Shailendra Kumar Dewangan / International Journal of Computer Science & Engineering Technology (IJCSET)

Importance & Applications of Digital

Image Processing
Shailendra Kumar Dewangan
Assistant Professor, Department of Electronics & Instrumentation Engineering
Chhatrapati Shivaji Institute of Technology, Durg, Chhattisgarh, India
Abstract - Digital image processing has become economical in many fields like signature recognition, iris
recognition and face recognition, in forensics, in automobile detection and in military applications. Each
of these applications has its basic requirements, which may be unique from the others. Everyone is
concerned and demands a system as faster, more accurate, cheaper and more extensive computation.
This paper has reviewed various image processing operations to illustrate the basic concepts and to use
them in different fields with minor changes in the methodology. This paper discusses about the basic
technical aspects of digital image processing with reference to be categorized into three groups as: Image
Rectification and Restoration, Enhancement and Information Extraction. Importance of digital image
processing and its applications are also discussed from the fields of computer vision and other
applications. An image is defined as an array, or a matrix, of square pixels arranged in rows and
columns. Image processing is a procedure of converting an image into digital form and carry out some
operation on it, in order to get an improved image and to retrieve some important information from the
image.
Keywords - Biomedical imaging, digital image processing, face recognition, image enhancement, iris
recognition, signature recognition, etc.
I. INTRODUCTION
Digital image processing is a very popular and rapidly growing area of application under computer science
engineering. Its growth leads by technological innovations in the fields of digital imaging, computer processing
and mass storage devices. Fields which have been traditionally using analog imaging are now switching to
digital systems, for their edibility and affordability. Important examples are medicine, and video production,
photography, remote sensing, and security monitoring. These sources produce a very huge volume of digital
image data daily, more than could ever be examined manually. Basically image processing can be defined as the
processing of a two dimensional picture by a computer. The outcome of image processing could be an image or
a result as set of features or characteristics related to the image. Most image processing methods treats an image
as a two dimensional signal and implementing standard signal processing techniques to it. [1-5] The goal of this
operation can be divided into 3 categories. Firstly image processing in which input is an image and output is
also an image; secondly image analysis in which input is an image and output are the dimensions or
measurements. Finally image understanding in which input is an image and output is the standard description of
an image. Some of the important applications of image processing in the field of science and technology include
computer vision, remote sensing, feature extraction, face detection, forecasting, optical character recognition,
finger-print detection, optical sorting, argument reality, microscope imaging, lane departure caution system,
Non-photorealistic representation, medical image processing, and morphological imaging.
II. LITERATURE REVIEW
Digital image processing contains wide scope for researchers and scientists to work on various areas of
science and engineering. Several algorithms have already been proposed and developed. This section makes a
brief discussion on previous works and applications of image processing. Digital image processing is helpful for
many applications and their analysis, which can be used in different applications like in vehicle detection from
an image using aerial cameras [1]. One such application by using this concept can be applied in keyboard
industry where poorly manufactured keyboards can be detected at manufacturing stage. In this type of
applications an input image of the manufactured keyboard is fed to detect the missing key or damaged key.
Similar concept has been used in Face Recognition [2-3], Facial Expression Recognition. Further with the
advancement of image enhancement techniques, a precise extraction of particular feature has become possible
like number plate recognition from the detected vehicle and eyes, nose, ears, lip gesture from recognized face
[4]. Digital Image Processing is applied in the fields of Computer vision, Face detection, Feature detection, Lane
departure warning system, Non-photorealistic rendering, Medical image processing, Microscope image
processing Morphological image processing, Remote sensing, etc. Some of the applications of digital image
processing are discussed as followings:

ISSN : 2229-3345 Vol. 7 No. 07 Jul 2016 316

Shailendra Kumar Dewangan / International Journal of Computer Science & Engineering Technology (IJCSET)

