1 / 4

Real Time Face Detection Security System using Haar Classifier Method

Face Detection is concerned with finding whether or not there are any faces in a given images. Security and surveillance are the two important aspects of human being. Face detection is very important because it is not being safe in human environment. So, Face Detection Security System is essential between individual in life. In the modern world everything is changed to provide a better life. So we were decided to develop the Real Time Face detection system. The importance of the face detection as it is essential for surveillance and real user interfaces security to the country. Face differ in skin colour, nose, eyebrows, chin between different people in humanity. In this paper we effort is to develop system about face detection security system in the real time. Ei Mon Phyo | Nay Win Zaw | Aye Aye Tun "Real-Time Face Detection Security System using Haar Classifier Method" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-2 | Issue-5 , August 2018, URL: https://www.ijtsrd.com/papers/ijtsrd18353.pdf Paper URL: http://www.ijtsrd.com/engineering/electronics-and-communication-engineering/18353/real-time-face-detection-security-system-using-haar-classifier-method/ei-mon-phyo<br>

Télécharger la présentation

Real Time Face Detection Security System using Haar Classifier Method

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. International Research Research and Development (IJTSRD) International Open Access Journal Face Detection Security System u Haar Classifier Method Ei Mon Phyo1, Nay Win Zaw2, Aye Aye Tun3 Assistant Lecturer, 2Professor,3Lecturer f Electronic Engineering, West Yangon Technological University, Myanmar angon Technological University, Myanmar International Journal of Trend in Scientific Scientific (IJTSRD) International Open Access Journal ISSN No: 2456 ISSN No: 2456 - 6470 | www.ijtsrd.com | Volume 6470 | www.ijtsrd.com | Volume - 2 | Issue – 5 Real-Time Face Detection Security System Haar Classifier Method using Ei Mon Phyo 1Assistant Lecturer Department of Electronic Engineering ABSTRACT Face Detection is concerned with finding whether or not there are any faces in a given images. Security and surveillance are the two important aspects of human being. Face detection is very important because it is not being safe in human environment. So, F Detection Security System is essential between individual in life. In the modern world everything is changed to provide a better life. So we were decided to develop the Real Time Face detection system. The importance of the face detection as it is esse surveillance and real user interfaces security to the country. Face differ in skin colour, nose, eyebrows, chin between different people in humanity. In this paper we effort is to develop system about face detection security system in the real time. KEYWORD: Haar classifier, Segmentation and Edge/Line Detection, Face Detection, Feature Extraction, Computer Vision 1.INTRODUCTION In the modern world of living, new technolog evolved every day. The most popular and widely use banking system, considering for smart higher security for superior life standard. Security System based on Face Detection and GSM for technology, which can be used in Banks, Security Offices and Ho giving protection to expensive possessions. In this system, only the authorized person the valuable things like money, licenses and jewels from locker. time human identification systems are security, surveillance and biometric applications. 2.COMPUTER VISION Computer Vision is a library of programming functions mainly aimed at real-time computer vision. In simple language it is library used for Image Processing. It is mainly used to do all the operation related to Images. The goal of Computer Vision is to emulate human vision using digital images through three main processing components, executed one after the other: Image acquisition, I analysis and Understanding closely linked with artificial intelligence, as the computer must interpret what it sees, and then perform appropriate analysis. [3 3.HAAR CLASSIFIER 3.1 What is Haar Classifier? Haar Cascade is basically a classifier which is used to detect the object for which it has been trained for from the source. The Haar Cascade positive image over a set of negative images. cascade is an object detection algorithm. It is used to locate faces, pedestrians, expressions in an image. Among them mainly used for face detection.[6] 3.2 Haar-like features Face Detection is concerned with finding whether or not there are any faces in a given images. Security and surveillance are the two important aspects of human being. Face detection is very important because it is not being safe in human environment. So, Face Detection Security System is essential between individual in life. In the modern world everything is changed to provide a better life. So we were decided to develop the Real Time Face detection system. The importance of the face detection as it is essential for surveillance and real user interfaces security to the country. Face differ in skin colour, nose, eyebrows, chin between different people in humanity. In this paper we effort is to develop system about face In simple language it is library used for Image Processing. It is mainly used to do all the operation l of Computer Vision is to emulate human vision using digital images through three main processing components, executed one after Image processing Image nderstanding. Computer vision is cial intelligence, as the computer must interpret what it sees, and then . [3] What is Haar Classifier? is basically a classifier which is used to detect the object for which it has been trained for, Haar Cascade is by covering the over a set of negative images. Haar cascade is an object detection algorithm. It is used to locate faces, pedestrians, expressions in an image. Among them mainly used me. Haar classifier, Segmentation and Edge/Line Detection, Face Detection, Feature objects objects and and facial facial technologies are . The most popular and widely use banking system, considering for smart higher security for superior life standard. Security System based on technology, which can Offices and Homes for giving protection to expensive possessions. In this valuable things like money, licenses and jewels from locker. Real Figure 1.Five Haar like features Figure 1.Five Haar like features important for lications. [2] The size and position of the pattern’s support can very provide its blank and white rectangles have the same dimension, border each other and keep their relative like features are digital image features The size and position of the pattern’s support can very provide its blank and white rectangles have the same dimension, border each other and keep their relative positions. Haar-like features are digital image features used in object recognition. They owe their name to recognition. They owe their name to is a library of programming time computer vision. @ IJTSRD | Available Online @ www.ijtsrd.com @ IJTSRD | Available Online @ www.ijtsrd.com | Volume – 2 | Issue – 5 | Jul-Aug 2018 Aug 2018 Page: 2453

