Napredna pretraga

Pregled bibliografske jedinice broj: 832723

Two-stage cascade model for unconstrained face detection


Marčetić, Darijan; Hrkać, Tomislav; Ribarić, Slobodan
Two-stage cascade model for unconstrained face detection // First International Workshop on Sensing, Processing and Learning for Intelligent Machines (SPLINE), 2016 / Zheng - Hua Tan (ur.).
Aalborg: Curran Associates, Inc., 2016. str. 21-24 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)


Naslov
Two-stage cascade model for unconstrained face detection

Autori
Marčetić, Darijan ; Hrkać, Tomislav ; Ribarić, Slobodan

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
First International Workshop on Sensing, Processing and Learning for Intelligent Machines (SPLINE), 2016 / Zheng - Hua Tan - Aalborg : Curran Associates, Inc., 2016, 21-24

ISBN
978-1-4673-8916-7

Skup
First International Workshop on Sensing, Processing and Learning for Intelligent Machines (SPLINE), 2016

Mjesto i datum
Aalborg, Denmark, July 6 - 8, 2016

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
Face; Detectors; Face detection; Silicon; Deformable models; Computational modeling; Feature extraction

Sažetak
In this paper, we propose a two-stage model for unconstrained face detection. The first stage is based on the normalized pixel difference (NPD) method, and the second stage uses the deformable part model (DPM) method. The NPD method applied to in the wild image datasets outputs the unbalanced ratio of false positive to false negative face detection when the main goal is to achieve minimal false negative face detection. In this case, false positive face detection is typically an order of magnitude higher. The result of the NPD-based detector is forwarded to the DPMbased detector in order to reduce the number of false positive detections. In this paper, we compare the results obtained by the NPD and DPM methods on the one hand, and the proposed two-stage model on the other. The preliminary experimental results on the Annotated Faces in the Wild (AFW) and the Face Detection Dataset and Benchmark (FDDB) show that the two-stage model significantly reduces false positive detections while simultaneously the number of false negative detections is increased by only a few.

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo



POVEZANOST RADA


Projekt / tema
HRZZ-IP-2013-11-6733 - Zaštita privatnosti deidentifikacijom u nadzornim sustavima (Slobodan Ribarić, )
HRZZ-UIP-2013-11-1544 - Metode deidentifikacije za meke i ne-biometrijske identifikatore (Tomislav Hrkać, )

Ustanove
Fakultet elektrotehnike i računarstva, Zagreb

Citiraj ovu publikaciju

Marčetić, Darijan; Hrkać, Tomislav; Ribarić, Slobodan
Two-stage cascade model for unconstrained face detection // First International Workshop on Sensing, Processing and Learning for Intelligent Machines (SPLINE), 2016 / Zheng - Hua Tan (ur.).
Aalborg: Curran Associates, Inc., 2016. str. 21-24 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)
Marčetić, D., Hrkać, T. & Ribarić, S. (2016) Two-stage cascade model for unconstrained face detection. U: Zheng - Hua Tan (ur.)First International Workshop on Sensing, Processing and Learning for Intelligent Machines (SPLINE), 2016.
@article{article, year = {2016}, pages = {21-24}, keywords = {Face, Detectors, Face detection, Silicon, Deformable models, Computational modeling, Feature extraction}, isbn = {978-1-4673-8916-7}, title = {Two-stage cascade model for unconstrained face detection}, keyword = {Face, Detectors, Face detection, Silicon, Deformable models, Computational modeling, Feature extraction}, publisher = {Curran Associates, Inc.}, publisherplace = {Aalborg, Denmark} }