SENSORY SIGHT : NEXTGEN DEVICE.

Abstract

ABSTRACT SENSORY SIGHT : NEXTGEN DEVICE Visually impaired individuals face significant challenges in their daily lives, particularly when navigating unfamiliar environments. The inability to perceive surroundings makes it difficult for them to move with confidence, and current assistive tools often fall short in providing comprehensive support. This lack of accessible information extends to educational and work environments, where visually impaired people struggle to access materials or use technology effectively. In India, the underrepresentation of visually impaired individuals in education, combined with the limited availability of resources like Braille books and audio content, has created a significant barrier to their participation in education and employment. Sensory Sight addresses these issues by presenting an innovative multifunctional assistive system aimed at enhancing the independence and safety of the visually impaired community. This system integrates text recognition, obstacle detection, and location-sharing features to tackle the various challenges faced by individuals with visual impairments. The primary objectives include developing a mobile application that utilizes image processing for effective text recognition, translating visual content into accessible audio or tactile feedback, and implementing obstacle detection capabilities to improve navigation safety. A panic button is also integrated, allowing for quick location sharing during emergencies by sending user coordinates to a dedicated website and triggering an email notification.

Specification

FORM 2
THE PATENTS ACT, 1970 (39 of 1970)
COMPLETE SPECIFICATION
(Section 10)
SENSORY SIGHT : NEXTGEN DEVICE
Applicant(s)
GAWAS NARAYAN DHAYABA
Nationality : Indian
Address: Sardar Patel Institute of Technology, Munshi Nagar, Bhavans Campus,
Andheri West, Mumbai 400058
GAUTAM SHRUTI KRISHNAVATAR
Nationality : Indian
Address: Sardar Patel Institute of Technology, Munshi Nagar, Bhavans Campus,
Andheri West, Mumbai 400058
GURAV SHREYA ANIL
Nationality : Indian
Address: Sardar Patel Institute of Technology, Munshi Nagar, Bhavans Campus,
Andheri West, Mumbai 400058
SONKUSARE REENA
Nationality : Indian
Address: Sardar Patel Institute of Technology, Munshi Nagar, Bhavans Campus,
Andheri West, MUMBAI 400058
COMPLETE SPECIFICATION
The following specification particularly describes the invention and the manner in which it is to be performed.

SENSORY SIGHT : NEXTGEN DEVICE
1. FIELD OF THE INVENTION:
The invention combines Assistive Technology, Internet of Things (IoT), Machine Learning, and Image Processing to create a multifunctional system specifically designed for visually impaired individuals. It integrates mobile applications with features like optical character recognition (OCR) for text-to-audio conversion, obstacle detection using sensors, and location-sharing through a panic button for emergency assistance. By leveraging IoT and machine learning, the system enhances accessibility, safety, and independence, providing real-time navigation support and improving access to information. This holistic solution empowers visually impaired users with greater autonomy in their daily lives.
2. OBJECT OF INVENTION:
The invention aims to develop a multifunctional assistive system that integrates text recognition, obstacle detection, and location tracking to empower visually impaired individuals. It provides real-time audio or tactile feedback by converting visual information into accessible formats, allowing users to read text from their environment. The system enhances safety through obstacle detection, alerting users to nearby hazards within a 2-meter range, while a panic button enables real-time location sharing in emergencies by transmitting GPS coordinates to designated contacts. This comprehensive solution promotes independence, safety, and accessibility for visually impaired users.

3. BACKGROUND OF THE INVENTION:
a) Visually impaired individuals encounter numerous challenges in their daily lives, particularly when it comes to navigating unfamiliar environments and accessing information crucial for their independence. The inability to see obstacles, read signs, or interact with visual content creates significant barriers, making even simple tasks daunting. Everyday activities like crossing streets, locating buildings, and reading printed material can transform into complex hurdles without proper assistance. While assistive tools such as canes, Braille, and audio guides have been developed to help mitigate these challenges, many of these solutions are limited in scope and cannot provide the real-time, comprehensive feedback that users need to navigate effectively.
b) Additionally, the lack of integration between different assistive devices means that individuals often rely on multiple tools, which complicates their mobility and access to vital information. This fragmentation can lead to a sense of dependency and insecurity, further affecting their confidence and autonomy. The evolving digital landscape only amplifies these challenges, as most of the information in daily life is predominantly visual and difficult to access without specific technology. Thus, there is an urgent need for innovative solutions that can address these gaps and enhance the quality of life for visually impaired individuals.
Given these challenges, the development of an integrated system that utilizes mobile devices, optical character recognition (OCR), and GPS technology provides a comprehensive assistive tool that promotes independence and safety for visually impaired individuals.

