ISSN (Online) 2278-1021
ISSN (Print) 2319-5940
International Journal of Advanced Research in Computer and Communication Engineering
Vol. 4, Issue 5, May 2015
Copyright to IJARCCE DOI 10.17148/IJARCCE.2015.4545 199
Implementation of Image Processing on
Raspberry Pi
K.S.Shilpashree
1
, Lokesha.H
2
, Hadimani Shivkumar
3
M.Tech, VLSI Design and embedded system, E & C Department, Kalpataru Institute of Technology, Tiptur, India
1
Senior Scientist, ALD Division, DSP Lab, CSIR-National Aerospace Laboratories, Bangalore, India
2
Associate Professor, E & C Department, Kalpataru Institute of Technology, Karnataka, India
3
Abstract: Today image processing are used in various techniques, this paper presents the implementation of image
processing operations on Raspberry Pi. The Raspberry Pi is a basic embedded system and being a low cost a single-
board computer used to reduce the complexity of systems in real time applications. This platform is mainly based on
python. Raspberry pi consist of Camera slot Interface (CSI) to interface the raspberry pi camera. Here, the Dark and
Low contrast images captured by using the Raspberry Pi camera module are enhanced in order to identify the particular
region of image. This concept is used in the real time application of MAV, The MAVs are basically used to capture
images and videos through the Raspberry pi camera module. Because of its credit card sized (small) and less weight in
the design. However, the image captured by MAVs will consist of unwanted things due to atmospheric conditions;
hence it is necessary to remove noise present in the MAVs images.
Keywords: Image Capturing, Raspberry Pi, Camera Module, Python, Enhancement Algorithms.
I. INTRODUCTION:
The image processing is a form of signal processing where
the input is an image, like a photograph or video frame,
the output of an image processing may be either an image
or a video frame or a set of characteristics or parameters
related to the image. The acquisition of digital image
usually suffers from undesirable camera shakes and due to
unstable random camera motions. Hence image
enhancement algorithms are required to remove these
unwanted camera shakes. This image processing concepts
are implemented in Raspberry pi in the application of
MAV. The Raspberry Pi is a basic embedded system
having a credit card-sized single board computers
developed in the UK by the Raspberry Pi Foundation. The
Raspberry Pi is based on the Broadcom BCM2835 system
on a chip (SOC) which includes an ARM1176JZF-S Core
(ARM V6K)700 MHz CPU processor, Broadcom Video
Core IV GPU having 17 pins, 3.5W of power, and
512 MB of RAM memory. The Raspberry Pi system has
Secure SD card reader (models A and B) or Micro SD card
reader (models A+ and B+) sockets for boot media and
persistent storage. The system provides Debian Linux
operating system Raspbian image for download. Python is
used as main programming language for raspberry pi. A
micro air vehicle (MAV) is a remote-controlled,
Unmanned Aircraft Vehicle (UAV) significantly smaller
than typical UAVs that have a size restriction. UAV is an
aircraft without a human pilot. Its flight is controlled either
autonomously on board computers or by the remote
control of a pilot on the ground or in another vehicle. By
having a Raspberry Pi camera module available on a MAV
the efficiency of this air vehicle increases and new fields
of applications are available. It is needed in military
Operations, in which targets have to be identified. Such
identification is often done by a human on ground, to
reduce the probability of mistakes. But a Raspberry Pi
camera module is also helpful if a MAV shall
autonomously fly through an arch.
II. BASIC CONCEPT OF IMAGE
PROCESSING
In general, any digital image processing algorithm consists
of three stages: input, processor and output. In the input
stage image is captured by a camera. It sent to a particular
system to focus on a pixel of image that’s gives, its output
as a processed image.
Fig. 1: General Block diagram of image processing
III. SYSTEM HARDWARE DESIGN
The Raspberry Pi board is the central module of the whole
embedded image capturing and processing system as given
in fig. 2. Its main parts include: main processing chip unit,
memory, power supply HDMI Out i.e VGA display,
Ethernet port, and USB ports.
Fig. 2: System Block Diagram
ISSN (Online) 2278-1021
ISSN (Print) 2319-5940
International Journal of Advanced Research in Computer and Communication Engineering
Vol. 4, Issue 5, May 2015
Copyright to IJARCCE DOI 10.17148/IJARCCE.2015.4545 200
A. RASPBERRY PI BOARD
The main signal processing chip unit used in Raspberry Pi
system is a Broadcom 2835 700MHz Chip in which CPU
core is a 32 bit ARM1176JZF-S RISC processor designed
by Advanced RISC Machines. This main processing chip
connects a camera and display. The Raspberry Pi design
does not include a built in hard disk or solid state drive,
instead used an SD card for booting and long term storage.