1) Computer Vision - Computer vision is a kind of automated watchdog, which uses both science and
technology. Being a discipline from science, computer vision is related to theory for design of artificial
systems that can acquire information from images. The image input may be of many formats, such as a
video signal sequence, or multiple views from different cameras, or data input from a medical scanning
machine. Examples of applications of computer vision include systems for controlling processes such as
an industrial robot or an autonomous vehicle; for detecting events such as in visual surveillance or people
counting; for organizing information such as for indexing databases of images and image sequences; for
modeling objects or environments such as industrial inspection, medical image analysis or topographical
modeling; for interaction such as the input to a device for interaction between a computing machine and
human. [6-9]
2) Face Detection - In this method important facial features are detected and else are ignored. Face detection
can be treated as a specific case of object class detection. The objective of face detection is to find the
specified features such locations and sizes of a known number of faces. Various face detection algorithms
are focused on the detection of frontal human faces. It is also an attempt to solve the more general and
difficult problems of multi view face detection. [10-11]
3) Digital Video Processing - In different engineering and computing applications video processing is a
particular and an important case of signal processing. Here the input and output signals are video files or
video streams. Video processing techniques are used in television sets, VCRs, DVDs, video codec, video
players and other devices. For example commonly only design of various systems and video processing
methodology is different in TV sets by different companies.
4) Remote Sensing - Remote sensing is basically an acquisition of small or large scale information signals
from an object or phenomenon, by the using various real-time sensing devices that are wireless in nature,
or not in physical or direct contact with the object (such as aircraft, spacecraft, satellite or ship). Practically
remote sensing is a collection of different data signals using variety of devices for gathering information
on a given object or area. The monitoring of a parolee using an ultrasound identification system, Magnetic
Resonance Imaging (MRI), Positron Emission Tomography (PET), X-radiation (X-ray) and space probes
are all examples of remote sensing. [12-14]
5) Biomedical Image Enhancement & Analysis - Biomedical image enhancement is very important issue for
biomedical image diagnosis, the aim of this area is to enhance the biomedical images. In addition to
originally digital methods, such as Computed Tomography (CT) or Magnetic Resonance Imaging (MRI),
initially analog imaging modalities such as traditional applications like endoscopy or radiography are
nowadays equipped with digital sensors. Digital images are composed by individual pixels to which points
to discrete brightness or different color values. After biomedical image enhancement & proper analysis,
they can be efficiently processed & objectively evaluated.
6) Biometric Verification - It refers to the automatic identification or recognition of humans by their
behaviors or characteristics. Biometrics recognition is such an efficient type of identification and access
control. It can also be used to recognize individuals in groups that are under observation. The purpose of
such a technique is to ensure that the rendered services are accessed only by a legitimate user and no one
else. A biometric system is theoretically a pattern recognition system that is based on acquiring biometric
data from an individual. The operating principle is based on extracting set of defined features from the
acquired data, and comparing this feature set against the template set in the database. Depending on the
type and mode of application, a biometric system may work under verification mode or identification
mode. [15-16]
7) Signature Recognition - Signature verification and recognition is also an important application, which is to
decide, whether a signature belongs to a given signer based on the image of signature and a few sample
images of the original signatures of the signer. Handwritten signatures are imprecise in nature as their
corners are not always sharp, lines are not perfectly straight, and curves are not necessarily smooth.
Furthermore, the fonts can be drawn in different sizes and orientation in contrast to handwriting which is
often assumed to be written on a baseline in an upright position. Therefore, a robust handwritten signature
recognition system has to account for all of these factors. [16-19]
8) Underwater Image Restoration & Enhancement - In Underwater Image processing, the basic physics of
light propagation in the water medium comes into extinction. When the light enters into water, it
exponentially attenuates with the depth of water level; therefore the visibility distance is affected and so
limited. Underwater images suffer from different problems such as blurring, non uniform lightening, noise,
low contrast, etc. Therefore, restoration & enhancement of underwater images is an essential area for
research. Various filters are used in the enhancement methods to improve the image quality, to suppress
the noise, to preserve the edges in an image and for smoothening of the image. [20-22]

ISSN : 2229-3345 Vol. 7 No. 07 Jul 2016 317

Shailendra Kumar Dewangan / International Journal of Computer Science & Engineering Technology (IJCSET)

