A comparative analysis of neural and statistical classifiers for dimensionality reduction-based face recognition systems.
Bibliographic record
Abstract
Human face recognition has received a wide range of attention since 1990s. Recent approaches focus on a combination of dimensionality reduction-based feature extraction algorithms and various types of classifiers. This thesis provides an in depth comparative analysis of neural and statistical classifiers by combining them with existing dimensionality reduction-based algorithms. A set of unified face recognition systems were established for evaluating alternate combinations in terms of recognition performance, processing time, and conditions to achieve certain performance levels. A preprocessing system and four dimensionality reduction-based methods based on Principal Component Analysis (PCA), Two-dimensional PCA, Fisher's Linear Discriminant and Laplacianfaces were utilized and implemented. Classification was achieved by using various types of classifiers including Euclidean Distance, MLP neural network, K-nearest-neighborhood classifier and Fuzzy K-Nearest Neighbor classifier. The statistical model is relatively simple and requires less computation complexity and storage. Experimental results were shown after the algorithms were tested on two databases of known individuals, Yale and AR database. After comparing these algorithms in every aspect, the results of the simulations showed that considering recognition rates, generalization ability, classification performance, the power of noise immunity and processing time, the best results were obtained with the Laplacianfaces, using either Fuzzy K-NN.Dept. of Electrical and Computer Engineering. Paper copy at Leddy Library: Theses & Major Papers - Basement, West Bldg. / Call Number: Thesis2006 .X86. Source: Masters Abstracts International, Volume: 45-01, page: 0428. Thesis (M.A.Sc.)--University of Windsor (Canada), 2006.
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 | 0.005 | 0.010 |
| 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 | 0.002 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 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".