Abstract: Human face matching across varying poses remains a significant challenge in the field of computer vision, particularly in applications such as security, identity verification, and surveillance. Traditional face recognition systems often struggle with pose variations, leading to reduced accuracy and unreliable identification. This project presents a Deep Learning-based multi-pose human face matching system that leverages the YOLO-V5 (You Only Look Once) algorithm for efficient and accurate face detection and recognition across multiple poses. The proposed system is designed to identify and match faces in diverse orientations, including frontal, left, right, downward, and upward poses, ensuring robust performance even under challenging viewing conditions such as variations in lighting, facial expressions, and occlusions. MATLAB is utilized for image preprocessing, including noise reduction, contrast enhancement, and feature extraction, preparing the input images for the deep learning model. The YOLO-V5 algorithm is integrated into the system to perform real-time face detection and recognition, significantly improving processing speed and accuracy. A deep learning model is trained on a comprehensive dataset comprising multi-pose facial images, allowing the system to enhance recognition accuracy and overcome pose-based challenges. The adaptability of this approach makes it suitable for various real-world applications, such as facial authentication systems, public security surveillance, and automated access control.
Description:Description of the Invention:
Face recognition technology has become an essential component in various modern applications, including security, surveillance, and authentication systems. With the increasing need for secure and efficient identification methods, face recognition has been widely adopted in domains such as law enforcement, access control, financial transactions, and public safety monitoring. Traditional face recognition models have demonstrated high accuracy in controlled environments; however, they often struggle with real-world scenarios where factors such as pose variations, lighting conditions, occlusions, and facial expressions significantly impact performance. Among these challenges, pose variation remains one of the most critical factors affecting recognition accuracy, as many systems are primarily trained on frontal facial images and fail to generalize well across different orientations, To overcome these limitations, this project presents a Deep Learning-Based Multi-Pose Human Face Matching System that utilizes the YOL0-V5 (You Only Look Once) algorithm for robust and efficient face detection and recognition. The system is specifically designed to handle multi-pose facial recognition, ensuring accurate identification across different orientations, including frontal, left, right, downward, and upward poses. By leveraging deep learning techniques and real-time object detection, this approach enhances the adaptability and reliability of face matching, even in challenging scenarios where individuals may not be directly facing the camera
The Proposed system is designed to identify and match human faces across multiple poses using deep learning techniques. The core components include face detection, pose classification, and face matching using the YOLO-V5 algorithm and MATLAB image processing tools. The system is designed to handle the challenge of matching faces captured from different angles (multi-pose). Utilize MATLAB's Image Processing for initial image handling and image pre processing, feature extraction, and interfacing with the deep learning model. Preprocess the images to enhance detection accuracy by resizing, normalizing, and possibly augmenting the input data with techniques like flipping and rotation. Apply image filtering and transformation to reduce noise and improve face detection YOLO-V5 allows for real-time detection and pose classification, enabling applications in surveillance and identity verification. Classify each detected face based on its pose (front, left, right, down, or up) using the output of the YOLO-V5 algorithm. A deep learning model is trained on a dataset comprising diverse facial orientations, improving the system's ability to recognize and match faces regardless of head position. To further enhance usability, an Arduino Uno microcontroller is incorporated alongside an APR voice module and a speaker to provide real-time voice updates about the recognition results. This feature enables an interactive and accessible system suitable for automated access control, public security, and smart authentication applications.
Hardware Requirements
Power Supply:
Power supply is a reference to a source of electrical power. A device or system that Supplies electrical or other types of energy to an output load or group of loads is called a Power supply unit or PSU. The term is most commonly applied to electrical energy supplies, Less often to mechanical ones, and rarely to others. Power supplies for electronic devices can be broadly divided into linear and Switching power supplies. The linear supply is a relatively simple design that becomes Increasingly bulky and heavy for high current devices; voltage regulation in a linear supply Can result in low efficiency. A switched-mode supply of the same rating as a linear supply Will be smaller, is usually more efficient, but will be more complex. An AC powered linear power supply usually uses a transformer to convert the Voltage from the wall outlet (mains) to a different, usually a lower voltage. If it is used to Produce DC, a rectifier is used. A capacitor is used to smooth the pulsating current from the Rectifier. Some small periodic deviations from smooth direct current will remain, which is Known as ripple. These pulsations occur at a frequency related to the AC power frequency (for example, a multiple of 50 or 60 Hz). The voltage produced by an unregulated power supply will vary depending on the Load and on variations the AC supply voltage. For critical electronics applications a linear Regulator will be used to stabilize and adjust the voltage. This regulator will also greatly Reduce the ripple and noise in the output direct current. Linear regulators often provide Current limiting, protecting the power supply and attached circuit from over current. Adjustable linear power supplies are common laboratory and service shop test Equipment, allowing the output voltage to be set over a wide range. For example, a bench Power supply used by circuit designers may be adjustable up to 30 volts and up to 5 amperes Output. Some can be driven by an external signal, for example, for applications Requiring a pulsed output.