  2. International Journal of Trend in Scientific Research and Development International Journal of Trend in Scientific Research and Development (IJTSRD) ISSN: 2456 (IJTSRD) ISSN: 2456-6470 5.FACE DETECTION The system is using Haar Classifier Method. We have developed three algorithms, for face detection given image, from a folder of images and for real time face detection. The following face detection system. their intuitive similarity with Haar wavelets and were used in the first real-time face detector. [5] 4.FEATURES EXTRACTION Transformation of input data into a set o features. Features are distinctive properties of input patterns that help in different between the categories of an input pattern. Feature extraction involves reducing the amount of resources required to describe a large set of data. [1] their intuitive similarity with Haar wavelets and were [5] The system is using Haar Classifier Method. We have developed three algorithms, for face detection from a a folder of images and for real time following below figure 3 is for Transformation of input data into a set of Features are distinctive properties of input between the categories Feature extraction involves reducing the amount of resources required to describe Figure3. (a) Face Detection by using Haar Classifier Method 3. (a) Face Detection by using Haar Classifier Method Figure2. Example of Feature Extraction mple of Feature Extraction 4.1 Segmentation and Edge/Line Detection The image analysis process requires us to take vast amounts of low level pixel data and extract information. Image segmentation is find regions that represent objects or meaningful parts of objects. Division of the image into regions corres objects of interest is necessary before any processing can be done at a level higher than that of the pixel Identification of real shadows, or actually finding anything of within the image, requires segmentation. Edge detection methods are used as a first step in the line detection process. Edge detection is also used to find complex object boundaries by mar potential edge of points corresponding to places in an image where rapid changes in brightness occur. After these edge points have been marked, they can be merged to form lines and object outlines. Often people are confused about the difference between an edge and a line. [7] Segmentation and Edge/Line Detection The image analysis process requires us to take vast ts of low level pixel data and extract find regions that f objects. Division of the image into regions corresponding to is necessary before any processing can be done at a level higher than that of the pixel. Identification of real Figure3. (b) Face Detection by using Haar Classifier Method Classifier Method 3. (b) Face Detection by using Haar objects, objects, pseudo pseudo-objects, ng of interest some form within the image, requires some form of of Edge detection methods are used as a first step in the tion is also used to find complex object boundaries by marking the Figure3. (c) Face Detection by using Haar Classifier Method Classifier Method 3. (c) Face Detection by using Haar ponding to places in an brightness occur. After 5.1 Aadvantages of by usin Method ?Haar-like image features used in object recognition ?A Haar-like feature considers adjacent rectangular regions at a specific location in a detection window, sums up the pixel intensit region and calculates the difference between these sums. ?Advantage of a Haar-like feature over most other features is its calculation speed. Due to the use of integral images, a Haar can be calculated in constant time (approximately calculated in constant time (approximately edge points have been marked, they can be merged to form lines and object outlines. Often people are confused about the difference between an of by using Haar Classifier like classifier classifier features features are digital object recognition. like feature considers adjacent rectangular regions at a specific location in a detection window, sums up the pixel intensities in each region and calculates the difference between these like feature over most other features is its calculation speed. Due to the use , a Haar-like feature of any size Figure2. Example of Segmentation and Edge/Line Detection Segmentation and Edge/Line @ IJTSRD | Available Online @ www.ijtsrd.com @ IJTSRD | Available Online @ www.ijtsrd.com | Volume – 2 | Issue – 5 | Jul-Aug 2018 Aug 2018 Page: 2454