This board is intended to run Linux Debian based
operating systems. This Raspberry Pi module has a
Samsung class 4 micro SD card preloaded with the
Raspberry Pi NOOBS (New Out of Box Software)
package, and a printed Micro SD card adaptor.
Fig. 3: Raspberry Pi board (Model B).
B. Camera Interface
The camera module used in this paper is raspberry pi
camera module as shown in the Fig. 3. The camera module
plugs to the CSI connector on the Raspberry Pi. It's able to
deliver clear 5MP resolution image, or 1080p HD video
recording at 30fps. The camera module attaches to
Raspberry Pi by a 15 pin Ribbon Cable, to the dedicated
15 pin MIPI Camera Serial Interface (CSI), which was
designed especially for interfacing to cameras. The CSI
bus is capable of extremely high data rates, and it
exclusively carries pixel data to the BCM2835 processor.
Fig. 4: Raspberry Pi camera board
IV. METHODOLOGY
The proposed method uses the raspberry pi board is the
main controller. The latest version of raspbian wheezy is
used on to the board. After installing the OS to the board
connect all the necessary hardware components and switch
on the power supply.
It starts booting up the Board and login the raspberry pi by
username and password. It operates on the Linux Debian
arch operating system. It mainly works on the python
software and checks the network settings to update the
python software by commands in the terminal window.
Following packages are to be installed for implementing
the proposed model. Installation commands have been
listed below.
1) sudo apt-get install python-matplotlib
2) sudo apt-get install python-numpy
3) sudo apt-get install python-scipy
4) sudo apt-get install python-imaging
Enable the camera settings on the board to capture the
image and save it on the folder. Run the python code to
check the enhancement algorithms and remove the noise
present in an image. The proposed method
implementation as shown in the flow chart in fig 5.
Fig 5: Flow chart of methodology.
V. RESULTS AND DISCUSSION
For the purpose of real time simulation the raspberry pi
running the latest version of Raspbian wheezy was used.
The development environment was python 2.7.3. Once the
ISSN (Online) 2278-1021
ISSN (Print) 2319-5940
International Journal of Advanced Research in Computer and Communication Engineering
Vol. 4, Issue 5, May 2015
Copyright to IJARCCE DOI 10.17148/IJARCCE.2015.4545 201
user captures the objective image and specifies the
reference image, the rest of the process is completely
automatic and there is no need for user intervention. Here
the algorithm has been applied to the complete image.
Fig. 6: Original Image
Fig 7. Gray Image
Fig 8: Brightness Enhanced Image
Fig 9: Contrast Stretched Enhanced Image.
In the application of micro air vehicle (MAVs) there is a
noise present in the images due to the atmospheric
conditions, so removing noise from images is important in
this application and improving the quality of images. For
this method I used the Rudin-Osher-Fatemi de-noising
model (ROF). The total variation of a grayscale image I is
defined as a sum of gradient norm for a continuous
representation is given by
For a discrete setting, the total variation becomes
In the ROF algorithm it is to find the denoised image U
that minimizes
Where the norm ||I-U|| measures the difference between U
and gray image I.
The ROF model has the interesting property that it finds a
smoother version of the image while preserving edges and
structures. The result as shown in below figures.
Fig 10: Noisy image
Fig 11: Noise removal image
Fig 12: Gaussian filtered image
ISSN (Online) 2278-1021
ISSN (Print) 2319-5940
International Journal of Advanced Research in Computer and Communication Engineering
Vol. 4, Issue 5, May 2015
Copyright to IJARCCE DOI 10.17148/IJARCCE.2015.4545 202
VI. CONCLUSION
We implemented the algorithm to enhance an image in
different enhancement degree using the raspberry pi. It
was found that the algorithm developed for the raspberry
pi executes successfully and gives a very colorful image.
REFERENCES
[1]. G.Senthilkumar1, K.Gopalakrishnan2, V. Sathish Kumar3
Embedded Image Capturing System Using Raspberry Pi System,
Volume 3, Issue 2March–April 2014 Page 213.
[2]. Sahani, M., Rout, S.K., Sharan, A.K., Dutta, S. real time color
image enhancement with a high regard for restoration of skin color
by using raspberry pi Communications and Signal Processing
(ICCSP), 2014 International Conference IEEE.
[3]. Y.Saahithi, E.Sai Spandana Reddy, P.Samskruthi Reddy,
Advanced Embedded Security System With Image Capturing In SD
Card, Volume No: 1(2014), Issue No: 12 (December).
[4]. Ajinkya Patil1, Mrudang Shukla2 Implementation Of Classroom
Attendance System Based On Face Recognition In Class, IJAET,
Vol. 7, Issue 3 July, 2014.
[5]. Umesh P Image Processing in Python, CSI Communications,
December 2012.
[6]. Jan Erik Solem, Programming Computer Vision with Python, 2012.
[7]. Raspberry pi – www.raspberrypi.org