4. BRIEF DESCRIPTION OF THE DRAWINGS:
Figure 1. provides the Operational Flow Diagram of the invention. This figure illustrates a system with three operational modes: ultrasonic sensor, text recognition, and panic button, each performing distinct tasks like object detection, text-to-speech conversion, and emergency alerts.
Figure 2. provides the System's Circuit Diagram. This figure describes in detail the connection between different components of the system.
Figure 3. provides the Receiver Side Software System Diagram. This figure describes in detail the Data flow on the receiver side, in order to generate the final received output on the screen.
Figure 4 provides the visual look of the system Prototype.
Figure 5 provides the visual look of the system's Application Prototype
5. DETAILED DESCRIPTION OF THE DRAWINGS:
Figure 1: System Diagram
1. Mode Selection: Users can choose between three modes of operation: Ultrasonic Sensor, Text Recognition, or Panic Button.
2. Mode 1: Ultrasonic Sensor:
c Activate Sensor Feature: Engages the ultrasonic sensor for distance detection. o Object Distance Detection: Measures the distance to nearby objects using
ultrasonic technology. o Buzzer Alert: Triggers an auditory alert if objects are detected within a
specified distance.

3. Mode 2: Text Recognition:
o Enable Camera: Activates the camera to capture text. o Text Recognition: Processes the captured image to extract textual data. o To Speaker: Sends the recognized text to an audio output device for vocalization.
4. Mode 3: Panic Button:
o Locate Coordinates: Retrieves GPS coordinates for the user's current location. o Display on Website: Shows the user's coordinates on a website interface. o Send Alert: Dispatches an emergency alert containing the user's location information.
5. End Process: After performing the desired mode operation, the system concludes
the current session.
Figure 2: Hardware Setup Diagram
1. Raspberry Pi Module: The central processing unit that controls and processes inputs from various connected components.
2. Power Supply Module: Provides necessary power to the Raspberry Pi and the connected components for operation.
3. Ultrasonic Sensor Module: Measures the distance to nearby objects by emitting ultrasonic waves and receiving the reflected signal, connected to the Raspberry Pi for input data processing.
4. Button Modules: Two push buttons are connected to the Raspberry Pi, functioning as manual input devices to trigger specific operations.
5. Buzzer Module: Produces an auditory alert based on input signals received from the Raspberry Pi, typically used for proximity warnings or notifications.
6. Wiring Setup: Various components (sensor, buttons, and buzzer) are connected to the Raspberry Pi through colored wires, each corresponding to specific GPIO (General Purpose Input Output) pins for power, ground, and data transmission.

Figure 4 : System Prototype
Figure 4 illustrates the hardware setup of the prototype, showing the placement of essential modules on the Raspberry Pi setup. The key components include the Raspberry Pi (central processor), Ultrasonic Sensor for object detection, Push Buttons for manual input, and a Buzzer for alert notifications. All components are wired to the Raspberry Pi through a well-organized circuit, powered by an external power supply.
Figure 5 : System Application
Figure 5 shows the prototype of the system's application interface. The application allows users to interact with the system's features.
6. DESCRIPTION OF THE INVENTION:
The invention of Sensory Sight device presents an integrated system that combines advanced text recognition, location tracking, and obstacle detection capabilities to enhance user safety, situational awareness, and accessibility. The system employs state-of-the-art technologies, seamlessly connecting a mobile application, a dedicated server, and hardware components like Raspberry Pi to deliver a robust solution. The core of the system is built around three key features.
The text recognition functionality is powered by a sophisticated mobile application that enables users to capture images. Once an image is captured, it is transmitted to a dedicated server, which channels the data to a Raspberry Pi device. Utilizing the PyTesseract library, the system performs optical character recognition (OCR) with high

