Compact convolutional neural network cascadefor face detection
| Parent link: | CEUR Workshop Proceedings: Online Proceedings for Scientific Conferences and Workshops Vol. 1576 : Parallel Computing Technologies 2016, PCT 2016.— 2016.— [P. 375-387] |
|---|---|
| Main Author: | |
| Corporate Author: | |
| Other Authors: | |
| Summary: | Title screen This paper presents a new solution to the frontal face detection problem based on a compact convolutional neural networks cascade. Test results on an FDDB dataset show that it is able to compete with state-of-the-art algorithms. This proposed detector is implemented using three technologies: SSE/AVX/AVX2 instruction sets for Intel CPUs, Nvidia CUDA, and OpenCL. The detection speed of our approach exceeds considerably all the existing CPUbased and GPU-based algorithms. Thanks to its high computational efficiency, our detector can process 4K Ultra HD video stream in real time (up to 27 fps) on mobile platforms while searching objects with a dimension of 60×60 pixels or higher. At the same time, its processing speed is almost independent of the background and the number of objects in a scene. This is achieved by asynchronous computation of stages in the cascade. |
| Language: | English |
| Published: |
2016
|
| Subjects: | |
| Online Access: | http://earchive.tpu.ru/handle/11683/36142 http://ceur-ws.org/Vol-1576/150.pdf |
| Format: | Electronic Book Chapter |
| KOHA link: | https://koha.lib.tpu.ru/cgi-bin/koha/opac-detail.pl?biblionumber=650721 |
MARC
| LEADER | 00000naa0a2200000 4500 | ||
|---|---|---|---|
| 001 | 650721 | ||
| 005 | 20250903132357.0 | ||
| 035 | |a (RuTPU)RU\TPU\network\15970 | ||
| 090 | |a 650721 | ||
| 100 | |a 20161018d2016 k||y0engy50 ba | ||
| 101 | 0 | |a eng | |
| 102 | |a DE | ||
| 135 | |a drcn ---uucaa | ||
| 181 | 0 | |a i | |
| 182 | 0 | |a b | |
| 200 | 1 | |a Compact convolutional neural network cascadefor face detection |f I. A. Kalinovsky, V. G. Spitsyn | |
| 203 | |a Text |c electronic | ||
| 300 | |a Title screen | ||
| 330 | |a This paper presents a new solution to the frontal face detection problem based on a compact convolutional neural networks cascade. Test results on an FDDB dataset show that it is able to compete with state-of-the-art algorithms. This proposed detector is implemented using three technologies: SSE/AVX/AVX2 instruction sets for Intel CPUs, Nvidia CUDA, and OpenCL. The detection speed of our approach exceeds considerably all the existing CPUbased and GPU-based algorithms. Thanks to its high computational efficiency, our detector can process 4K Ultra HD video stream in real time (up to 27 fps) on mobile platforms while searching objects with a dimension of 60×60 pixels or higher. At the same time, its processing speed is almost independent of the background and the number of objects in a scene. This is achieved by asynchronous computation of stages in the cascade. | ||
| 461 | |t CEUR Workshop Proceedings |o Online Proceedings for Scientific Conferences and Workshops | ||
| 463 | |t Vol. 1576 : Parallel Computing Technologies 2016, PCT 2016 |o Proceedings of the 10th Annual International Scientific Conference on Parallel Computing Technologies, Arkhangelsk, Russia, March 29-31, 2016 |v [P. 375-387] |d 2016 | ||
| 610 | 1 | |a электронный ресурс | |
| 610 | 1 | |a труды учёных ТПУ | |
| 610 | 1 | |a распознавание лиц | |
| 610 | 1 | |a нейронные сети | |
| 610 | 1 | |a классификаторы | |
| 700 | 1 | |a Kalinovsky |b I. A. |c specialist in the field of Informatics and computer engineering |c assistant at Tomsk Polytechnic University |f 1990- |g Iljya Andreevich |3 (RuTPU)RU\TPU\pers\37438 | |
| 701 | 1 | |a Spitsyn |b V. G. |c specialist in the field of informatics and computer technology |c Professor of Tomsk Polytechnic University, Doctor of technical sciences |f 1948- |g Vladimir Grigorievich |3 (RuTPU)RU\TPU\pers\33492 |9 17160 | |
| 712 | 0 | 2 | |a Национальный исследовательский Томский политехнический университет (ТПУ) |b Институт кибернетики (ИК) |b Кафедра вычислительной техники (ВТ) |3 (RuTPU)RU\TPU\col\18699 |
| 801 | 2 | |a RU |b 63413507 |c 20170124 |g RCR | |
| 856 | 4 | |u http://earchive.tpu.ru/handle/11683/36142 | |
| 856 | 4 | |u http://ceur-ws.org/Vol-1576/150.pdf | |
| 942 | |c CF | ||