Description:BACKGROUND
Field of Invention
[001] Embodiments of the present invention generally relate to a face recognition system and particularly to a face recognition system through Principal Component Analysis (PCA) algorithm.
Description of Related Art
[002] Face recognition systems have seen widespread adoption in various domains, from security to personal devices, due to their ability to accurately identify individuals. One of the fundamental techniques employed in these systems is Principal Component Analysis (PCA) algorithm. PCA is a powerful tool for dimensionality reduction and feature extraction, making it particularly suitable for analyzing facial images. By representing facial images in a lower-dimensional space, PCA facilitates efficient and effective recognition of faces, even in the presence of variations in illumination, pose, and facial expressions. However, while PCA-based face recognition systems have shown promising results, there is an ongoing research to enhance their accuracy, speed, and robustness, thus making them more suitable for real-world applications.
[003] There is thus a need for an improved and advanced face recognition system through Principal Component Analysis (PCA) algorithm that can administer the aforementioned limitations in a more efficient manner.
SUMMARY
[004] Embodiments in accordance with the present invention provide a face recognition system through Principal Component Analysis (PCA) algorithm. The system comprising: a user device adapted to upload and/or capture a digital image. The system further comprising: a processor. The processor is configured to: receive the uploaded and/or the captured digital image from the user device; recognize a human face from the received digital image; segment the recognized human faces into, one of categories; filter the selected human face from one of the categories; analyze features of the filtered human face; obtain a covariance matrix from the analyzed features of the filtered human face; calculate Eigen values, Eigen vectors, Eigen faces, for the obtained covariance matrix to obtain a distance; compare the distance with zero; and match the human face in the digital content with the training set of human faces to recognize the human face, when the distance is greater than zero.
[005] Embodiments in accordance with the present invention further provide a method for face recognition system through Principal Component Analysis (PCA) algorithm. The method comprising steps of: receiving uploaded and/or the captured digital image from a user device; recognizing a human face from the received digital image; segmenting the recognized human faces into, one of categories; filtering the selected human face from one of the categories; analyzing features of the filtered human face; obtaining a covariance matrix from the analyzed features of the filtered human face; calculating Eigen values, Eigen vectors, Eigen faces, for the obtained covariance matrix to obtain a distance; comparing the distance with zero; and matching the human face in the digital content with the training set of human faces to recognize the human face, when the distance is greater than zero.
[006] 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 face recognition system through Principal Component Analysis (PCA) algorithm.
[007] Next, embodiments of the present application may provide a face recognition system through Principal Component Analysis (PCA) algorithm that reduces the data needed to recognize the individual to 1/1000th of the data presented.
[008] These and other advantages will be apparent from the present application of the embodiments described herein.
[009] 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
[0010] 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:
[0011] FIG. 1 illustrates a block diagram of a face recognition system through Principal Component Analysis (PCA) algorithm, according to an embodiment of the present invention;
[0012] FIG. 2 illustrates a block diagram of a processor of the face recognition system through Principal Component Analysis (PCA) algorithm, according to an embodiment of the present invention; and
[0013] FIG. 3 depicts a flowchart of a method for face recognition system through Principal Component Analysis (PCA) algorithm, according to an embodiment of the present invention.
[0014] 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
[0015] 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 scope of the invention as defined in the claims.
[0016] 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.
[0017] 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.
[0018] FIG. 1 illustrates a block diagram of a face recognition system 100 (hereinafter referred to as the system 100) through Principal Component Analysis (PCA) algorithm, according to an embodiment of the present invention. The system 100 may be utilized for various applications requiring quick and accurate facial recognition and matching. For instance, the system 100 may be deployed in security systems for access control, allowing only authorized individuals entry to secured premises or resources. Additionally, the system 100 may be integrated into surveillance systems for identifying persons of interest in real-time from video feeds. Furthermore, the system 100 may find applications in personal devices like smartphones or laptops for enabling secure authentication for ensuring that only the rightful owner can access sensitive information or perform certain actions. Overall, the system 100 may offer a versatile solution for numerous scenarios where robust face recognition capabilities are paramount.
[0019] In an embodiment of the present invention, the system 100 may comprise non-limiting elements such as a user device 102, a processor 104, a database 106, and a training set 108.
