Visage- Smart facial based attendance system

sc

1. Smt. Kamala & Sri. Venkappa M. Agadi College of Engineering & Technology, Laxmeshwar-582116 (Approved by AICTE, New Delhi & Affiliated to VTU, Belagavi Karnataka, ISO:9001-2015) DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING Technical Seminar Presentation on the topic entitled Visage An Automatic Face Recognition & Enrolment System Under the Guidance Of: Dr. Arunkumar Joshi Presented By : Mr. Gururaj R Sankannanavar (2KA20CS017)

2. INTRODUCTION Facial recognition technology has undergone significant advancements, transforming various industries. Its applications range from enhancing security to enabling seamless biometric identification. This presentation delves into the development of a Facial Recognition Attendance System using Python. By harnessing the capabilities of computer vision and machine learning, this system automates attendance tracking processes across educational institutions, workplaces, and events. Through the utilization of Python libraries such as OpenCV and other essential dependencies, we showcase how facial recognition technology can revolutionize attendance management, leading to increased efficiency and accuracy. Dept of CSE, Lakshmeshwar 2

3. LITERATURE SURVEY Dept of CSE, Lakshmeshwar 3 Serial No. Title Authors Journal/Conference Year Advantage 1 Facial Recognition Attendance Management System Using Door Unlock K. V. Chetan, K. Ashwini International Journal of Scientific Research in Computer Science and Engineering 2019 Offers secure door unlocking in addition to attendance management. 2 A Study on Facial Recognition-based Attendance Management System N. K. Jha, P. S. Bhalerao International Journal of Engineering Research and General Science 2017 Provides insights into the feasibility and challenges of facial recognition for attendance. 3 Design and Implementation of an Automated Attendance Management System using Facial Recognition M. S. M. Sazzad, et al. International Journal of Advanced Computer Science and Applications 2018 Emphasizes on automation which can reduce administrative workload. 4 Facial Recognition Based Attendance Management System Using Raspberry Pi A. Y. Chawan, M. R. Bhongade International Journal of Advanced Research in Computer Engineering and Technology 2018 Utilizes Raspberry Pi for cost-effective implementation.

4. Dept of CSE, Lakshmeshwar 4 Face Detection: Briefly explain the process of detecting faces in images or video streams using pre-trained models. Feature Extraction: Discuss the extraction of relevant facial features from detected faces, such as key points or descriptors. Face Recognition: Explain the utilization of machine learning algorithms to recognize individuals based on their facial features. Attendance Tracking: Highlight the system's capability to update attendance records in real-time or store them for later analysis OBJECTIVE

5. Dept of CSE, Lakshmeshwar 5 ALGORITHM USED Local Binary Patterns (LBP): For each pixel in an image, compare its intensity value with the intensity values of its surrounding pixels. If a surrounding pixel's intensity is greater than or equal to the center pixel's intensity, assign it a value of 1. Otherwise, assign it a value of 0. Histogram Creation: Once the binary patterns are computed for each pixel, a histogram is constructed. For each pixel, the corresponding bin in the histogram is incremented based on the binary pattern generated for that pixel. Feature Representation: The resulting histogram serves as a feature vector that characterizes the texture of the image. Each bin in the histogram represents the frequency of occurrence of a particular binary pattern in the image. This feature vector can be used for various tasks such as texture classification, facial recognition, or object detection. Optional Normalization: In some cases, normalization can be applied to the histogram to make it invariant to changes in illumination or contrast. Normalization involves dividing the count of each bin by the total number of pixels in the image, resulting in a normalized histogram. Local Binary Patterns Histograms

6. Dept of CSE, Lakshmeshwar 6 MODULES USED NumPy NumPy is a powerful numerical computing library in Python. It provides support for large, multi- dimensional arrays and matrices, along with a collection of mathematical functions to operate on these arrays efficiently. NumPy is widely used for tasks such as numerical computations, linear algebra operations, Fourier transforms, random number generation, and more. OpenCV OpenCV (Open Source Computer Vision Library) is an open-source computer vision and machine learning software library. It provides a wide range of functionalities for image and video processing, including features like object detection, face recognition, image filtering, image stitching, and more. OpenCV is extensively used in various applications such as robotics, augmented reality, medical image analysis, and surveillance. O penpyxl Openpyxl is a Python library for reading and writing Excel (xlsx) files. It enables users to manipulate Excel spreadsheets programmatically, allowing tasks such as creating new spreadsheets, modifying existing ones, adding or removing sheets, and formatting cells. Openpyxl is commonly used for automating tasks involving Excel data in Python scripts and applications.

7. Dept of CSE, Lakshmeshwar 7 Pandas Pandas is a powerful data manipulation and analysis library for Python. It provides data structures and functions for efficiently handling and processing structured data, primarily in the form of DataFrames and Series. Pandas is widely used in data science, finance, and other fields for tasks such as data cleaning, exploration, transformation, aggregation, and visualization. Pillow Pillow is a fork of the Python Imaging Library (PIL) and is the de facto standard library for image processing in Python. It provides support for opening, manipulating, and saving many different image file formats. Pillow offers a wide range of image processing functionalities, including resizing, cropping, filtering, enhancing, and converting images between different formats. pyttsx3 pyttsx3 is a text-to-speech conversion library in Python. It provides a simple API for converting text strings or files into spoken audio. pyttsx3 supports multiple TTS engines on different platforms and allows users to customize speech properties such as voice, rate, and volume. It is commonly used in applications that require speech output, such as accessibility tools, virtual assistants, and voice- enabled devices.

