Description: BACKGROUND
Field of Invention
[001] Embodiments of the present invention generally relate to a facemask detection system, and particularly to a system and method for detecting a facemask using advanced learning techniques.
Description of Related Art
[002] Facemask is a layered piece of fabric that is used for preventing spread of diseases. There are many serious respiratory diseases such as Coronavirus (Covid-19), Severe Acute Respiratory Syndrome (SARS), and Middle East Respiratory Syndrome (MERS). These diseases are infectious and usually spread among people breathing in the air close to an infected person. These diseases have increased a lot in past few years. Therefore, the people should be concerned about their health and respiratory diseases.
[003] It has been advised by healthcare organizations that the people who are having respiratory symptoms should certainly wear a face mask. The facemask can prevent the spread of the diseases to a great extent. Therefore, many service providers, schools, colleges, supermarkets, and alike require visitors to wear the face masks. In many places, there is a provision of penalty in case someone is found without a facemask in a public place. However, many people become ignorant and willingly do not want to wear the facemask and ends up spreading the infectious diseases.
[004] There is thus a need for a system that can detect the facemask using advanced learning techniques in a more efficient manner.
SUMMARY
[005] Embodiments in accordance with the present invention provide a facemask detection system. The system includes a camera arranged on a specified location, and adapted to capture images and/or to record a video. The system further includes a controller located on an application server. The controller is configured to prepare a dataset of the captured images and/or the recorded video. The controller is further configured to perform an image augmentation in the dataset for improving a generalization of the dataset. The controller is further configured to enable a single-shot detection of a facemask in the dataset by using an object detection algorithm. The controller is further configured to train the dataset with an object detection model using an inception version 3 architecture. The controller is further configured to evaluate the object detection model and validating the dataset. The controller is further configured to provide results for detection and/or no detection of the facemask in the dataset.
[006] Embodiments in accordance with the present invention further provide a method of detecting a facemask. The method comprising steps of: capturing images and/or recording a video using a camera; preparing a dataset of the captured images and/or the recorded video using a controller; performing image augmentation in the dataset for improving a generalization of the dataset; enabling a single-shot detection of the facemask in the dataset by using an object detection algorithm; training the dataset with an object detection model using an inception version 3 architecture; evaluating the object detection model and validating the dataset; and providing results for detection and/or no detection of the facemask in the dataset.
[007] Embodiments of the present invention may provide a number of advantages depending on their particular configuration. First, embodiments of the present application may provide a facemask detection system incorporating an inception version 3 architecture. Next, embodiments of the present application may provide a facemask detection system that utilizes a transfer learning for training a dataset.
[008] Next, embodiments of the present application may provide a facemask detection system that accurately detects faces with masks and without the masks.
[009] Next, embodiments of the present application may provide a facemask detection system that utilizes an object detection model instead of an image classification technique.
[0010] Next, embodiments of the present application may provide a facemask detection system that may be used with a single-shot detection of a facemask.
[0011] Next, embodiments of the present application may provide a facemask detection system that can be integrated with a camera for real-time detection.
[0012] Next, embodiments of the present application may provide a facemask detection system that achieves an accuracy of 98.53% which makes the system reliable.
[0013] Next, embodiments of the present application may provide a facemask detection system that works faster due to its training with light weight models.
[0014] These and other advantages will be apparent from the present application of the embodiments described herein.
[0015] The preceding is a simplified summary to provide an understanding of some embodiments of the present invention. This summary is neither an extensive nor exhaustive overview of the present invention and its various embodiments. The summary presents selected concepts of the embodiments of the present invention in a simplified form as an introduction to the more detailed description presented below. As will be appreciated, other embodiments of the present invention are possible utilizing, alone or in combination, one or more of the features set forth above or described in detail below.
BRIEF DESCRIPTION OF THE DRAWINGS
[0016] The above and still further features and advantages of embodiments of the present invention will become apparent upon consideration of the following detailed description of embodiments thereof, especially when taken in conjunction with the accompanying drawings, and wherein:
[0017] FIG. 1 illustrates a block diagram depicting a facemask detection system, according to an embodiment of the present invention; and
[0018] FIG. 2 depicts a flowchart of a method of detecting a facemask, according to an embodiment of the present invention.
[0019] The headings used herein are for organizational purposes only and are not meant to be used to limit the scope of the description or the claims. As used throughout this application, the word "may" is used in a permissive sense (i.e., meaning having the potential to), rather than the mandatory sense (i.e., meaning must). Similarly, the words “include”, “including”, and “includes” mean including but not limited to. To facilitate understanding, like reference numerals have been used, where possible, to designate like elements common to the figures. Optional portions of the figures may be illustrated using dashed or dotted lines, unless the context of usage indicates otherwise.
