Home Free Lab ReportsThis project helps in identifying the properties of an image which will be used to identify the nature of an image

This project helps in identifying the properties of an image which will be used to identify the nature of an image

This project helps in identifying the properties of an image which will be used to identify the nature of an image. This project includes in setting up a system where you can get SMS to your mobile or an email with an attachment file containing the photo of a person who has visited your house by using smartphone as IP-Camera, Raspberry Pi and a PIR sensor, Node-Red programming tool, Watson’s Visual recognition tool, and Twilio or SendGrid for Email service. Here an old smartphone is used as an IP-Camera. It is connected to a local network with the help of a Raspberry Pi which allows us to capture a snapshot at any moment when a motion occurs.” Decision of when to capture the snapshot is determined with the help of PIR sensor. We use Node-RED visual programming tool which takes the help of IBM Watson by making use of its services through nodes. IBM Watson’s visual recognition service firstly detects a face and the executes other command based on the response obtained from Watson”. Twilio or SendGrid are used in the project which allows us to send SMS to a number or multiple numbers that someone is at the door step and an email service which allows us to send an email containing the picture of the person visited the home
“Here, the complete image processing computations are done by Watson, and we set up Raspberry Pi which is connected to Bluemix IOT platform service and it doesn’t do any image processing. IBM Bluemix allows users to understand the content of images and classify images into logical categories”. For instance consider we upload the images for certain areas, we can create a custom classifier and can get crowded ratio which we will be used for finding routes and we can also find gender of people if number of people in image are comparatively less and that can also be used for increasing efficiency.

Intrusion Detection System is currently being able to sense the motion of objects and take a picture. The objects in the picture are identified and the user is alerted if there is a person in the picture. This existing setup can be used in cases where the user must leave their home for a long period of time. The device when setup and switched on, connects to the cloud provided to the user to manage all their devices. The activity of a device is stored in the cloud and the user can access it from remotely anywhere in the world. The proposed system helps in solving the problem of taking action against the intruder visiting the home when you are not available at home. It also helps the user to monitor their home remotely which increases the security of the users home with less expensive equipment unlike security cameras, storage devices etc. instead we just use email services, IBM cloud for storage and an old smart phone as an IP-Camera
The images which we get are not so accurate, we need to increase the quality of images by enhancing images. Basically, the idea behind enhancement techniques is to bring out detail that is obscured, or simply to highlight certain features of interest in an image. We use cloud IOT platforms like IBM Watson and messaging services like SendGrid or Node-RED and hence reducing the amount of Physical storage required and also increasing the overall performance of the system
With the increasing volume of users using internet there is a need for identifying certain attributes of the user so that data quality could be quite good. Images are now one of the key enablers of users connectivity. Accuracy of attribute information retrieved from images are quite low when compared to processing from Bluemix. The information can not only be used for identifying gender but also for predicting accidents in certain area, so before any accident happens we can predict it. The aggregated information can result in unexpected exposure of one’s social environment and lead to abuse of one’s personal information. The main aim is to collect the quality data and increase target marketing which will be used to reduce cost to a great extent
Existing systems tend to perform the face detection using complex systems like MATLAB and SIMULINK where the load on the required system is too high. It also requires us to install these software that are licensed on the Raspberry Pi which increases the storage capacity required on the Pi. To encounter these issues, we use cloud IOT platforms like IBM Watson and messaging services like SendGrid or Node-RED and hence reducing the amount of Physical storage required and also increasing the overall performance of the system. The proposed system helps in solving the problem of taking action against the intruder visiting the home when you are not available at home. It also helps the user to monitor their home remotely which increases the security of the users home with less expensive equipment unlike security cameras, storage devices etc. instead we just use email services, IBM cloud for storage and an old smart phone as an IP-Camera
The main aim of the project is to detect the intruder which includes in setting up a system where the users can get SMS to their mobile or an email with an attachment file containing the photo of a person who has visited their house by using smartphone as IP-Camera, Raspberry Pi and a PIR sensor, Node-Red programming tool, IBM Watson, and Twilio or SendGrid or Node-RED for Email service.

We Will Write a Custom Essay Specifically
For You For Only $13.90/page!


order now

Advantages: Provides user an opportunity to monitor the home remotely which increases the security. The system easy to setup and doesn’t use expensive equipment like security cameras, storage devices etcVarious techniques have been developed in Image Processing during the last four to five decades. Most of the techniques are developed for enhancing images obtained from unmanned spacecraft’s, space probes and military reconnaissance flights. Image Processing is a technique to enhance raw images received from cameras/sensors placed on satellites, space probes and aircrafts or pictures taken in normal day-to-day life for various applications. Image Processing systems are becoming popular due to easy availability of powerful personnel computers, large size memory devices, graphics software’s etc. The IBM Watson Visual Recognition service uses deep learning algorithms to analyze images (.jpg, or .png) for scenes, objects, faces, and other content, and return keywords that provide information about that content. Generally people are curious to know who had arrived at their doorstep when they were away from home and it would be good to receive a notification when someone arrives at the doorstep or if some activity is detected using image processing and some messaging service”.

Image Processing is a technique to enhance raw images received from cameras/sensors placed on satellites, space probes and aircrafts or pictures taken in normal day-to-day life for various applications. Image processing has changed warfare in the last decade with remote piloted drone aircrafts being able to get images which were transmitted and analysed remotely. We use Watson visual recognition for image processing.

Watson uses Deepqa which is a software architecture for deep content analysis and evidence-based reasoning that embodies that philosophy. The overarching principles in Deepqa are massive parallelism, many experts, pervasive confidence estimation, and integration of shallow and deep knowledge.

