Tampere University of Technology

TUTCRIS Research Portal

Cascade of Boolean detector combinations

Research output: Contribution to journalArticleScientificpeer-review

Standard

Cascade of Boolean detector combinations. / Mahkonen, Katariina; Virtanen, Tuomas; Kämäräinen, Joni.

In: Eurasip Journal on Image and Video Processing, Vol. 2018, 61, 12.2018.

Research output: Contribution to journalArticleScientificpeer-review

Harvard

Mahkonen, K, Virtanen, T & Kämäräinen, J 2018, 'Cascade of Boolean detector combinations', Eurasip Journal on Image and Video Processing, vol. 2018, 61. https://doi.org/10.1186/s13640-018-0303-9

APA

Mahkonen, K., Virtanen, T., & Kämäräinen, J. (2018). Cascade of Boolean detector combinations. Eurasip Journal on Image and Video Processing, 2018, [61]. https://doi.org/10.1186/s13640-018-0303-9

Vancouver

Mahkonen K, Virtanen T, Kämäräinen J. Cascade of Boolean detector combinations. Eurasip Journal on Image and Video Processing. 2018 Dec;2018. 61. https://doi.org/10.1186/s13640-018-0303-9

Author

Mahkonen, Katariina ; Virtanen, Tuomas ; Kämäräinen, Joni. / Cascade of Boolean detector combinations. In: Eurasip Journal on Image and Video Processing. 2018 ; Vol. 2018.

Bibtex - Download

@article{49151356678c422284f7b47066c0c05f,
title = "Cascade of Boolean detector combinations",
abstract = "This paper considers a scenario when we have multiple pre-trained detectors for detecting an event and a small dataset for training a combined detection system. We build the combined detector as a Boolean function of thresholded detector scores and implement it as a binary classification cascade. The cascade structure is computationally efficient by providing the possibility to early termination. For the proposed Boolean combination function, the computational load of classification is reduced whenever the function becomes determinate before all the component detectors have been utilized. We also propose an algorithm, which selects all the needed thresholds for the component detectors within the proposed Boolean combination. We present results on two audio-visual datasets, which prove the efficiency of the proposed combination framework. We achieve state-of-the-art accuracy with substantially reduced computation time in laughter detection task, and our algorithm finds better thresholds for the component detectors within the Boolean combination than the other algorithms found in the literature.",
keywords = "Binary classification, Boolean combination, Classification cascade",
author = "Katariina Mahkonen and Tuomas Virtanen and Joni K{\"a}m{\"a}r{\"a}inen",
year = "2018",
month = "12",
doi = "10.1186/s13640-018-0303-9",
language = "English",
volume = "2018",
journal = "Eurasip Journal on Image and Video Processing",
issn = "1687-5176",
publisher = "Springer Verlag",

}

RIS (suitable for import to EndNote) - Download

TY - JOUR

T1 - Cascade of Boolean detector combinations

AU - Mahkonen, Katariina

AU - Virtanen, Tuomas

AU - Kämäräinen, Joni

PY - 2018/12

Y1 - 2018/12

N2 - This paper considers a scenario when we have multiple pre-trained detectors for detecting an event and a small dataset for training a combined detection system. We build the combined detector as a Boolean function of thresholded detector scores and implement it as a binary classification cascade. The cascade structure is computationally efficient by providing the possibility to early termination. For the proposed Boolean combination function, the computational load of classification is reduced whenever the function becomes determinate before all the component detectors have been utilized. We also propose an algorithm, which selects all the needed thresholds for the component detectors within the proposed Boolean combination. We present results on two audio-visual datasets, which prove the efficiency of the proposed combination framework. We achieve state-of-the-art accuracy with substantially reduced computation time in laughter detection task, and our algorithm finds better thresholds for the component detectors within the Boolean combination than the other algorithms found in the literature.

AB - This paper considers a scenario when we have multiple pre-trained detectors for detecting an event and a small dataset for training a combined detection system. We build the combined detector as a Boolean function of thresholded detector scores and implement it as a binary classification cascade. The cascade structure is computationally efficient by providing the possibility to early termination. For the proposed Boolean combination function, the computational load of classification is reduced whenever the function becomes determinate before all the component detectors have been utilized. We also propose an algorithm, which selects all the needed thresholds for the component detectors within the proposed Boolean combination. We present results on two audio-visual datasets, which prove the efficiency of the proposed combination framework. We achieve state-of-the-art accuracy with substantially reduced computation time in laughter detection task, and our algorithm finds better thresholds for the component detectors within the Boolean combination than the other algorithms found in the literature.

KW - Binary classification

KW - Boolean combination

KW - Classification cascade

U2 - 10.1186/s13640-018-0303-9

DO - 10.1186/s13640-018-0303-9

M3 - Article

VL - 2018

JO - Eurasip Journal on Image and Video Processing

JF - Eurasip Journal on Image and Video Processing

SN - 1687-5176

M1 - 61

ER -