International Journal of Advanced Research in Engineering and Technology (IJARET), ISSN 0976 INTERNATIONAL JOURNAL OF ADVANCED RESEARCH IN 6480(Print),

, ISSN 0976 6499(Online) Volume 4, Issue 5, July August (2013), IAEME

ENGINEERING AND TECHNOLOGY (IJARET)

ISSN 0976 - 6480 (Print) ISSN 0976 - 6499 (Online) Volume 4, Issue 5, July August 2013, pp. 35-45 IAEME: www.iaeme.com/ijaret.asp Journal Impact Factor (2013): 5.8376 (Calculated by GISI) www.jifactor.com

IJARET
IAEME

HEIGHT, WEIGHT AND BODY MASS INDEX MEASUREMENT USING MATLAB

Mr. Shrikant J. Honade Assistant Professor, Dept. of Electronics & Telecommunication, G. H. R. C. E. M., Amravati. S. G. B. A. U., Amravati, India,

ABSTRACT Now a days height and weight measurement is one of the most important aspects in the recruitment process of defence and police departments. In both the departments, the height and weight is measured by conventional way which is very cumbersome and time consuming process. As an alternative to this problem, this paper provides an efficient solution in order to make the recruitment process fast and errorless. In this paper a webcam is used to capture the image of person, whose height is to be measured. To capture the image by using webcam image acquisition toolbox is used. After capturing the image of candidate, the processing is done on the image by using efficient digital image processing tool that comes with MATLAB. Also, weight sensor is used for measuring the weight of the person and hence by using height and weight, Body Mass Index (BMI) is calculated to decide the fitness of person. Keywords: Body Mass Index, Height Measurement, Image Acquisition, Image Processing Algorithms, Weight Measurement. 1. INTRODUCTION Height and weight measurement is one of the major aspects of the recruitment process of Defence and Police. Thousands of candidates appear for this recruitment process in which the height and weight is measured by traditional method. This process is very cumbersome and time consuming. To mitigate this problem, an efficient method is proposed to speed-up the process of Height and weight measurement during recruitment process of Defence and Police. In this paper, a webcam is used to take the snap of person whose height is to be measured. The platform is designed to stand the person under which the weight sensors are placed. This sensor generates an analog output equivalent to weight of the person. Using analog to digital convertor and microcontroller this signal will be converted to equivalent weight.

35

International Journal of Advanced Research in Engineering and Technology (IJARET), ISSN 0976 6480(Print), ISSN 0976 6499(Online) Volume 4, Issue 5, July August (2013), IAEME

In this paper MATLAB toolboxes are used to develop software and camera and microcontroller based (embedded system) hardware is used as input device to pc. This tool can be interface with general public by using simple and effective GUI (Graphical User Interface). Also, the algorithms of image acquisition toolbox and image processing toolbox are used. The webcam is use to capture the image of person, whose height is to be measured. To capture the image by using webcam image acquisition toolbox is used. After capturing the image of candidate, the processing is done on the image by using efficient digital image processing tool that comes with MATLAB. Weight sensor is used to calculate the weight of person and the measured height and weight is used to calculate Body Mass Index (BMI) to decide fitness of person. Body mass index is defined as the individual's body mass divided by the square of his or her height. The formulae universally used in medicine produce a unit of measure of kg/m2.

1.1 Digital Image Processing Digital image processing is nothing but the set of computer algorithms designed to perform operation on digital images. As a subcategory or field of digital signal processing, digital image processing has many advantages over analog image processing. It allows much wider range of algorithms to be applied to the input data and can avoid problems such as the build-up of noise and signal distortion during processing. Since images are defined over two dimensions (perhaps more), digital image processing may be modelled in the form of Multidimensional Systems. Digital image processing is an area characterized by the need for extensive experimental work to establish the viability of proposed solutions to a given problem. This section describes how a theoretical base and state-of-the-art software can be integrated into a prototyping environment whose objective is to provide a set of well-supported tools for the solution of a broad class of problems in digital image processing [7]. An image may be defined as a two dimensional function f(x, y) where x & y are coordinate and amplitude of f at any pair of coordinate (x ,y) is called intensity or gray level of the image at that point. Where x, y the intensity values of f [8]. Figure 1 shows an image of an array or a matrix of pixels arranged in rows and columns.