[0020] In an embodiment of the present invention, the user device 102 may be adapted to upload and/or capture a digital image. The processor 104 may compare the uploaded digital image with the training set 108 stored in the database 106. If a human face in the uploaded digital content may be present in the training set 108 then the system 100 may recognize the human face in the uploaded digital content. Else, the system 100 may instate the human face in the uploaded digital content in the training set 108. The training set 108 contains 400 digital content of 40 different human faces. The digital content may be images.
[0021] In an embodiment of the present invention, the Principal Component Analysis (PCA) algorithm may be an optimal compression scheme that may minimizes mean squared error between the digital content and their reconstructions for any given level of compression. The Principal Component Analysis (PCA) algorithm may be based on the idea that face recognition may be be accomplished with a small set of features that best approximates the set of known facial images.
[0022] Application of the Principal Component Analysis (PCA) algorithm for face recognition may proceed by first performing Principal Component Analysis (PCA) algorithm on the training set 108 of known human faces. From this analysis, a set of principal components may be obtained, and the projection of the test faces on these components may be used in order to compute distances between test faces and the training faces. These distances, in turn, may be used to make predictions about the test faces. The Principal Component Analysis (PCA) algorithm may approach may reduce dimensions of human face space data by means of feature extraction and the reduction of the dimensions may remove information that may not useful or required to recognize the human face.
[0023] FIG. 2 illustrates a block diagram of the processor 104 of the system 100, according to an embodiment of the present invention. The processor 104 may comprise the computer-executable instructions in form of programming modules such as a data receiving module 200, data recognition module 202, data segmentation module 204, data filter module 206, data analysis module 208, data obtaining module 210, data calculation module 212, data comparison module 214, and a data match module 216.
[0024] In an embodiment of the present invention, the data receiving module 200 may be configured to receive the uploaded and/or the captured digital image from the user device 102. The data receiving module 200 may temporarily store the received uploaded and/or the captured digital image in an associated memory (not shown), facilitating subsequent processing steps. In another embodiment of the present invention, the data receiving module 200 may permanently store the received uploaded and/or the captured digital image in the associated memory, ensuring long-term retention of the image data for future reference or analysis purposes.
[0025] In an embodiment of the present invention, the data recognition module 202 may be configured to recognize the human face from the received digital image by employing advanced facial recognition algorithms and techniques. These algorithms may involve detecting key facial features, such as eyes, nose, and mouth, and analyzing their spatial relationships to identify and delineate the contours of the human face within the digital image. Embodiments of the present invention are intended to include or otherwise cover any type of the key facial features including known, related art, and/or later developed technologies. Furthermore, the data recognition module 202 may utilize machine learning and pattern recognition methodologies to enhance the accuracy and robustness of the facial recognition process, enabling reliable identification even under varying environmental conditions and facial expressions.
[0026] In an embodiment of the present invention, the data segmentation module 204 may be configured to segment the recognized human faces into, one of categories. In an embodiment of the present invention, the recognized human faces are segmented into categories such as, but not limited to, a gender, an age group, a presence of accessories on the recognized human face, a presence of facial hair on the recognized human face, and so forth. Embodiments of the present invention are intended to include or otherwise cover any type of the categories including known, related art, and/or later developed technologies.
[0027] In an embodiment of the present invention, the data filter module 206 may be configured to filter the selected human face from one of the categories. This filtering mechanism may allow for a precise isolation of the target human face for ensuring that subsequent analysis and processing steps may focused solely on relevant facial data. The data filter module 206 may employ various criteria and thresholds specific to each category to accurately select the desired human face for enhancing the overall efficiency and accuracy of the face recognition system 100.
[0028] In an embodiment of the present invention, the data analysis module 208 may be configured to analyze features of the filtered human face. In an embodiment of the present invention, the analyzed features of the filtered human face may be, but not limited to, a contour of the human face, a crevice of the human face, and so forth. Embodiments of the present invention are intended to include or otherwise cover any type of the analyzed features including known, related art, and/or later developed technologies.
[0029] In an embodiment of the present invention, the data obtaining module 210 may be configured to obtain a covariance matrix from the analyzed features of the filtered human face. The covariance matrix captures the relationships between different features or variables, summarizing the variability and structure of the facial data.
[0030] In an embodiment of the present invention, the data calculation module 212 may be configured to calculate Eigen values, Eigen vectors, and Eigen faces for the obtained covariance matrix to obtain a distance. Eigen values and Eigen vectors represent the magnitude and direction of the principal components of the data, respectively, while Eigen faces are the derived principal components. These computations aid in reducing the dimensionality of the facial data and extracting discriminative features for facial recognition.