The first step in any application of Deepqa to solve a qa problem is content acquisition, or identifying and gathering the content to use for the answer and evidence sources. Content acquisition is a combination of manual and automatic steps. The first step is to analyse example questions from the problem space to produce a description of the kinds of questions that must be answered and a characterization of the application domain. Analyzing example questions is primarily a manual task, while domain analysis may be informed by automatic or statistical analyses. Given the kinds of questions and broad domain of the Jeopardy Challenge, the sources for Watson include a wide range of encyclopedias, dictionaries, thesauri, newswire articles, literary works, and so on.Given a reasonable baseline corpus, Deepqa then applies an automatic corpus expansion process. The process involves four high-level steps: (1) identify seed documents and retrieve related documents from the web; (2) extract self-contained text nuggets from the related web documents; (3) score the nuggets based on whether they are informative with respect to the original seed document; and (4) merge the most informative nuggets into the expanded corpus. The live system itself uses this expanded corpus and does not have access to the web during play.

In addition to the content for the answer and evidence sources, Deepqa leverages other kinds of semi structured and structured content. Another step in the content-acquisition process is to identify and collect these resources, which include databases, taxonomies, and ontologies, such as dbPedia, WordNet and the Yago ontology. The first step in the run-time question-answering process is question analysis. During question analysis the system attempts to understand what the question is asking and performs the initial analyses that determine how the question will be processed by the rest of the system. The DeepQA approach encourages a mixture of experts at this stage, and in the Watson system we produce shallow parses12,deep parses, logical forms, semantic role labels, co reference, relations, named entities, and so on, as well as specific kinds of analysis for question answering. Most of these technologies are well understood and are not discussed here, but a few require some elaboration. Question classification is the task of identifying question types or parts of questions that require special processing. This can include anything from single words with potentially double meanings to entire clauses that have certain syntactic, semantic, or rhetorical functionality that may inform downstream components with their analysis. Question classification may identify a question as a puzzle question, a math question, a definition question, and so on. It will identify puns, constraints, definition components, or entire sub clues within questions.

The images we capture from IP-Camera when a motion is detected should be highly contrasted so that we can have a better classification of images. Currently we are using images for classification purpose only, in future will try to make data prediction for the classified data from Bluemix which can make more productivity with less image processing
The report is organized in the following way. What follows is the literature review of the previous works in the image and data processing. Then, the design and setup of the system is explained. The details about implementation of the proposed image, data processing techniques are explained in the section after design. The results and discussion of the future works, and the conclusions drawn are all explained in the further sections
Existing systems tend to perform the face detection using complex systems like MATLAB and SIMULINK where the load on the required system is too high. It also requires us to install these software that are licensed on the Raspberry Pi which increases the storage capacity required on the Pi. To encounter these issues, we use cloud IOT platforms like IBM Watson and messaging services like SendGrid or Node-RED and hence reducing the amount of Physical storage required and also increasing the overall performance of the system.

The enhancements on this system use the likes of advanced and lightweight technologies that help in the easier detection of faces and also reduce the overall cost due to the use of Open Source Services that are widely available these days
Here in this module, we used a smartphone which acts as an IP-Camera which is controlled using Raspberry Pi where both smartphone and Raspberry pi are connected to the same local network(Router). Firstly, we used an application called IP Webcam where all we need to do is to be able to get an image from the camera at any instance
The PIR sensor is used for motion detection which is used in our project to capture snapshots from the IP-Camera only when activity is detected in front of the door. As soon as the image is captured using IP Webcam and then the digital status of the output pin of PIR sensor can be seen in Node Red page. When the motion is detected it sends a digital signal which is taken as an input to Raspberry Pi. As soon as a signal is detected , the flow in the Node-Red program halts for 5 seconds. The Visual Recognition services comes with a set of built-in classes so that you can analyse images with high accuracy right out of the box. You can also train custom classifiers to create specialized classes, and create custom collections to search for similar images. In this project, the visual recognition is done using IBM Watson. Here the image which is captured using IP Webcam is given as an input to IBM Watson and the result obtained by Watson’s analysis is displayed. Based on the result we can known if a person is detected in the image or if something else is detected in the image. Email can also act as a cloud storage which stores all the images captured using IP-Webcam. In this way we can avoid the problem of saving long duration video’s captured from the camera to detect activities. Images will be captured whenever a motion or activity is detected so there is no need to buy large capacity storage devices to save data. Here, we are using Twilio or SendGrid messaging service for emailing the image as a file to the user.

“Implementation is the stage of the project when the theoretical design is turned out into a working system. Thus it can be considered to be the most critical stage in achieving a successful new system and in giving the user, confidence that the new system will work and be effective. The implementation stage involves careful planning, investigation of the existing system and it’s constraints on implementation, designing of methods to achieve changeover and evaluation of changeover methods”.

Setting up Smartphone as IP Camera
Motion detection using PIR sensor
Visual recognition
Emailing service using TwilioHere in this module, we used a smartphone which acts as an IP-Camera which is controlled using Raspberry Pi where both smartphone and Raspberry pi are connected to the same local network(Router). Firstly, we used an application called IP Webcam where all we need to do is to be able to get an image from the camera at any instance.

The PIR sensor is used for motion detection which is used in our project to capture snapshots from the IP-Camera only when activity is detected in front of the door. As soon as the image is captured using IP Webcam and then the digital status of the output pin of PIR sensor can be seen in Node Red page. When the motion is detected it sends a digital signal which is taken as an input to Raspberry Pi. As soon as a signal is detected , the flow in the Node-Red program halts for 5 seconds.

x

Hi!
I'm Marcia!

Would you like to get a custom essay? How about receiving a customized one?

Check it out