on the TU-Berlin dataset of 20,000 hand-drawn greyscale images
- Demonstrated that top-k categorical accuracy is the appropriate metric for hand-drawn sketch classification, where visual ambiguity across classes is inherent
- Showed that image scaling (128x128), normalization, and grayscale preprocessing significantly impact model convergence and accuracy
- Achieved 58.7% top-k test accuracy in just 5 training epochs, outperforming earlier SVM-based approaches (56%) on the same dataset
- Explored the effects of hyperparameter tuning using AutoKeras and KerasTuner, settling on a sequential model with progressively deeper convolutional blocks
Links¶
- PDF: to be hosted
- arXiv / TechRxiv: to be added