A system design for content-based image retrieval and analysis of mammograms using PostgreSQL with image-handling extension
Bibliographic record
Abstract
This paper presents the design of a system for content-based image retrieval applied to mammograms. The system takes into account the imprecision presents in the search, and makes available user-defined methods to create new image descriptors as well as user-defined feature vectors formed by combinations of previously defined descriptors using a graphical interface. The system was projected and developed using the eXtension Relational DataBase Management System (XRDBMS) PostgreSQL with Image-Handling Extension (PostgreSQL-IE) that supports content-based image retrieval. PostgreSQL-IE is independent of application, and offers the advantage of being open-source and portable. The extended data manipulation and definition language for manipulating image data in the proposed extension is called SQL-IE. The language has a syntax similar to that of SQL (Structured Query Language), and is composed of a set of functions that includes commands to create new feature extraction procedures, new feature vectors as a combination of previously defined features; and new access methods. SQL-IE also includes resources for defining queries by combining conventional and visual data. PostgreSQL-IE makes a new image data type available that permits associating several images with one unique attribute. This resource makes possible the combination of visual features of different images in the same feature vector.
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 | 0.004 | 0.005 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.003 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.008 | 0.006 |
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".