Image-Based Retrieval of Concrete Crack Properties
Bibliographic record
Abstract
Purpose This paper presents a new method to retrieve concrete crack properties based on image processing techniques.Method Detection and quantification of cracks in concrete bridges pose various challenges.Cracks have fewer pixels compared to their background.For effective visualization, the objects need to be captured from near field.But it is not always possible to capture the complete cracked surface in a single frame while taking the image from near field.Hence image stitching is required before pre-processing of images for further analysis.Usually retrieved images have low contrast due to environmental and equipment limitations which add another difficulty in image visualization.State-ofthe-art image pre-processing as suggested in the literature may not be suitable for images captured in different environmental conditions.This paper discusses various techniques for image enhancement using point processing, histogram equalization and mask processing.Furthermore, a binary image is required to obtain a skeleton of an object.However, the pre-processing techniques cause discontinuity in crack alignment.Morphological techniques (e.g.dilation) are used in this work through successive iteration to ensure connectivity.Then the object skeleton which is unaffected by expanded boundaries is obtained by using skeleton algorithm to retrieve concrete crack properties such as length, bounding rectangle, and major and minor principal axes lengths.Results & Discussion The preliminary results obtained using this methodology is capable of retrieving length, orientation and bounding box of the identified cracks.This method is aimed at assisting in obtaining automated prediction of condition state (CS) rating of cracks in bridges.It can be also used as a tool for post-earthquake damage evaluation purposes.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.004 | 0.003 |
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".