9) Character Recognition - Character recognition, usually known as optical character recognition or

abbreviated as OCR. It is mechanical or electronic translation of images of either handwritten or printed
text (usually captured by a scanner) into machine editable text. It is a wide area for researchers in pattern
recognition, artificial intelligence and machine vision. For many document input tasks, character
recognition is the most cost effective and speedy method available. [23-24]
10) Medical Palmistry - Palmistry is a science which observes human palm by different aspects and derives
conclusions about nature of the person. Since from ancient times, many civilizations like Indian, Chinese,
Persian, Egyptian, Roman and Greek, people were used to get guidance about their present and future by
means of palmistry. It includes attributes of human, like, health, psychology, intelligence, lifestyle and
other related entities. Medical palmistry can be considered as one of the branches of palmistry. By using
this medical palmistry, probable diseases can be identified by observing some symbols in human palms
such as iceland, cross, grill, spot, star, square and circle. Additionally shapes of palm and fingers also play
very important role in such decision making for identification of deseases. [25]
III. METHODOLOGY
The process of analysis using digital image processing can be divided into various phases. The blocks
diagram of a digital image processing (DIP) system is shown in Figure 1. The general functioning of different
block stages are briefly discussed as followings:
A. Image Acquisition: It is the first step or fundamental step of digital image processing. Under image
acquisition the image is given in digital format. Generally, this stage of image acquisition stage involves
preprocessing, such as scaling etc. An image can be made input by some sort of scanner, digital cameras or
with the help of aerial cameras .This image should be a high quality image with greater resolution, which
helps in proper image analysis.

Figure 1 - Block Diagram of a DIP System

B. Preprocessing - Some preprocessing operations are required to be performed on the input image. The aim
of preprocessing techniques is to improve the image data to suppress the unwanted distortions and to
enhance some features of the input image. When processing high resolution images, the image size is
needed to be reduced because of the reason that processing on high resolution images takes a longer time.
Then after the color image is converted into grey scale image, because less information is needed to be
provided for each pixel. In fact grey color is the one in which the red, blue and green components contain
equal intensities; therefore it is necessary to specify a single value of intensity level for each pixel.
C. Edge Detection & Segmentation - Under edge detection some points are required to be identified to capture
some important changes and events in the properties of the image. In case of image segmentation, image is
identified into multiple segments. In form of these segments an image that is more meaningful and easy to
analyze. Segmentation is accomplished by scanning the image pixel by pixel and then after each pixel is
labeled, depending on whether the grey level is greater or less than the threshold value.
D. Image Restoration: Image restoration is an area, in which the appearance of an image is improved. Image
restoration techniques are based on mathematical models or probabilistic analysis of an image. There are
various filter available or can be designed for the restoration and to enhance the quality of an image.
E. Output Image - After using various image processing techniques accompanied with morphological
operation on digital image, the object of interest from the given image can be obtained.
IV. PROBLEMS IDENTIFICATION
This section discusses with few problems associated with digital image processing methods under various
applications. Edge detection, which is an approach for region splitting. It indicates important information about
the image showing an edge map. The memory space requirement for storage of cropped image is comparatively
very small. Also the edge map (cropped image) is able to restore easily the original image. So often, noise
affects the image during the acquisition process. The properties of the noise are likely to vary. However, there
are three standard noises which are encountered in most images, (i) Additive noise, (ii) Multiplicative noise, and
(iii) Impulse noise. Additive noise is basically independent of the pixel values available in original image. It
results as, not altering the average brightness of the image, or large parts thereof. Additive noise is a common
source for thermal noise when using photo electronic sensors. Multiplicative noise, which is also known as
speckle noise, is a signal dependent form of noise, whose magnitude is related to the value of the original pixel

ISSN : 2229-3345 Vol. 7 No. 07 Jul 2016 318

Shailendra Kumar Dewangan / International Journal of Computer Science & Engineering Technology (IJCSET)