DETAILED DESCRIPTION
[0020] The following description includes the preferred best mode of one embodiment of the present invention. It will be clear from this description of the invention that the invention is not limited to these illustrated embodiments but that the invention also includes a variety of modifications and embodiments thereto. Therefore, the present description should be seen as illustrative and not limiting. While the invention is susceptible to various modifications and alternative constructions, it should be understood, that there is no intention to limit the invention to the specific form disclosed, but, on the contrary, the invention is to cover all modifications, alternative constructions, and equivalents falling within the spirit and scope of the invention as defined in the claims.
[0021] "In any embodiment described herein, the open-ended terms "comprising", "comprises”, and the like (which are synonymous with "including", "having” and "characterized by") may be replaced by the respective partially closed phrases "consisting essentially of", “consists essentially of", and the like or the respective closed phrases "consisting of", "consists of”, the like."
[0022] As used herein, the singular forms “a”, “an”, and “the” designate both the singular and the plural, unless expressly stated to designate the singular only.
[0023] FIG. 1 illustrates a block diagram depicting a facemask detection system 100 (hereinafter referred to as the system 100), according to an embodiment of the present invention. In an embodiment of the present invention, the system 100 may check a presence of a facemask on a face of a person. The system 100 may further check an absence of the facemask on the face of the person, in another embodiment of the present invention. According to embodiments of the present invention, the system 100 may be installed in locations such as, but not limited to, a school, an office, a college, a university, an airport, a railway station, a supermarket, a shopping center, a restaurant, and so forth. Embodiments of the present invention are intended to include or otherwise cover any location for installation of the system 100.
[0024] According to an embodiment of the present invention, the system 100 may comprise a camera 102, a database 104, a dataset 106, an application server 108, a controller 110, and a storage medium 112.
[0025] In an embodiment of the present invention, the camera 102 may be arranged at a specified location, to capture images of the person. In another embodiment of the present invention, the camera 102 may be configured to record a video of the person for a predefined duration. In an exemplary embodiment of the present invention, the predefined duration of the recorded video may be of 2 seconds. In another exemplary embodiment of the present invention, the predefined duration of the recorded video may be of 4 seconds. In yet another exemplary embodiment of the present invention, the video may be of any duration such as defined by a system administrator.
[0026] The camera 102 may also be configured to transmit the captured images and/or recorded video of the person to a central monitoring unit (not shown), in an embodiment of the present invention. In an embodiment of the present invention, the central monitoring unit may be configured for continuous monitoring of the captured images and/or recorded video of the person. In an embodiment of the present invention, the central monitoring unit may be automated using a computer system. In another embodiment of the present invention, a manual monitoring of the captured images and/or recorded video of the person may be done by the system administrator.
[0027] According to other embodiments of the present invention, a resolution for the captured images and/or recorded video using the camera 102 may be, but not limited to, 320 pixels by 240 pixels, 640 pixels by 480 pixels, 1024 pixels by 768 pixels, 1360 pixels by 768 pixels, 1920 pixels by 1080 pixels, and so forth. Embodiments of the present invention are intended to include or otherwise cover any resolution for the captured images and/or recorded video.
[0028] According to other embodiments of the present invention, the camera 102 may be, but not limited to, a still camera, a video camera, a color balancer camera, a thermal camera, an infrared camera, a telephoto camera, a wide-angle camera, a macro camera, and so forth. In a preferred embodiment of the present invention, the camera 102 may be a Close-Circuit Television (CCTV) camera. Embodiments of the present invention are intended to include or otherwise cover any type of the camera 102, including known, related art, and/or later developed technologies.
[0029] In an embodiment of the present invention, the database 104 may store the dataset 106. The dataset 106 may comprise images of mask and no mask faces, in an embodiment of the present invention. According to embodiments of the present invention, the database 104 may be for example, but not limited to, a distributed database, a personal database, an end-user database, a commercial database, a Structured Query Language (SQL) database, a non-SQL database, an operational database, a relational database, an object-oriented database, a graph database, a cloud server database, and so forth. Embodiments of the present invention are intended to include or otherwise cover any type of the database 104 including known, related art, and/or later developed technologies.