Figure 1: An image of an array or a matrix of pixels arranged in columns and rows

36

International Journal of Advanced Research in Engineering and Technology (IJARET), ISSN 0976 6480(Print), ISSN 0976 6499(Online) Volume 4, Issue 5, July August (2013), IAEME

2. LITERATURE SURVEY 2.1 Measurement of Height of a Tree In order to establish a set of tree height measuring system, on the basis of digital image processing, in 2009 an ordinary digital camera was used by Zhang, Juan to get tree photos and two marker points were chosen in the camera's field of view on the tree. One marker point was set on the root of the tree; the other was set one meter high from the root. A tripod was used to fix the camera for taking photos of the tree. It made the photo perpendicular to the ground. The computer was used to extract the coordinates of the two marker points and the top point according to their colour features using image processing. Lastly, the tree height can be worked out using triangle similarity theory. The experimental results indicate that the relative measurement error of tree height is about 4% [1]. Figure 2 shows tree height measuring system. Where, H is tree height, 1 and 2 are vertical angles of root and tree top respectively.

Figure 2: Tree height measurement system. 2.2 Traditional Method of Height Measurement Also Height and weight measurement is an important aspect of recruitment process of Defence and Police. Thousands of candidates appear for this recruitment process and by traditional method height and weight is measured. This process is very time consuming. Figure 3 shows traditional method of height measurement in recruitment process of Defence and Police.

Figure 3: Traditional method of height measurement

37

International Journal of Advanced Research in Engineering and Technology (IJARET), ISSN 0976 6480(Print), ISSN 0976 6499(Online) Volume 4, Issue 5, July August (2013), IAEME

The proposed algorithm provides an alternatives method to this problem in which height, weight and body mass index is measured more accurately based on MATLAB. Body mass index is defined as the individual's body mass divided by the square of his or her height. The formulae universally used in medicine produce a unit of measure of kg/m2.The WHO regards a BMI of less than 18.5 as underweight and may indicate malnutrition, an eating disorder, or other health problems, while a BMI greater than 25 is considered overweight and above 30 is considered as obese. 3. DESIGN METHODOLOGY 3.1 What is GUI? A GUI uses a combination of technologies and devices to provide a platform the user can interact with, for the tasks of gathering and producing information. A graphical user interface (GUI) is a type of user interface that offers graphical icons and visual indicators, as opposed to text-based interfaces, typed command labels or text navigation to fully represent the information and actions available to a user. The actions are usually performed through direct manipulation of the graphical elements.

Figure 4: Graphical user interface created in MATLAB Figure 4 shows the view of Graphical user interface created in MATLAB. This GUI is having four window and two push buttons. In the first window the main title of the paper Height measurement system is highlighted. The second window is highlighting the text persons height. The third window is editing window. This window is used to show the height of the person after calculation by the software. Fourth window indicate the unit (cm) in which the height of person is displayed in third window. There are two push buttons first one is start and second close. When operation will click start button, the process of height measurement will get start and after calculation of height of a person, the height will be indicated in the third editing window in centre. The close button is used to close the software of height measurement.
38

International Journal of Advanced Research in Engineering and Technology (IJARET), ISSN 0976 6480(Print), ISSN 0976 6499(Online) Volume 4, Issue 5, July August (2013), IAEME

3.2 Implementation Algorithm 3.2.1 Height Measurement The basic operations and the working of the paper can be explained with the help of following steps: 1. Start 2. Initialize image acquisition device (i.e. camera) 3. Capture the image with no person (background must be white) 4. Capture image with person whose height is to be measure 5. Subtract image with no person from image with person 6. Apply thresholding to subtracted image to get black & white image 7. Scan the black & white image for finding the pixel value 1 i.e. the head of the person 8. From the row no calculate the height of the person 9. Display the height of person a. Start When click on the start button shown in GUI, the command to the webcam will be send and it waits for initialization command as shown in figure 5.