ESP32 is a series of low-cost, low-power system on a chip microcontrollers with Integrated Wi-Fi and dual-mode Bluetooth. The ESP32 series employs either A Ten silica XtensąLX6 microprocessor in both dual-core and single-core variations, XtensaLX7 dual-core microprocessor or a single-core RISC-V microprocessor and includes built- In antenna switches, RF balun , power amplifier, low-noise receive amplifier, filters, and Power- management modules. ESP32 is created and developed by Express if Systems, a Shanghai- based Chinese company, and is manufactured by TSMC using their 40 nm Process. It is a successor to the ESP8266 microcontroller.
The APR9600 device, offers true single-chip voice recording, non-volatile storage, and Playback capability for 40 to 60 seconds The device supports both random and sequential access of Multiple messages. Sample rates are user-selectable, allowing designers to customize their design for Unique quality and storage time needs. Integrated output amplifier, microphone amplifier, and AGC Circuits greatly si mplify, system design. The device is ideal for use in portable voice recorders, toys, And many other consumer and industrial applications. APLUS integrated achieves these high levels of storage capability by using its proprietary Analog/multilevel storage technology implemented, in an advanced Flash non-volatile memory Process, where each memory cell can store 256 voltage levels. This technology enables the APR9600 Device to reproduce voice signals in their natural form. It eliminates the need for encoding and Compression, which often introduce distortion.
The Arduino Integrated Development Environment – or Arduino Software (IDE) – contains a Text editor for writing code, a message area, a text console, a toolbar with buttons for common Functions and a series of menus. It connects to the Arduino and Genuino hardware to upload Programs and communicate with them. Programs written using Arduino Software (IDE) are called sketches. These sketches are written In the text editor and are saved with the file extension .ino. The editor has features for Cutting/pasting and for searching/replacing text. The message area gives feedback while saving And exporting and also displays errors. The console displays text output by the Arduino Software (IDE), including complete error messages and other information. The bottom right hand corner Of the window displays the configured board and serial port. The toolbar buttons allow you to Verify and upload programs, create, open, and save sketches, and open the serial monitor. NB: Versions of the Arduino Software (IDE) prior to 1.0 saved sketches with the extension .pdf It is possible to open these files with version 1.0, you will be prompted to save the sketch with The .ing extension on save.
MATLAB:
MATLAB is a high-level language and interactive environment for numerical computation, Visualization, and programming. Using MATLAB, you can analyze data, develop algorithms, and create models and applications.
, C , C , Claims:We claim that,
• Enhances the overall robustness of the system
• Establishes a reliable framework in public safety, identity verification, and intelligent surveillance systems
• Efficient Energy Saving
| # | Name | Date |
|---|---|---|
| 1 | 202541043074-STATEMENT OF UNDERTAKING (FORM 3) [03-05-2025(online)].pdf | 2025-05-03 |
| 2 | 202541043074-REQUEST FOR EARLY PUBLICATION(FORM-9) [03-05-2025(online)].pdf | 2025-05-03 |
| 3 | 202541043074-FORM-9 [03-05-2025(online)].pdf | 2025-05-03 |
| 4 | 202541043074-FORM 1 [03-05-2025(online)].pdf | 2025-05-03 |
| 5 | 202541043074-DRAWINGS [03-05-2025(online)].pdf | 2025-05-03 |
| 6 | 202541043074-DECLARATION OF INVENTORSHIP (FORM 5) [03-05-2025(online)].pdf | 2025-05-03 |
| 7 | 202541043074-COMPLETE SPECIFICATION [03-05-2025(online)].pdf | 2025-05-03 |