value of the image [9]. It represents that one simple form it can take. Multiplicative noise is a particular type of
noise, which is found in images recorded by using synthetic aperture radar. [10] Quantization noise is
introduced, due to the quantization of pixel values during the analog to digital signal conversion process. The
standard case of impulse noise uses a uniform distribution on (0, z-1).
V. DIGITAL IMAGE PROCESSING USING MATLAB
MATLAB (MATrix LABoratory) is software, which provides an interactive environment for numerical
computations and graphics analysis. This software is especially designed and used for mathematical analysis
using matrix computations. [1-3] Also this software has a large variety different tool boxes having graphic
solving capabilities and it can be extended using programming, which are written in its own programming
language. MATLAB has a large collection of toolboxes in a variety of domains. Some examples of MATLAB
toolboxes are control system, signal processing, neural network, image processing, and system identification.
The toolboxes consist of functions that can be used to perform computations in a specific domain. [7]
VI. CONCLUSION & FUTURE SCOPE
The basics of image processing such as Image, image-analysis and understanding, image-transforms,
compression techniques, optical character recognition (OCR) and its applications such as video and 3D graphics
firmness, Remote Sensing, Pattern gratitude, Visual content analysis, Biometrics, Statistical image processing,
Multimedia interacting and Virtual reality, face detection and medical image processing are discussed in this
paper. This study will help the researchers to work on various fields such as image processing, fault detection in
industrialized Industries, medical image segmentation. The biggest limitation of all these algorithms is that the
accuracy of these algorithms is dependent on the resolution quality of camera and view angle between camera
and the target object. It is also observed that at some angles the results were not accurate beyond a certain range
of camera.
The future of digital image processing involves new intelligent, digital automated robots created entirely by
research scientists in various nations of the world. It includes advancements in various digital image processing
applications. Due to innovations in image processing and other related technologies, there will be millions and
millions of robots in the world in a few decades of time span, transforming the way the world is managed.
Advance researches in image processing and artificial intelligence will involve voice commands, anticipating
the information requirements of governments, translating languages, recognizing and tracking people and things,
diagnosing medical conditions, performing operation & surgery, reprogramming defects in human DNA, and
automatic driving all formats of transportation. With increase in power and sophistication of modern computing,
the concept of computation can be extended beyond the present limits. In future, image processing technology
will be more advanced and the visual system of man can be replicated. The future trends in remote sensing will
be aiming towards various improved sensors that can record the same scene in many spectral channels. Graphics
data is also getting tremendously importance in the field of digital image & signal processing app1ications.
REFERENCES
[1] A. K. Jain, “A handbook of Fundamentals of Digital Image Processing", Prentice Hall of India, 1989.
[2] R. C. Gonzalez & R. E. Woods, “Digital Image Processing”, 3rd Edition, Prentice Hall of India, 2009.
[3] Madhuri A. Joshi, “Digital Image Processing - An Algorithmic Approach”, Prentice Hall of India, 2010.
[4] Aisha Ajmal & Ibrahim M. Hussain, “Vehicle Detection Using Morphological Image Processing Technique”, IEEE, 2010.
[5] J. M. S. Prewitt, “Object Enhancement and Extraction”, Picture Processing and Psychopictorics, Academic Press, New York, 1970.
[6] Ye Zhang, Hongsong Qu & Yanjie Wang, "Adaptive Image Segmentation Based on Fast Thresholding & Image Merging",
International Conference on Artificial Reality & Telexistence Workshops, pp. 308-311, 2006.
[7] S. K. Dewangan, “Devnagari Handwritten Signature Recognition Using Neural Network”, Lambert Academic Publications (LAP),
ISBN: 978-3-659-26595-2, Germany, 2012.
[8] Soumen Bag & Gaurav Harit, “Topographic Feature Extraction For Bengali And Hindi Character Images”, International Journal of
Signal & Image Processing, Vol. 2, No. 2, pp. 181-196, 2011.
[9] Kwon Lee, Chulhee Lee & Seon Ae Kim, "Fast Object Detection Based on Color Histograms and Local Binary Patterns", IEEE
Region Conference TENCON 2012, Vol. 1, No. 4, pp. 19-22, 2012.
[10] Ritu Tiwari, Anupam Shukla, Chandra Prakash, Dhirender Sharma, Rishi Kumar & Sourabh Sharma, “Face Recognition using
Morphological Method”, IEEE, 2009.
[11] N. Patel & S. K. Dewangan, “An Overview of Face Recognition Schemes”, International Conference of Advance Research and
Innovation (ICARI-2015), Institution of Engineers (India), Delhi State Centre, Engineers Bhawan, New Delhi, India, 2015.
[12] K. Geetha, Thanushkodi, Kishore Kumar, “New Particle Swarm Optimization for Feature Selection and Classification of Micro
calcifications in Mammograms”, International Conference on Signal Processing Communications and Networking, pp. 458-463, 2008.
[13] Y. Yang, Wei, L. Nishikawa, “Microcalcification Classification Assisted by Content Based Image Retrieval for Breast Cancer
Diagnosis”, IEEE International Conference on Image Processing, Vol. 5, pp. 1-4, 2007.
[14] Hadjiiski, Filev, P. Chan, J. Sahiner, B. Helvie, M.A. Roubidoux, “Computerized Detection and Classification of Malignant and
Benign Microcalcifications on Full Field Digital Mammograms” Springer IWDM, Vol. 5116, pp. 336-342, 2008.
[15] Shailendra Kumar Dewangan, “Human Authentication Using Biometric Recognition”, International Journal of Computer Science &
Engineering Technology (IJCSET), ISSN: 2229-3345, Vol. 6, No. 4, pp. 240-245, April 2015.
[16] S. Dewangan, P. Gupta, U. K. Sahu & I. Verma, “Realtime Recognition of Handwritten Words using Hidden Markov Model”,
International Journal of Technological Synthesis and Analysis (IJTSA), ISSN: 2320-2386, Vol. 1, Issue 1, pp. 07-09, December 2012.