[0030] Further, the database 104 may be stored in a cloud server, in an embodiment of the present invention. In an embodiment of the present invention, the cloud server may be remotely located. In an exemplary embodiment of the present invention, the cloud server may be a public cloud server. In another exemplary embodiment of the present invention, the cloud server may be a private cloud server. In yet another embodiment of the present invention, the cloud server may be a dedicated cloud server. According to embodiments of the present invention, the cloud server may be, but not limited to, a Microsoft Azure cloud server, an Amazon AWS cloud server, a Google Compute Engine (GEC) cloud server, an Amazon Elastic Compute Cloud (EC2) cloud server, and so forth. Embodiments of the present invention are intended to include or otherwise cover any type of the cloud server including known, related art, and/or later developed technologies.
[0031] In an embodiment of the present invention, the application server 108 may be a hardware on which the controller 110 may be installed. According to embodiments of the present invention, the application server 108 may be, but not limited to, a motherboard, a wired board, a mainframe, and so forth. Embodiments of the present invention are intended to include or otherwise cover any type of the application server 108, including known, related art, and/or later developed technologies.
[0032] In an embodiment of the present invention, the controller 110 may be configured to execute computer-executable instructions to generate an output relating to the system 100. According to embodiments of the present invention, the controller 110 may be, but not limited to, a Programmable Logic Control (PLC) unit, a microprocessor, a development board, and so forth. Embodiments of the present invention are intended to include or otherwise cover any type of the controller 110 including known, related art, and/or later developed technologies.
[0033] In an embodiment of the present invention, the storage medium 112 may store computer programmable instructions in form of programming modules. The storage medium 112 may be a non-transitory storage medium, in an embodiment of the present invention. In an embodiment of the present invention, the storage medium 112 may store the captured images and/or recorded video of the person received from the camera 102. The storage medium 112 may communicate with the controller 110 and execute the computer-executable instructions present as modules in the storage medium 112, in an embodiment of the present invention.
[0034] According to embodiments of the present invention, the storage medium 112 may be, but not limited to, a Random-Access Memory (RAM), a Static Random-access Memory (SRAM), a Dynamic Random-Access Memory (DRAM), a Read-Only Memory (ROM), an Erasable Programmable Read-only Memory (EPROM), an Electrically Erasable Programmable Read-only Memory (EEPROM), a NAND Flash, a Secure Digital (SD) memory, a cache memory, a Hard Disk Drive (HDD), a Solid-State Drive (SSD), and so forth. Embodiments of the present invention are intended to include or otherwise cover any type of the storage medium 112, including known, related art, and/or later developed technologies. In an embodiment of the present invention, the storage medium 112 further comprises a dataset preparation module 114, a dataset training module 116, a dataset validation module 118, and a facemask detection module 120.
[0035] In an embodiment of the present invention, the dataset preparation module 114 may be configured to prepare the dataset 106 of the captured images and/or the recorded video. The captured images and/or the recorded video may be received from the camera 102, in an embodiment of the present invention. In an embodiment of the present invention, the dataset preparation module 114 may further be configured to perform an image augmentation in the dataset 106 for improving a generalization of the dataset 106. The image augmentation may improve the image captured and/or a frame of the recorded video by removing any disfigurement, in an embodiment of the present invention. According to embodiments of the present invention, the image augmentation may be done by a method such as, but not limited to, a random rotation, a zoom, a shear, a shift, flip parameters of the image, and so forth. Embodiments of the present invention are intended to include or otherwise cover any method for the image augmentation, including known, related art, and/or later developed technologies.
[0036] In an embodiment of the present invention, the dataset preparation module 114 may further be configured to enable a single-shot detection of the facemask in the dataset 106 by using an object detection algorithm. According to embodiments of the present invention, the object detection algorithm may be, but not limited to, a Histogram of Oriented Gradients (HOG), a Region-based Convolutional Neural Network (R-CNN), a Region-based Fully Convolutional Network (R-FCN), a Single-Shot Detector (SSD), a Spatial Pyramid Pooling network (SPP-net), and so forth. Embodiments of the present invention are intended to include or otherwise cover any object detection algorithm, including known, related art, and/or later developed technologies.
[0037] In an embodiment of the present invention, the dataset training module 116 may be configured to train the dataset 106 with an object detection model using an inception version 3 architecture. The inception version 3 architecture may be divided into several inception blocks, in an embodiment of the present invention. In an embodiment of the present invention, each inception block may contain a different combination of convolution layers. The inception version 3 architecture may effectively speed up a training process by reducing a number of connections and also prevents overfitting by reducing parameters to learn, in an embodiment of the present invention.
[0038] In an embodiment of the present invention, the dataset validation module 118 may be configured to validate the dataset 106. The dataset 106 may be validated by evaluating the object detection model, in an embodiment of the present invention.