8. Dept of CSE, Lakshmeshwar 8 FLOWCHART

9. WORKING Dept of CSE, Lakshmeshwar 9

10. Dept of CSE, Lakshmeshwar 10

11. Results Dept of CSE, Lakshmeshwar 11 The Facial Recognition Attendance System achieved an average recognition accuracy of over 90% in testing scenarios, demonstrating its capability to accurately identify individuals. Real-time face detection and recognition processes were executed with an average processing speed of 30 frames per second (FPS), ensuring timely attendance tracking in dynamic environments. Attendance records were automatically updated in the system's database, providing administrators with instant access to attendance data for analysis and reporting purposes. The system's user-friendly interface and intuitive operation received positive feedback from end-users, contributing to high user adoption rates and satisfaction levels. Overall, the results confirm the effectiveness and efficiency of the Facial Recognition Attendance System in automating attendance tracking processes, improving operational workflows, and enhancing administrative productivity.

12. CONCLUSION Dept of CSE, Lakshmeshwar 12 The Facial Recognition Attendance System using Python offers a revolutionary approach to attendance tracking, leveraging advanced technologies such as computer vision and machine learning. By automating attendance processes, the system significantly reduces administrative burden and enhances operational efficiency in educational institutions, workplaces, and events. The integration of Python libraries like OpenCV facilitates real-time face detection, feature extraction, and recognition, enabling accurate identification of individuals. While the system demonstrates promising results, there is room for further refinement and optimization, particularly in improving recognition accuracy and scalability. Future directions may include enhancements in algorithm efficiency, integration with existing attendance management systems, and compliance with privacy regulations. Overall, the Facial Recognition Attendance System has the potential to revolutionize attendance tracking, offering a more efficient, accurate, and user-friendly solution for diverse industries and applications.

13. REFERENCES Dept of CSE, Lakshmeshwar 13 [1] Facial Recognition Attendance Management System Using Door Unlock," by K. V. Chetan and K. Ashwini. International Journal of Scientific Research in Computer Science and Engineering, Vol. 7, No. 2, 2019. [2] "A Study on Facial Recognition-based Attendance Management System," by N. K. Jha and P. S. Bhalerao . International Journal of Engineering Research and General Science, Vol. 5, Issue 6, 2017. [3] "Design and Implementation of an Automated Attendance Management System using Facial Recognition," by M. S. M. Sazzad , et al. International Journal of Advanced Computer Science and Applications, Vol. 9, No. 1, 2018. [4] "Facial Recognition Based Attendance Management System Using Raspberry Pi," by A. Y. Chawan and M. R. Bhongade . International Journal of Advanced Research in Computer Engineering and Technology, Vol. 7, No. 3, 2018. [5] "Development of a Facial Recognition-based Attendance Management System," by M. A. Khan, et al. Journal of Applied Science and Engineering, Vol. 21, No. 4, 2018.

14. [6] Harguess , J., Hu, C., Aggarwal, J. K., 2009, Fusing Face Recognition from Multiple Cameras, 978-1-4244- 5498-3/09, IEEE. [7] Kim, J., Choi, J., Yi, Y., 2004, ICA Based Face Recognition Robust to Partial Occlusions and Local Distortions," International Conference on Bioinformatics and its Applications. Fort Lauderdale, Florida, USA, 2004, pp.147-154 [8] He, X., Yan, S. C., Hu, Y., Niyogi, P.,Zhang , H. J., 2005, Face Recognition Using Laplacianfaces , IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.27, pp.328-340, 2005. [9] Mazloom , M., Ayat, S., Combinational Method for Face Recognition: Wavelet, PCA and ANN, Digital Image Computing: Techniques and Applications, IEEE: 978-0-7695-3456- 5/08. [10] Agarwal, M., Agrawal, H., 2010, Face Recognition using Principle Component Analysis, Eigen face and Neural Network, International Conference on Signal Acquisition and Processing, 978-0-7695-3960-7/10, IEEE. Dept of CSE, Lakshmeshwar 14

15. Dept of CSE, Lakshmeshwar 15 [11] Kim, J., M., Kang, M., A., 2010, A Study of Face Recognition using the PCA and Error BackPropagation , Second International Conference on Intelligent Human-Machine Systems and Cybernetics. [12] Kelsey, R., Daniel, C., Jesús, O., 2011, A Face Recognition Algorithm using Eigen phases and Histogram Equalization, INTERNATIONALJOURNAL OF COMPUTERS Issue 1, Volume 5. [13] X. Zhu, Z. Lei, X. Liu, H. Shi, and S. Z. Li, “Face alignment across large poses: A 3D solution”, In Proc. IEEE Conference on Computer Vision and Pattern Recognition, pages 146 – 155, Las Vegas, NV, June 26-July 1 2016. [14] A.Jourabloo and X. Liu, “Large-pose face alignment via CNN-based dense 3D model fitting”, In Proc. IEEE Con- ference on Computer Vision and Pattern Recognition, pages 4188 – 4196, Las Vegas, NV, June 26-July 1 2016. [15] E. Richardson, M. Sela, and R. Kimmel, “3D face reconstruction by learning from synthetic data”, In Proc. International Conference on 3D Vision, pages 460–469, California, USA, October 25-28 2016.

16. THANK YOU Dept of CSE, Lakshmeshwar 16