A New Algorithm for the Automatic Skin Ulcer Detection Using Color Features
Bibliographic record
Abstract
This paper presents a new algorithm for automatic skin cancerous ulcer detection, leveraging image processing and machine learning techniques to improve diagnostic accuracy.The proposed method consists of two main phases: learning and detection, preceded by a crucial pre-processing step to enhance image quality.The presence of hair can obscure ulcerated regions, leading to inaccurate detection.To address this, the DullRazor algorithm is applied, effectively removing hairs while preserving critical lesion details.This step ensures clearer feature extraction in subsequent stages.A dataset of 200 manually annotated ulcer images is analyzed to identify distinguishing characteristics.Three key reference feature vectors are derived: Texture (Capturing roughness and irregularity patterns), Relative Color (Comparing ulcer hues against surrounding healthy skin), and Color (Identifying diseasespecific pigmentations).An analysis window scans the lesion, comparing local features against the reference vectors.If the extracted features closely match, the region is classified as ulcerated.Distance metrics or machine learning classifiers likely determine similarity thresholds.Two methods are used to evaluate the suggested algorithm.A dermatologist will subjectively (qualitatively) determine if the detection is "Good", "Fairly good", or "not detected", objectively, based on whether the ulcer is there or not.The results of the proposed algorithm are encouraging, as they gave promising results.
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 | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.004 | 0.002 |
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".