accuracy and speed, ensuring that essential text information is extracted from images in real time. This feature greatly benefits users who need to quickly process and understand textual data from their surroundings.
The location tracking feature leverages the enhanced GPS capabilities of the mobile app to accurately collect and transmit user location data. These GPS coordinates are sent securely to a server, where they are validated and stored. The server also powers an intuitive website that displays the location data in real time using the Google Maps API. This dynamic visualization provides users or designated recipients with a user-friendly interface to monitor movements and track location. In addition, the system includes a panic button feature, which allows users to send their precise location to a nominated contact during emergencies. This feature has been rigorously tested through a comprehensive survey that cross-referenced reported GPS coordinates with Google Maps data to validate the accuracy and reliability of the system.
To further enhance user safety, the invention integrates ultrasonic sensors connected to the Raspberry Pi for obstacle detection. These sensors feed real-time data into a dedicated algorithm that interprets the surrounding environment and alerts users to potential obstacles. This feature is particularly useful for individuals who need assistance navigating physical spaces or for situations where spatial awareness is critical, contributing significantly to overall safety.
The strength of the system lies in the seamless integration of these three features-text recognition, location tracking, and obstacle detection-into a cohesive and efficient platform. The design ensures that from image capture to location visualization and obstacle detection, the components work harmoniously to provide a synchronized and user-centric experience. A detailed block diagram visually represents the interactions

between the mobile application, Raspberry Pi, server, and website, showcasing the efficiency and synergy of the system architecture.
The user experience has been carefully crafted to ensure that both the mobile application and the website offer intuitive, easy-to-use interfaces. The website efficiently receives, processes, and displays real-time location data, ensuring that users can rely on it for accurate and timely information. The system has undergone thorough testing to confirm its reliability. The panic button feature, in particular, has been tested across various conditions, ensuring that location reporting is precise and consistent. The combination of cutting-edge technology and user-focused design makes this invention a comprehensive solution for diverse safely and accessibility needs.
7. SUMMARY OF INVENTION:
This invention is an integrated system combining text recognition, location tracking, and obstacle detection to enhance user safety and situational awareness. Using a mobile app, images are captured and sent to a server, which processes the data on a Raspberry Pi using the PyTesseract library for accurate optical character recognition (OCR). The app also collects GPS coordinates, transmitting them to a server for real-time visualization on a website powered by the Google Maps API. This system includes a panic button that sends precise location information during emergencies, ensuring reliable and responsive tracking. Additionally, the system incorporates ultrasonic sensors connected to a Raspberry Pi for obstacle detection, alerting users to nearby hazards. These three features are seamlessly integrated, providing a comprehensive and synchronized user experience. The entire setup has been tested rigorously to ensure accuracy, particularly in location tracking, making it a reliable and efficient solution for various safety and accessibility needs.

CLAIMS
SENSORY SIGHT : NEXTGEN DEVICE We Claim,
1. A location tracking system with emergency response capabilities, the
system comprising:
(a) a panic button feature enabling users to send their precise location to designated contacts during emergencies;
(b) an alert mechanism that dispatches an email containing the user's current coordinates to the contact person.
wherein the system ensures rapid emergency assistance by providing exact location data.
2. The location tracking system of claim 1, further comprising:
(a) a mobile application that retrieves user GPS coordinates;
(b) a server to validate and store location data;
(c) a website interface displaying the user's location in real-time using Google Maps API.
wherein the system allows for real-time monitoring of user location, enhancing user safety.
3. An Optical Character Recognition based text recognition system for
visually impaired users, the system comprising:
(a) a mobile application that captures and transmits images to a dedicated server;
(b) a processing unit using PyTesseract for optical character recognition (OCR) to convert text from images to audio;
(c) an audio output device such as earphones connected to Raspberry Pi that vocalizes recognized text.
wherein the system allows users to convert textual information into audio output for immediate accessibility.
4. The text recognition system of claim 3, wherein the processing unit provides real-time text-to-audio conversion, allowing visually impaired users to interpret and understand text from their environment promptly.
5. An obstacle detection system for visually impaired individuals, the system comprising:

(a) an ultrasonic sensor integrated with a Raspberry Pi for real-time environment scanning;
(b) a buzzer that provides auditory alerts when obstacles are detected within a pre-set range.

wherein the system warns users of nearby hazards, enhancing navigation safety in real-world environments. 6. The obstacle detection system of claim 5, wherein the ultrasonic sensor accurately measures object distances and triggers alerts for objects detected within a pre-set range, providing immediate feedback to users.

Documents