Optimal face templates: the next step in surveillance face recognition

Malach, Tobias; Poměnková, Jitka

doi:10.1007/s10044-019-00842-y

Cited by 3 publications

(10 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this study, in line with the stated objective, we evaluate each method’s influence on the recognition performance of the system described earlier, utilizing the extended database. The cluster description-based methods (namely centroid, weighted centroid, and medoid) and Gaussian mixture model method were also used in our previous research [ 11 , 20 ].…”

Section: Methodological Overviewmentioning

confidence: 99%

“…The central focus of this research lies in the creation of a template for the classifier. As documented in our work [ 11 ], a suitable representation of a face contributes to the improvement of the face recognition rate. Therefore, we investigate a template creation process to enhance the correct recognition rate, and we use the face recognition systems described above as they are convenient for implementation in security systems and edge computing devices.…”

Section: Introductionmentioning

confidence: 99%

“…Various methods for template creation have been introduced in the literature [ 11 , 12 , 13 ]. The main objective of this paper is to offer a comprehensive performance comparison of template creation methods while conducting an in-depth study of selected methods and their characteristics.…”

Section: Introductionmentioning

confidence: 99%

“…Most results were evaluated on images from the IFaViD database [ 14 ], which comprises real-world scenarios and applications captured by security cameras. In our prior work, we used IFaViD database images captured in two scenarios represented by datasets A1 and B (for a detailed description see [ 11 ]). In this study, we used a database extended by the dataset A2, which consists of 62,801 images and extends the overall number of images in the database nearly four times (see Table 2).…”

Section: Introductionmentioning

confidence: 99%

“…In our previous research, we found out that the quantile interval method (QIM) method is a promising method for creating a face template in the face recognition process [ 11 ]. Previously, QIM was solely compared with the centroid method, while the presented paper proposes a comparison with other above-mentioned methods.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Optimized Classifier Learning for Face Recognition Performance Boost in Security and Surveillance Applications

Poměnková

Malach

2023

Sensors

Self Cite

View full text Add to dashboard Cite

Face recognition has become an integral part of modern security processes. This paper introduces an optimization approach for the quantile interval method (QIM), a promising classifier learning technique used in face recognition to create face templates and improve recognition accuracy. Our research offers a three-fold contribution to the field. Firstly, (i) we strengthened the evidence that QIM outperforms other contemporary template creation approaches. For this reason, we investigate seven template creation methods, which include four cluster description-based methods and three estimation-based methods. Further, (ii) we extended testing; we use a nearly four times larger database compared to the previous study, which includes a new set, and we report the recognition performance on this extended database. Additionally, we distinguish between open- and closed-set identification. Thirdly, (iii) we perform an evaluation of the cluster estimation-based method (specifically QIM) with an in-depth analysis of its parameter setup in order to make its implementation feasible. We provide instructions and recommendations for the correct parameter setup. Our research confirms that QIM’s application in template creation improves recognition performance. In the case of automatic application and optimization of QIM parameters, improvement recognition is about 4–10% depending on the dataset. In the case of a too general dataset, QIM also provides an improvement, but the incorporation of QIM into an automated algorithm is not possible, since QIM, in this case, requires manual setting of optimal parameters. This research contributes to the advancement of secure and accurate face recognition systems, paving the way for its adoption in various security applications.

show abstract

Section: Methodological Overviewmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%