Artificial Intelligence Depended Security Providence by IORT

6220 words (25 pages) Essay

8th Feb 2020 Computer Science Reference this

Tags:

Disclaimer: This work has been submitted by a university student. This is not an example of the work produced by our Essay Writing Service. You can view samples of our professional work here.

Any opinions, findings, conclusions or recommendations expressed in this material are those of the authors and do not necessarily reflect the views of UKEssays.com.

ARTIFICIAL INTELLIGENCE DEPENDED SECURITY PROVIDENCE BY IORT

ABSTRACT

In robotics, vision is the primary source to identify an object or person in automobiles especially detecting pedestrians, traffic signals and other nearby cars with distance. Therefore, machine vision has more prominence in companies and customers need. Object identification during harsh or extreme weather/temperatures or in highly populous streets has become a major concern in modern day business models. This is an automatically organizing visual environment. But, it is not up to the mark in the real-world applications. For example, many object identification algorithms are just used to identify objects/faces from group pedestrians in a video file. Like, we are tracing some object identification algorithms in video processing mode that helps to tag in social networking sites. But it only suggests that whether it is the object or face you know and will not confirm. So, this requires a solution of not only tracing the general pedestrians but to suggest the different objects in their path.

CHAPTER1INTRODUCTION

1.1 Background

1.2  

Machine vision helps in observing process production safety, For example human couldn’t stay at high temperature that will even make them to death. So, to reduce the effect of human moment at restricted zones machine visions will do the rest [1].

This even helps in emotional analysis and face, gender and object classification [2]. This is now mostly used in social networking sites.

1.3 Significance

Various algorithms were proposed for computer/machine vision. Object identification and recognition of various objects where human eye cannot see, or reach has become a challenge. Therefore, on behalf of human vision, artificial intelligence dependent IoRT computer vision / robotics with high accuracy object identification model will be used. This can be used in various industries and can be implemented for Process and production safety, material safety, fire safety and environmental safety.

1.4 StatementofProblem

“AI Depended Security Providence by IORT” uses computer vision for object identification. In computer vision, high lighting or different textures of objects make the object identification difficult. And current systems identify only one type of objects but not all with in the image. To overcome these difficulties, we are implementing a high accuracy object identification model using SVM (Support Vector Machine) and SIFT (Scale Invariant Feature Transform) algorithms which identify all the objects within the image.

1.4ResearchQuestions

This proposal will answer the following questions:

  • What is Machine Vision?
  • How machine vision related IoRT?
  • How many ways machine vision can be accessed?
  • How machine vision of IoRT is implemented?

1.5Objectives

This project proposal will try to cover the following:

•         Gathering the image data.

•         Extracting the image features data

•         To find the best possible features subtract the feature from background.

•         Recognition of Image.

•         Classification

1.6Delimitations

This project proposal will not include:

  • Object detection and identification needs a serious attention
  • Time of detection need to be reduced
  • Object Identification and other needs to be detected in a each frame
  • Semi supervisory algorithm needs to be followed

CHAPTER2

REVIEWOFRELATEDLITERATURE

An image-based process control or automatic inspection or robot guidance usually in an industry that helps to classify the object through computer vision algorithms and machine learning algorithms is known as Machine Vision. Some applications under this section are image based automatic inspection and sorting and the next is a real time world application i.e., Robot guidance in this section automatic driving cars widely use this application. This is also used in medical appliances, virtual world of shopping for direct trail room not using physical dresses.

Machine vision helps in observing process production safety, for example human couldn’t stay at elevated temperature that will even make them to death. So, to reduce the effect of human moment at restricted zones, machine vision will do the rest [1].This even helps in emotional analysis, face, gender and object classification [2]. This is now mostly used in social networking sites.

Important aspects of vision systems in robotic applications, are the simplicity of the algorithm, the low cost and the reduced need for maintenance, while aspects such as the fast and effective identification still constitutes an unsolved problem. Even though adequately efficient and accurate algorithms have been developed, the processing speed still fails to meet the modern manufacturing requirements [1]. The problem becomes further complicated owing to the objects’ properties, such as shape, material, color, etc. Additionally, the requirements for simplicity and low cost are directly connected to the production rate that is expected to be increased with the introduction of robotic equipment in modern production lines [2]. The need for objects’ recognition systems is met in multiple industrial applications, where different objects of variable shapes and sizes should be handled. An example of such an application is the consumer goods industry. This sector lacks in flexible, low cost and simple automation solutions that will eventually cope with high production rates and a variety of products. Currently, the high-speed feeding and handling of objects imposes the need for dedicated equipment, namely feeder bowls. Such solutions are characterized as noisy, expensive and are dedicated to product specific equipment. Specifically, feeder bowls cannot perform in more than one product, whilst for new products need redesigning. The sensor technologies extended reviews trends for assembly systems shown vision systems are best for objects’ recognition and robot handling applications [3,8]. Vision-based robot control is investigated in [9,1, 4], while a survey on the visual serving systems is presented in [1,5,7]. Research has been done in the design aspects of the machine vision systems for industrial applications [8] and has led to improvements in reliability and product quality [1,9]. The vision system classification was investigated in [1-7]. The pattern recognition method has also been investigated in [4,8,9], while 3D vision systems have been presented in [3,8]. Such systems have the advantages of recognizing the objects’ characteristics, but they are based on complicated algorithms and are prompt to failures in industrial environments. Methods for errors measurement in vision systems have been researched in [9], while techniques for the classification of objects and point descriptors are designated in [4]. Histogram-based image descriptors have been evaluated for the classification of 3D objects [5], while a comparison between the methods of local and full ranking point descriptors was reported in [6,7].