Figure 5: GUI Window b. Initialize image acquisition device By using image acquisition toolbox, the webcam will be initialized. The interaction with Image Acquisition Toolbox is done through a video input object. These objects are created with the VIDEOINPUT command. This demo uses a webcam that is accessed through the toolbox's "winvideo" interface. vid = videoinput('winvideo'); After initialization, the GUI will display the command as shown in figure 6.

39

International Journal of Advanced Research in Engineering and Technology (IJARET), ISSN 0976 6480(Print), ISSN 0976 6499(Online) Volume 4, Issue 5, July August (2013), IAEME

Figure 6: GUI after initialization of webcam c. Capture the image with no person To calculate the height of person, here the image with only background is captured, so that this image with no person and only background can be used in the next step.To acquire a single frame, GETSNAPSHOT function is used. noobj = getsnapshot(vid); The snapshot of background without a person is shown in figure 7:

Figure 7: Snapshot of background without a person

40

International Journal of Advanced Research in Engineering and Technology (IJARET), ISSN 0976 6480(Print), ISSN 0976 6499(Online) Volume 4, Issue 5, July August (2013), IAEME

The GUI is showing zero height when no person is standing as depicted in figure 8.

Figure 8: GUI showing zero height when no person standing in front of background d. Capture image with person whose height is to be measure To calculate the height of person the image of person is captured, so that this image with person and background can be used in the next step. Syntax: Per=getsnapshot(vid); figure,imshow(per); The snapshot of background with a person is shown in figure 9:

Figure 9: Snapshot of background with a person e. Subtract image with no person from image with person To eliminate the effect of background and the shading effect, the two images captured in step 3 and step 4 are subtracted and the subtracted image is used for further processing. The substraction is done by using following code: subim=noobj-per; figure,imshow(subim); The snapshot of subtracted image is shown in figure 10:

41

International Journal of Advanced Research in Engineering and Technology (IJARET), ISSN 0976 6480(Print), ISSN 0976 6499(Online) Volume 4, Issue 5, July August (2013), IAEME

Figure 10: Snapshot of background with a person f. Apply thresholding to subtracted image to get black and white image To convert this subtracted image to black & white local thresholding is used. This image is having pixel value 0 for black background and 1 for head of the person i.e. white as shown in figure 11.

Figure 11: Subtracted image converted to black & white g. Scan the black & white image for finding the pixel value 1 The image obtained in step f is a black & white image. This image is scanned to find out the pixel with value 1 which is the pixel for the head of person. Observed and noted down the pixels with value 1 and are used to calculate the height of the person. h. Calculate the height of the person From the no. of row noted in step h, the height of the person can be formed. Noted row must have certain height, this height is assigned to that particular row by conducting certain experiments and created database. i. Display the height of person From the database, the height of person is found; this height in centimeter is displayed in the window shown in figure 12.

42

International Journal of Advanced Research in Engineering and Technology (IJARET), ISSN 0976 6480(Print), ISSN 0976 6499(Online) Volume 4, Issue 5, July August (2013), IAEME

Figure 12: GUI showing height in centimeter 3.2.2 Weight Measurement In order to measure the weight of person load cell is used. A load cell is a transducer that converts load acting on it into an analog electrical signal. This conversion is achieved by the physical deformation of strain gauges which are bonded into the load cell beam and wired into a Wheatstone bridge configuration. The output of load cell is in the range of milivolts. In order to amplify output of a load cell OP-07 operational amplifier is used. The output of OP-07 is connected to analog to digital converter IC ADC0809 to convert analog electrical signal into digital. The output of ADC0809 is applied to the 89C51 Microcontroller in order to assign equivalent weight to the output of ADC0809.The output of 89C51 Microcontroller is fed to PC to execute the weight of person. Figure 13 shows the block diagram of weight measurement system.

Figure 13: Block Diagram of Weight Measurement system

43

International Journal of Advanced Research in Engineering and Technology (IJARET), ISSN 0976 6480(Print), ISSN 0976 6499(Online) Volume 4, Issue 5, July August (2013), IAEME

3.2.3 BMI Measurement Body mass index is defined as the individual's body mass divided by the square of his or her height. The formulae universally used in medicine produce a unit of measure of kg/m2. By using height and weight we can calculate Body Mass Index (BMI) to decide fitness of the person.

