Evaluation of feature points descriptors' performance for visual finger printing localization of smartphones
Bibliographic record
Abstract
Visual information are among the useful sources that can be used to localize a smartphone device. Visual information can be used in the process of image matching based on a pre-built database and Visual Map (A map tagged with images). There are different number of feature detection/description algorithms. These algorithms vastly differ in the accuracy, space usage and average matching time for each image. The color information obtained using these methods is typically ignored during the further processing steps. This paper investigates and compares thirteen different descriptors for Visual Finger Printing (VFP) localization of smartphones. These descriptors can be divided into three categories; color histogram, color-moment and Scale Invariant Feature Transformation (SIFT) based algorithms. These descriptors except for the original SIFT are all based on the colored information. Four spaces, RGB, opponent, transformed and HSV are represented in the results. The results show that the SIFT-like algorithms, despite having a high accuracy, takes more time and space that can surpass the real-time implementation requirements on a smartphone. However, the accuracy associated with SIFT algorithms are predominantly higher than moment based, and histogram-based algorithms. Testing also show a slightly better performance for the RGB-SIFT's, Opponent SIFT (O-SIFT) and SIFT, for the investigated experiment setups. However, with different image size, these advantages might vanish or even be reversed. The results also show that with a proper image size reduction and choice of a color space, the practical implementation requirements on a smartphone for SIFT and histogram-based methods can be met.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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 teacher head, 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".