 

 

 

 

 

 

 

 

 

 

 

 

 CHAPTER3

 METHODOLOGY

 3.1Design

This object identification model starts with basic image processing techniques and principles, via the combination of algorithms for object detection. Firstly, for image trained Data base. We need to have Individual image for data backup and extraction of each object from image and using SIFT algorithm to know/identify object shape, length, rotational angel, texture of object image and training them using Multiclass SVM to detect and classify the object of type. This creates model [image trained] database.

SIFT algorithm extracts various objects from transmitted images. In SIFT training process, i.e. object extraction we convert the images to binary format and then we will be subtracting the subsequent background of image to identify various objects. Then the features of individual objects extraction are analyzed and classified in to diverse groups using SVM. In other words, Gaussian Distribution Based Multiclass SVM calculates the distance between extracted features samples/object with trained samples from databases. Finally, Object tag classification will be provided automatically without any human interaction.

Coming to real-time scenario, the test image will be provided as input to object extraction and SIFT algorithm which extracts the features of different objects in the image. Once the objects are extracted, they are fed to SVM in a linear combination of all objects in image. In SVM, based on binary data of object, it identifies to which category the object belongs by comparing it with the existing data and classifies it accordingly.

Finally, “Artificial Intelligence Depended Security Providence By IORT” is that we integrate Robot with Internet of things which sends the image after object classification to the respective organization/individual with encryption to avoid data loss. For instance, Industries with multiple machineries, this Robotic process handle Security of the equipment. In case of failure, the robotic captures the images of various parts and classifies them accordingly and perform tasks to avoid large system failure.

3.2Resources

In order to complete to proceed any further in the project, there are certain resources required.

•         Software-Python with OpenCV or MATLAB

•         Windows OS

•         Hardware- I3 and above

•         Laptop or System

3.3Timeline

TASKS

YEAR / MONTH

2018

2019

AUG

SEP

OCT

NOV

DEC

JAN

FEB

MAR

APR

Selecting a research topic

 

 

 

 

 

 

 

 

Selection of Committee members

 

 

 

 

 

 

 

 

Submitting the topic

 

 

 

 

 

 

 

 

Begin the review of related literature

 

 

 

 

 

 

 

 

Developing the dissertation document

 

 

 

 

 

 

 

 

Submit the draft of document

 

 

 

 

 

 

 

 

Presenting the topic to committee members

 

 

 

 

 

 

 

 

Continue review of related literature

 

 

 

 

 

 

 

 

Getting the Images

 

 

 

 

 

 

 

 

Extracting the data data

 

 

 

 

 

 

 

 

Creating the test database

 

 

 

 

 

 

 

 

Recognition of Image using SIFT

 

 

 

 

 

 

 

 

classifying using SVM

 

 

 

 

 

 

 

 

Visualizing the complete database and Object recognition model

 

 

 

 

 

 

 

 

Work on the final document

 

 

 

 

 

 

 

 

Submitting the final document

 

 

 

 

 

 

 

 

Defend the Thesis

 

 

 

 

 

 

 

 

References:

[1] Kodagali, J., Balaji, S., 2012, Computer Vision and Image Analysis Based Techniques for Automatic Characterization of Fruits – A Review, International Journal of Computer Applications, 50/6: 6–12.

[2] Chryssolouris, G., 2006, Manufacturing Systems: Theory and Practice, Springer.

[3] Santochi, M., Dini, G., 1998, Sensor Technology in Assembly Systems, CIRP Annals – Manufacturing Technology, 503–524. http://dx.doi.org/10.1016/ S0007-8506(07)63239-9.

[4] To¨ nshoff, H.K., Janocha, H., Seidel, M., 1988, Image Processing in a Production Environment, CIRP Annals – Manufacturing Technology, 579–590. SURF features extraction. P. Tsarouchi et al. / CIRP Journal of Manufacturing Science and Technology 14 (2016) 20–2726

[5] Michalos, G., Makris, S., Eytan, A., Matthaiakis, S., Chryssolouris, G., 2012, Robot Path Correction Using Stereo Vision System, Procedia CIRP, 352–357

[6] Vahrenkamp, N., Bo¨ ge, C., Welke, K., Asfour, T., Walter, J., et al, 2009, Visual Servoing for Dual Arm Motions on a Humanoid Robot, 9th IEEE-RAS International Conference on Humanoid Robots, HUMANOIDS09, pp.208–214.

[7] Han, S.H., See, W.H., Lee, J., Lee, M.H., Hashimoto, H., 2000, Image-Based Visual Servoing Control of a SCARA Type Dual-Arm Robot, ISIE’2000. Proceedings of the 2000 IEEE International Symposium on Industrial Electronics (Cat. No. 00TH8543),

[8] Han, S.H., Choi, J.W., Son, K., Lee, M.C., Lee, J.M., et al, 2001, A Study on Feature- Based Visual Servoing Control of Eight Axes-Dual Arm Robot by Utilizing Redundant Feature, in: Proceedings 2001 ICRA. IEEE International Conference on Robotics and Automation (Cat. No.01CH37164), vol. 3

[9] Hutchinson, S., Hager, G.D., Corke, P.I., 1996, A Tutorial on Visual Servo Control, IEEE Transactions on Robotics and Automation, 12/5: 651–670.

Cite This Work

To export a reference to this article please select a referencing stye below:

Reference Copied to Clipboard.
Reference Copied to Clipboard.
Reference Copied to Clipboard.
Reference Copied to Clipboard.
Reference Copied to Clipboard.
Reference Copied to Clipboard.
Reference Copied to Clipboard.

Related Services

View all

DMCA / Removal Request

If you are the original writer of this essay and no longer wish to have your work published on the UKDiss.com website then please:

Related Lectures

Study for free with our range of university lectures!