During the coronavirus pandemic, the mask detection problem has become of particular interest. Usually, the goal is to create a system that can detect whether or not a person is wearing a mask or respirator. However, this tends to trivialize a problem that hides a greater complexity. In fact, people wear masks or respirators in various ways, many of which are incorrect. This makes the problem ill-conditioned and creates a bias compared to training cases, with the consequence that these systems have a considerably lower accuracy when used in practice. We claim that focusing on the ways in which a mask can be worn and classifying the problem not as binary but at least as ternary, thus adding an intermediate class containing all those ways in which a mask or respirator can be worn incorrectly, could help address this problem. For this reason, this paper describes and puts to the proof the Ways to Wear a Mask or a Respirator Database (WWMR-DB). It has a fine classification of the most common ways in which a mask or respirator is worn, which can be used to test how mask detection systems work in cases that resemble the real ones more. It was used to test a neural network, the ResNet-152, which was trained on less fine databases, like the Face-Mask Label Dataset and the MaskedFace-Net. The mixed results denote the shortcomings of these databases and the need to enhance them or resort to finer databases.
Mask and respirator detection: analysis and potential solutions for a frequently ill-conditioned problem / Marceddu, ANTONIO COSTANTINO; Ferrero, Renato; Montrucchio, Bartolomeo. - ELETTRONICO. - (2022), pp. 1056-1061. (Intervento presentato al convegno 2022 IEEE 46th Annual Computers, Software, and Applications Conference (COMPSAC) tenutosi a Online nel 27 June - 1 July 2022) [10.1109/COMPSAC54236.2022.00165].
Mask and respirator detection: analysis and potential solutions for a frequently ill-conditioned problem
Antonio Costantino Marceddu;Renato Ferrero;Bartolomeo Montrucchio
2022
Abstract
During the coronavirus pandemic, the mask detection problem has become of particular interest. Usually, the goal is to create a system that can detect whether or not a person is wearing a mask or respirator. However, this tends to trivialize a problem that hides a greater complexity. In fact, people wear masks or respirators in various ways, many of which are incorrect. This makes the problem ill-conditioned and creates a bias compared to training cases, with the consequence that these systems have a considerably lower accuracy when used in practice. We claim that focusing on the ways in which a mask can be worn and classifying the problem not as binary but at least as ternary, thus adding an intermediate class containing all those ways in which a mask or respirator can be worn incorrectly, could help address this problem. For this reason, this paper describes and puts to the proof the Ways to Wear a Mask or a Respirator Database (WWMR-DB). It has a fine classification of the most common ways in which a mask or respirator is worn, which can be used to test how mask detection systems work in cases that resemble the real ones more. It was used to test a neural network, the ResNet-152, which was trained on less fine databases, like the Face-Mask Label Dataset and the MaskedFace-Net. The mixed results denote the shortcomings of these databases and the need to enhance them or resort to finer databases.File | Dimensione | Formato | |
---|---|---|---|
Mask_and_respirator_detection_analysis_and_potential_solutions_for_a_frequently_ill-conditioned_problem.pdf
accesso riservato
Tipologia:
2a Post-print versione editoriale / Version of Record
Licenza:
Non Pubblico - Accesso privato/ristretto
Dimensione
653.91 kB
Formato
Adobe PDF
|
653.91 kB | Adobe PDF | Visualizza/Apri Richiedi una copia |
Camera+Ready.pdf
accesso aperto
Tipologia:
2. Post-print / Author's Accepted Manuscript
Licenza:
Pubblico - Tutti i diritti riservati
Dimensione
844.62 kB
Formato
Adobe PDF
|
844.62 kB | Adobe PDF | Visualizza/Apri |
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
https://hdl.handle.net/11583/2963422