  3. International Journal of Trend in Scientific Research and Development (IJTSRD) ISSN: 2456-6470 60 microprocessor instructions for a 2-rectangle feature). ?The main of cascading is achieving a good performance for both accuracy and time- complexity, when you have a number of weak classifier. ?The weak classifier must work at least with 51% accuracy. The cascade classifier rejects the many of samples in first node classifier with an efficient time. ?High detection accuracy and low false positive rate.[4] 6.EQUIPMENT OF EXPERIMENTAL TEST (b) Figure5. (a) Open File of Data, (b) Programming of Face Detection by using Haar Classifier Method Figure6. (a) Test and result of Face Detection by using Haar Classifier Figure4. (a) Equipment of Test Figure6. (b) Test and result of Face Detection by using Haar Classifier . Figure4. (b) Equipment of Test 8.CONCLUSION The smart security system has been aimed to design in such a way that it can fulfil the needs of the users for surveillance security area. Face detection security is very useful and essential important in many living together in the world. Using Haar Classifier Method, we have worse knowledge and sharing interface between human and computer software today. 9.ACKNOWLEDGEMENTS Firstly, the author would like to acknowledge Dr. Kyi Soe, Rector of West Yangon Technological University, for his kind permission to carry out this research work. The authors would like to express their thanks to all persons who have given support during the preparation period of this paper. The authors 7.TEST AND RESULTS In this section, tests and results of face detection and classification system using Haar Classifier Method are shown expressed. The performance of the algorithm as a whole is analyzed and discussed below the figure. The image pre-processing is shown in Figure 5. (a) @ IJTSRD | Available Online @ www.ijtsrd.com | Volume – 2 | Issue – 5 | Jul-Aug 2018 Page: 2455

  4. International Journal of Trend in Scientific Research and Development (IJTSRD) ISSN: 2456-6470 would like to thank many colleagues from digital image processing research group of Department of Electronic Engineering Technological University. The author particularly wishes to acknowledge (Head of Electronic Department) Dr. Nay Win Zaw, my supervisor Daw Aye Aye Tun, my teacher U Myat Htut Zaw and all the teachers from Department Engineering, West Yangon Technological University, for their support, encouragement and invaluable guidance in preparation of this research. The authors would like to express their thanks to all persons who have given support during the period of this research work. 10. REFERENCE 1.https://en.wikiwpedia.org/iki/feature_extractio 2.K.Raju1& Dr. Y. Srinivasa Rao “Real time Implementation of Face Recognition System on Raspberry Engineering & Technology, 7 (2.17) (2018) 85-89 3.https://en.wikipedia.org/wiki/Computer_vision 4.https://en.wikipedia.org/wiki/Haarlike_feature 5.Vandna Singh1, Dr. Vinod Shokeen2, Bhupendra Singh3 “Face Detection by Haar Cascade Classifier with Simple and Complex Backgrounds Images Using Open International Journal of Advanced Technology in Engineering and Science, Volume No.01, Issue No. 12, December 2013 6.Nora Krasner, “Real-time face detection with Haar cascades” 7.SCOTT E UMBAUGH “Digital Image Processing and Analysis” “Human and Computer Vision with CVIP tools second edition” Pi” International Journal of of West Yangon of Electronic CV Implementation” @ IJTSRD | Available Online @ www.ijtsrd.com | Volume – 2 | Issue – 5 | Jul-Aug 2018 Page: 2456

More Related