Rotation distortions for improvement in face recognition with PCNC

Monterrosas, Zamira Cruz; Baidyk, Tatiana; Kussul, Ernst; Gallardo, Alejandro J. Ibarra

doi:10.1109/iwobi.2014.6913937

Cited by 2 publications

(2 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our approach is based on the addition of rotation distortions to the training set. The results improved from 46.6% to 23.00% for four distortions, from 41.7% to 21.00% for eight distortions and from 31.1% to 16.00% for 12 distortions [35,36]. In comparison with the basic version (without rotations), the new version significantly improved the recognition rate by decreasing by approximately twice the number of errors.…”

Section: Experiments and Resultsmentioning

confidence: 85%

See 1 more Smart Citation

Analysis of Random Local Descriptors in Face Recognition

2021

Self Cite

View full text Add to dashboard Cite

This article describes and analyzes the new feature extraction technique, Random Local Descriptor (RLD), that is used for the Permutation Coding Neural Classifier (PCNC), and compares it with Local Binary Pattern (LBP-based) feature extraction. The paper presents a model of face feature detection using local descriptors, and describes an improvement on the PCNC for the recognition of plane rotated and small displaced face images, as applied to three databases, i.e., ORL, FRAV3D and FEI. All databases are described along with the recognition results that were obtained. We also include a comparison of our classifier with the Support Vector Machine (SVM) and Iterative Closest Point (ICP). The ORL database was selected to compare our RLDs with LBP-based algorithms. The PCNC with the RLDs demonstrated the best recognition rate, i.e., 97.49%, in comparison with 90.49% for LBPs. For the FEI image database, we obtained the best recognition rate, i.e., 93.57%, in comparison with 66.74% for LBPs. Using the RLDs and rotating the original images for FRAV3D, we improved the recognition rate by decreasing by approximately twice the number of errors. In addition, we analyzed the influence of different RLD parameters on the quality of facial recognition.

show abstract

Section: Experiments and Resultsmentioning

confidence: 85%

“…We consider the middle of the face image to be the origin O(w/2,h/2). For our experiments, we selected three values of the clockwise rotation angle (the reference point is the vertical axis) θ = 5 • , 10 • , 15 • , and three values for counterclockwise rotations θ = −5 • , −10 • , −15 • [35,36].…”

Section: Experiments and Resultsmentioning

confidence: 99%