Time and Accuracy Analysis of Skew Detection Methods for Document Images
Bibliographic record
Abstract
Detecting skew angle in a document image has been an area of research interest for a long time. This paper presents an experimental analysis of various existing skew detection techniques involving methods such as Radon transform, Hough transform, Principal Component Analysis (PCA), PCA with Wavelet transform and Moments with Wavelet transform. Detailed analysis of existing skew detection method against the parameters time complexity, space complexity, robustness, accuracy, flexibility, etc. has been carried out for seven different categories of digital documents. The categories of these documents spans from those containing handwritten text in different languages, to the ones with both text and pictures. Radon transform is observed to be the fastest method when the image size is small and works with virtually all types of documents. It is an accurate method as well as works faster, even with the document containing pictures. PCA method is also faster than Hough transform for machine printed documents but used less for real time skew distortion due to its limitations. If the document image size is large, then Moments with Wavelet transform has better time complexity than other methods, but do not work well with documents containing images. Hough transform is the most accurate method, though it is computationally expensive.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.013 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".