The WHO regards a BMI of less than 18.5 as underweight and may indicate malnutrition, an eating disorder, or other health problems, while a BMI greater than 25 is considered overweight and above 30 is considered obese. These ranges of BMI values are valid only as statistical categories. Table 1: Ranges of BMI values Category Very severely underweight Severely underweight BMI range kg/m2 less than 15.0 from 15.0 to 16.0 from 16.0 to 18.5 from 18.5 to 25 from 25 to 30 Mass (weight) of a 1.8-metre (5 ft 11 in) person with this BMI less than 48.6 kilograms between 48.6 and 51.8 kilograms between 51.8 and 59.9 kilograms between 59.9 and 81.0 kilograms between 81.0 and 97.2 kilograms between 97.2 and 113.4 kilograms between 113.4 and 129.6 kilograms over 129.6 kilograms

Underweight Normal (healthy weight) Overweight Obese Class I (Moderately from 30 to 35 obese) Obese Class II (Severely from 35 to 40 obese) Obese Class III (Very severely over 40 obese)

CONCLUSION The proposed method is one of the efficient and accurate method of measurement of height, weight and BMI using MATLAB in which the processing time during recruitment process can be saved to a great extent which ultimately helps in increasing the speed of the recruitment process. By using latest technology this paper can reduce the efforts of human being and make the task simple. This paper of Height, weight and BMI measurement is one of the steps to make these tasks simple and efficient. By using this paper we can save the valuable time in recruitment process of police and army departments. ACKNOWLEDGEMENT The author sincerely thanks to Dr. P. V. Ingole, Principal, G.H.R.C.E.M., Amravati, Prof. N. N. Mandaogade, Head of E & TC Department G.H.R.C.E.M Amravati and Prof. R. D. Ghongade, Head of E & TC Department, P. R. Patil C. O. E Amravati for their valuable suggestion, criticism and time to time encouragement. The author also expresses his warm appreciation to his Brother, Amol, for his help in editing this article.
44

International Journal of Advanced Research in Engineering and Technology (IJARET), ISSN 0976 6480(Print), ISSN 0976 6499(Online) Volume 4, Issue 5, July August (2013), IAEME

REFERENCES Zhang, Juan. Measuring Method of Tree Height Based on Digital Image Processing Technology IEEE Information Science and Engineering (ICISE), 1st international conference 2009 (26-28Dec.2009), 1327-1331. [2] Moradkhani, A. Load cell design and construct with fault detection by Probabilistic Neural Network Mechatronics and Automation, 2008. ICMA2008. IEEE International Conference (5-8 Aug.2008), 55-60. [3] Stefanescu, D.M. Strain gauges and Wheatstone bridges - Basic instrumentation and new applications for electrical measurement of non-electrical quantities Systems, Signals and Devices (SSD), 2011 8th International Multi-Conference (22-25 March 2011 ),1-5. [4] Abraham Asfaw Introduction to MATLAB. IEEE-HKN Lecture Series. EECS '12. Manhattan College. Riverdale, NY. 2011 . [5] Van Dam and Andries. Graphical User Interface. IEEE Computer Graphics and Applications ( Jan/Feb 2000) 50-51. [6] Guerrero, J. Image Processing and Analysis with MATLAB Electrical, Communications, and Computers, 2009. CONIELECOMP 2009. International Conference (26-28 Feb. 2009), 16. [7] Digital image processing by R. C. Gonzalez. [8] Digital Image processing by Kenneth R. cattleman. [9] Mr.J.Rajarajan and Dr.G.Kalivarathan, Influence of Local Segmentation in the Context of Digital Image Processing A Feasibility Study, International Journal of Computer Engineering & Technology (IJCET), Volume 3, Issue 3, 2012, pp. 340 - 347, ISSN Print: 0976 6367, ISSN Online: 0976 6375. [10] Mane Sameer S. and Dr. Gawade S.S., Review on Vibration Analysis with Digital Image Processing, International Journal of Advanced Research in Engineering & Technology (IJARET), Volume 4, Issue 3, 2013, pp. 62 - 67, ISSN Print: 0976-6480, ISSN Online: 0976-6499. [1]

45