- Published
- 2024-01-01
- Cited by
- 4,148
- Open access
- Yes, green
- DOI
- 10.57702/e7wwo0zk
Abstract
Detecting and reading text from natural images is a hard computer vision task that is central to a variety of emerging applications. Related problems like document character recognition have been widely studied by computer vision and machine learning researchers and are virtually solved for practical applications like reading handwritten digits. Reliably recognizing characters in more complex scenes like photographs, however, is far more difficult: the best existing methods lag well behind human performance on the same tasks. In this paper we attack the problem of recognizing digits in a real application using unsupervised feature learning methods: reading house numbers from street level photos. To this end, we introduce a new benchmark dataset for research use containing over 600,000 labeled digits cropped from Street View images. We then demonstrate the difficulty of recognizing these digits when the problem is approached with hand-designed features. Finally, we employ variants of two recently proposed unsupervised feature learning methods and find that they are convincingly superior on our benchmarks. 1
Cite this paper
Formatted from the source metadata, not typed by hand. For a whole reference list, use the citation generator or ask your assistant through Find Research.
- APA 7
Netzer, Y. (2024). Reading digits in natural images with unsupervised feature learning. https://doi.org/10.57702/e7wwo0zk
- MLA 9
Netzer, Yuval. "Reading digits in natural images with unsupervised feature learning." 2024, https://doi.org/10.57702/e7wwo0zk.
- Chicago
Netzer, Yuval. "Reading digits in natural images with unsupervised feature learning." (2024). https://doi.org/10.57702/e7wwo0zk.
- GOST
Netzer Y. Reading digits in natural images with unsupervised feature learning — 2024. — URL: https://doi.org/10.57702/e7wwo0zk
- BibTeX
@misc{netzer2024reading, title = {{Reading digits in natural images with unsupervised feature learning}}, author = {Yuval Netzer}, year = {2024}, doi = {10.57702/e7wwo0zk}, url = {https://doi.org/10.57702/e7wwo0zk} }- RIS
TY - JOUR AU - Netzer, Yuval TI - Reading digits in natural images with unsupervised feature learning PY - 2024 DA - 2024/01/01 DO - 10.57702/e7wwo0zk UR - https://doi.org/10.57702/e7wwo0zk ER -
Ask Claude about this paper
Add Find Research to Claude or ChatGPT and ask in plain language. The assistant reads this record, finds the papers around it and cites only what it actually found:
- “Summarize doi:10.57702/e7wwo0zk and list its main limitations.”
- “Find newer studies that test the same question, with free PDFs.”
- “Cite this and five related papers in APA for my literature review.”
Setup takes about a minute: add the connector, then start the free trial.
Record from OpenAlex; open-access location from Unpaywall and the indexes. Find Research links only to legal copies.