[0031] In an embodiment of the present invention, the data comparison module 214 may be configured to compare the distance with zero. This distance metric reflects the dissimilarity between the analyzed facial features and those present in the training set. By comparing this distance with zero, the module determines whether the facial features in the digital content match those in the training set, potentially triggering further steps in the recognition process.
[0032] In an embodiment of the present invention, the data match module 216 may be configured to match the human face in the digital content with the training set 108 of human faces to recognize the human face, if the distance is greater than zero. In an embodiment of the present invention, store the human face in the digital content in the training set 108 of human faces when none of the human faces in the training set 108 matches the human face in the digital content, and the calculated distance for the corresponding digital content is less than zero.
[0033] FIG. 3 depicts a flowchart of a method 300 for face recognition using the system 100, according to an embodiment of the present invention.
[0034] At step 302, the system 100 may receive the uploaded and/or the captured digital image from the user device 102.
[0035] At step 304, the system 100 may recognize the human face from the received digital image.
[0036] At step 306, the system 100 may segment the recognized human faces into, one of categories.
[0037] At step 308, the system 100 may filter the selected human face from one of the categories.
[0038] At step 310, the system 100 may analyze features of the filtered human face.
[0039] At step 312, the system 100 may obtain the covariance matrix from the analyzed features of the filtered human face.
[0040] At step 314, the system 100 may calculate Eigen values, Eigen vectors, Eigen faces, for the obtained covariance matrix to obtain the distance.
[0041] At step 316, the system 100 may compare the distance with zero. If the distance is greater than zero, then the method 300 may proceed to a step 318. Else, the method 300 may proceed to a step 320.
[0042] At step 318, the system 100 may match the human face in the digital content with the training set 108 of human faces to recognize the human face.
[0043] At step 320, the system 100 may store the human face in the digital content in the training set 108 of human faces when none of the human faces in the training set 108 matches the human face in the digital content.
[0044] 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 scope of the appended claims.
[0045] 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:CLAIMS
We Claim:
1. A face recognition system (100) through Principal Component Analysis (PCA) algorithm, the system (100) comprising:
a user device (102) adapted to upload and/or capture a digital image;
a processor (104), characterized in that the processor (104) is configured to:
receive the uploaded and/or the captured digital image from the user device (102);
recognize a human face from the received digital image;
segment the recognized human faces into, one of categories;
filter the selected human face from one of the categories;
analyze features of the filtered human face;
obtain a covariance matrix from the analyzed features of the filtered human face;
calculate Eigen values, Eigen vectors, Eigen faces, for the obtained covariance matrix to obtain a distance;
compare the distance with zero; and
match the human face in the digital content with the training set (108) of human faces to recognize the human face, when the distance is greater than zero.
2. The system (100) as claimed in claim 1, wherein the processor (104) is configured to store the human face in the digital content in the training set (108) of human faces when none of the human faces in the training set (108) matches the human face in the digital content, and the calculated distance for the corresponding digital content is less than zero.
3. The system (100) as claimed in claim 1, wherein the recognized human faces are segmented into categories selected from a gender, an age group, a presence of accessories on the recognized human face, a presence of facial hair on the recognized human face, or a combination thereof.
4. The system (100) as claimed in claim 1, wherein the analyzed features of the filtered human face is selected from a contour of the human face, a crevice of the human face, or a combination thereof.
5. The system (100) as claimed in claim 1, wherein the training set (108) of the human faces is stored in a database (106).
6. The system (100) as claimed in claim 1, wherein the training set (108) contains 400 digital content of 40 different human faces.
7. The system (100) as claimed in claim 1, wherein the digital content is an image.
8. A method (300) for face recognition system (100) through Principal Component Analysis (PCA) algorithm, the method (300) is characterized by steps of:
receiving uploaded and/or the captured digital image from a user device (102);
recognizing a human face from the received digital image;
segmenting the recognized human faces into, one of categories;
filtering the selected human face from one of the categories;
analyzing features of the filtered human face;
obtaining a covariance matrix from the analyzed features of the filtered human face;
calculating Eigen values, Eigen vectors, Eigen faces, for the obtained covariance matrix to obtain a distance;
comparing the distance with zero; and
matching the human face in the digital content with the training set (108) of human faces to recognize the human face, when the distance is greater than zero.
Date: May 20, 2024
Place: Noida

Dr. Keerti Gupta
Agent for the Applicant
(IN/PA-1529)