[0039] In an embodiment of the present invention, the facemask detection module 120 may be configured to provide results in the dataset 106. The results may be provided as detection and/or no detection of the facemask, in an embodiment of the present invention.
[0040] FIG. 2 depicts a flowchart of a method 200 of detecting the facemask, according to an embodiment of the present invention.
[0041] At step 202, the system 100 may capture the images and/or record the video using the camera 102.
[0042] At step 204, the system 100 may prepare the dataset 106 of the captured images and/or the recorded video using the controller 110.
[0043] At step 206, the system 100 may perform the image augmentation in the dataset 106 for improving the generalization of the dataset 106.
[0044] At step 208, the system 100 may enable the single-shot detection of the facemask in the dataset 106 by using the object detection algorithm.
[0045] At step 210, the system 100 may train the dataset 106 with the object detection model using the transferred learning with the inception version 3 architecture.
[0046] At step 212, the system 100 may evaluate the object detection model and validate the dataset 106.
[0047] At step 214, the system 100 may provide results for detection and/or no detection of the facemask in the dataset 106.
[0048] Embodiments of the invention are described above with reference to block diagrams and schematic illustrations of methods and systems according to embodiments of the invention. It will be understood that each block of the diagrams and combinations of blocks in the diagrams can be implemented by computer program instructions. These computer program instructions may be loaded onto one or more general-purpose computers, special purpose computers, or other programmable data processing apparatus to produce machines, such that the instructions which execute on the computers or other programmable data processing apparatus create means for implementing the functions specified in the block or blocks. Such computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means that implement the function specified in the block or blocks.
[0049] While the invention has been described in connection with what is presently considered to be the most practical and various embodiments, it is to be understood that the invention is not to be limited to the disclosed embodiments, but on the contrary, is intended to cover various modifications and equivalent arrangements included within the spirit and scope of the appended claims.
[0050] This written description uses examples to disclose the invention, including the best mode, and also to enable any person skilled in the art to practice the invention, including making and using any devices or systems and performing any incorporated methods. The patentable scope of the invention is defined in the claims, and may include other examples that occur to those skilled in the art. Such other examples are intended to be within the scope of the claims if they have structural elements that do not differ from the literal language of the claims, or if they include equivalent structural elements within substantial differences from the literal languages of the claims.
, Claims: I/We Claim:
1. A facemask detection system (100), the system (100) comprising:
a camera (102) arranged on a specified location, and adapted to capture images and/or to record a video; and
a controller (110) located on an application server (108), and configured to:
prepare a dataset (106) of the captured images and/or the recorded video;
perform an image augmentation in the dataset (106) for improving a generalization of the dataset (106);
enable a single-shot detection of the facemask in the dataset (106) by using an object detection algorithm;
train the dataset (106) with an object detection model using an inception version 3 architecture;
evaluate the object detection model and validating the dataset (106); and
provide results for detection and/or no detection of the facemask in the dataset (106).
2. The system (100) as claimed in claim 1, wherein the camera (102) is a Closed-Circuit Television camera.
3. The system (100) as claimed in claim 1, wherein the image augmentation comprises a random rotation, a zoom, a shear, a shift, flip parameters of the image, or a combination thereof.
4. The system (100) as claimed in claim 1, wherein the dataset (106) is trained using a transferred learning.
5. The system (100) as claimed in claim 1, wherein the dataset (106) comprises the images of mask faces and no mask faces.
6. A method (200) of detecting a facemask, the method (200) comprising steps of:
capturing images and/or recording a video using a camera (102);
preparing a dataset (106) of the captured images and/or the recorded video using a controller (110);
performing image augmentation in the dataset (106) for improving a generalization of the dataset (106);
enabling a single-shot detection of the facemask in the dataset (106) by using an object detection algorithm;
training the dataset (106) with an object detection model using an inception version 3 architecture;
evaluating the object detection model and validating the dataset (106); and
providing results for detection and/or no detection of the facemask in the dataset (106).
7. The method (200) as claimed in claim 6, wherein the camera (102) is a Closed-Circuit Television camera.
8. The method (200) as claimed in claim 6, wherein the image augmentation comprises a random rotation, a zoom, a shear, a shift, flip parameters of the image, or a combination thereof.
9. The method (200) as claimed in claim 6, wherein the dataset (106) is trained using a transferred learning.
10. The method (200) as claimed in claim 6, wherein the dataset (106) comprises the images of mask faces and no mask faces.
Date: 22 April 2022
Place: Noida

Nainsi Rastogi
Patent Agent (IN/PA-2372)
Agent for the Applicant