ISSN : 2229-3345 Vol. 7 No. 07 Jul 2016 319

Shailendra Kumar Dewangan / International Journal of Computer Science & Engineering Technology (IJCSET)

[17] S. K. Dewangan, “Real Time Recognition of Handwritten Devnagari Signatures without Segmentation Using Artificial Neural
Network”, International Journal of Image, Graphics and Signal Processing (IJIGSP), ISSN: 2249-8958, Vol. 5, No. 4, pp. 30-37, April
2013.
[18] S. B. Patil & S. Dewangan, “Offline Handwritten Devnagari Signature Recognition using Moment Invariant Analysis in Neural
Network”, Journal on Communication Engineering and Systems, ISSN: 2277-5242, Vol. 1, No. 1, pp. 39-48, November 2011 –
January 2012.
[19] S. Patil & S. Dewangan, “Neural Network based Offline Handwritten Signature Verification System using Hu’s Moment Invariant
Analysis”, International Journal of Engineering and Advanced Technology (IJEAT), ISSN: 2249-8958, Vol. 1, Issue 1, pp. 73-79,
October 2011.
[20] N. Patel & S. Dewangan, “Visual Quality Accomplishment of Underwater Images”, International Journal of Electrical and Electronics
Engineers (IJEEE), ISSN: 2321-2055, Vol. 7, Issue 1, pp. 367-375, 2015.
[21] S. Dewangan, P. Gupta, U. K. Sahu, I. Verma & R. Sonwane, “Performance Evaluation of Edge Detection Techniques on
Photographic Images”, International Journal of Advanced Research in Computer Science (IJARCS), ICV - 5.47, ISSN: 0976-5697,
Vol. 3, No. 7, pp. 206-208, 2012.
[22] S. K. Dewangan, “Identification of Colors in Photographic Images Using Color Quantization”, Proceedings of International
Conference of Advance Research and Innovation (ICARI, ISBN : 978-93-5156-328-0, pp. 318-322), Institution of Engineers (India),
Delhi State Centre, Engineers Bhawan, New Delhi, India, February, 2014.
[23] Brijmohan Singh, Ankush Mittal and Debashis Ghosh, “An Evaluation of Different Feature Extractors and Classifiers for Offline
Handwritten Devnagari Character Recognition”, Journal of Pattern Recognition Research, pp. 269-277, 2011.
[24] Soumen Bag and Gaurav Harit, “Topographic Feature Extraction For Bengali And Hindi Character Images”, International Journal of
Signal & Image Processing, Vol. 2, No. 2, pp. 181-196, June 2011.
[25] Hardik Pandit & D. M. Shah, “Application of Digital Image Processing & Analysis in Healthcare Based on Medical Palmistry”, Proc.
of International Conference on Intelligent Systems & Data Processing, pp. 56-59, 2011.

Author’s Profile
Shailendra Kumar Dewangan received M.E. & B.E. in ETC from SSCET Bhilai,
Chhattisgarh, India. He is currently working as an Assistant Professor in the Department of
Electronics & Instrumentation Engg. at CSIT Durg. His areas of interest include digital
signal processing, digital image processing, information security, digital watermarking,
advancements in communication technology, etc. Besides he has lifetime membership of
Indian Society of Technical Education (ISTE) and Associate membership of Institute of
Electronics & Telecommunication Engineers (IETE).

ISSN : 2229-3345 Vol. 7 No. 07 Jul 2016 320