Metraipolis › archive › dc_ea2781fc2e8c

A Lightweight Convolutional Neural Network for Real-Time Recognition of Hand-Drawn Geometric Shapes — arXiv:2609.24384

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.24384
License (as archived)
CC0-1.0
Archived
2026-10-09T07:08:47.072Z
SHA-256 of the archived text
f95037fc9dc95dfa871e2909a384090422a5c4dfd2841a74ebac9df8aa8440e9
Stable URL of this page
https://metraipolis.com/documento/dc_ea2781fc2e8c

How to cite

A Lightweight Convolutional Neural Network for Real-Time Recognition of Hand-Drawn Geometric Shapes — arXiv:2609.24384 — arXiv (en), https://arxiv.org/abs/2609.24384 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ea2781fc2e8c (Metraipolis archive dc_ea2781fc2e8c, sha256 f95037fc9dc95dfa871e2909a384090422a5c4dfd2841a74ebac9df8aa8440e9)
BibTeX
@misc{dcea2781fc2e8c,
  title = {A Lightweight Convolutional Neural Network for Real-Time Recognition of Hand-Drawn Geometric Shapes — arXiv:2609.24384},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.24384},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ea2781fc2e8c; sha256 f95037fc9dc95dfa871e2909a384090422a5c4dfd2841a74ebac9df8aa8440e9},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.24384. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Recognizing hand-drawn geometric shapes is a foundational sub-problem of sketch recognition, with applications in education, human-computer interaction, and diagram digitization. This paper presents the design, implementation, and evaluation of a desktop application that recognizes four basic hand-drawn geometric shapes, circle, square, rectangle, and triangle using a compact Convolutional Neural Network (CNN). A dataset of 2,000 labeled 28x28-pixel shape images was collected independently and released publicly. The classifier consists of three convolutional blocks (16, 32, and 64 filters) with max-pooling, an in-model data-augmentation stage (random horizontal flip, rotation, and zoom), a dropout-regularized dense layer of 128 units, and a 4-way linear output layer, totaling 97{,}956 trainable parameters. The network is trained with the Adam optimizer on a sparse categorical cross-entropy objective computed directly on logits. On an 80/20 train-validation split, the model achieves 94.80% training accuracy and 96.01% validation accuracy with a validation loss of 0.1437. A Tkinter-based graphical interface allows a user to draw a shape with the mouse and receive an immediate class prediction with a confidence score. We situate this system within the broader sketch and shape-recognition literature, compare its accuracy against related hand-drawn shape classification studies, and discuss the limitations inherent to a small, single-contributor dataset. The complete source code, trained model, and per-class datasets are released publicly to support reproducibility.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-22 in cs.LG).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.24384 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-09T06:58:09.642Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).