CHAPTER 1

INTRODUCTION
Digital image processing is the use of computer algorithms to perform image processing on
digital images. As a subcategory or field of digital signal processing, digital image processing
has many advantages over analog image processing. It allows a 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 imam are defined over two dimensions (perhaps
more) digital image processing may be modeled in the form of multidimensional systems.

Many of the techniques of digital image processing, or digital picture processing as it often
was called, were developed in the 1960s at the Jet Propulsion Laboratory, Massachusetts
Institute of Technology. Bell Laboratories, University of Maryland, and a few other research
facilities, with application to satellite imagery, wire-photo standards conversion, medical
imaging, videophone, character recognition, and photograph enhancement. The cost of
processing was fairly high, however, with the computing equipment of that era. That changed
in the 1970s, when digital image processing proliferated as cheaper computers and dedicated
hardware became available. Images has could be processed in real time, for some dedicated
problems such as television standards conversion.

As general-purpose computers became faster, they started to take over the role of dedicated
hardware for all but the most specialized and computer-intensive operations. A good target
representation or pattern representation is one of the key issues for a well-designed pattern
recognition system. Representation issues include: what representation is desirable for the
recognition of a pattern and how to effectively extract the representation from the original
input signal.

With the fast computers and signal processors available in the 2000s, digital image processing
has become the most common form of image processing and generally, is used because it is
not only the most versatile method, but also the cheapest. There are various techniques for
target recognition that involve texture, pattern or color based processing of image. Digital
image processing allows the use of much more complex algorithms, and hence, can offer both
more sophisticated performance at simple tasks, and the implementation of methods which
would be impossible by analog means. In particular, digital image processing is the only
practical technology.

1
1.1. Classification
1. Feature extraction
2. Multi-scale signal analysis
3. Pattern recognition
4. Projection
5. Some techniques which are used in digital image processing include
6. Anisotropic diffusion

1.2 Target Recognition

All the objects and faces around the world look totally different from each other. For instance
the position, orientation of the objects is different, the same as the color and pixels. The target
recognition processes have to distinguish between different types of objects and that is not an
easy job. There are various other difficulties came around due to approximately same
orientation, faded & unclear images. This may result into wrong recognition, so there is a
need of an efficient and foolproof system to aid in the work.

The aim of our system is to help people who need to recognize different currencies, and work
with convenience and efficiency. Image Processing involves changing the nature of an image
in order to improve its pictorial information for human interpretation. There are various
techniques for target recognition that involve texture, pattern or color based. The proposed
system will work on two images, one is original image of the target and other is the test image
on which verification is to be performed. A number of methods for target classification have
been proposed. A picture might be considered to contain sub-pictures some of the time alluded
to as districts of-intrigue, ROIs, or essentially areas.

This idea mirrors the way that pictures every now and again contain accumulations of articles
each of which can be the reason for an area. In a complex picture preparing framework it
ought to be conceivable to apply particular picture handling operations to chose districts.
Along these lines one a player in a picture (district) may be handled to stifle movement

1.3 Theoretical background

The system is based on PC, and algorithm. The aid of the algorithm is located in the unique
figure. RGB to Gray, image binarisation, noise elimination, segmentation, pattern matching,
etc we realize there by programming with MATLAB.

2
 Figure 1.1 Algorithm
1.3.1 Image format
The image we get from a database is formatted by JPG/JPEG (Joint Photographic Experts
Group) is a standard for destructive or loss compromising for digital images. When you save
the image as JPG, the image will lose some information, and this cannot be recovered

1.4 Technical background

The major technique of this system is image analysis and image processing, which are part of
cognitive and computer science. Image processing is a signal processing after pre-processing.
The output can be either an image testes of characteristics or parameters related to the image.
Actually the image is treated as 2-dimensional signal and applies some standard signal
processing techniques with image-processing techniques involved. Image analysis is a means
that the meaningful information from an image is extracted mainly from digital images by
means of digital image processing techniques. Image analysis tasks can be as simple as
reading bar coded tags or as sophisticated as identifying a person from their face. Most more
often than not, picture preparing frameworks require that the pictures be accessible in digitized
shape, that is, varieties of limited length paired words. For digitization, the given Image is
inspected on a discrete matrix and each example or pixel is quantized utilizing a limited
number of bits. The digitized picture is prepared by a PC. To show an advanced picture, it is
first changed over into simple flag, which is examined onto a show. Firmly identified with
picture preparing are PC illustrations and PC vision. In PC design, pictures are physically
produced using physical models of items, conditions, and lighting, rather than being obtained
(by means of imaging gadgets, for example, cameras) from regular scenes, as in most
enlivened motion pictures. PC vision, then again, is regularly viewed as abnormal state picture
handling out of which a machine/PC/programming means to decode the physical substance of
a picture or a succession of pictures (e.g., recordings or 3D full-body attractive reverberation
checks). In present day sciences and advances, pictures likewise increase substantially more

3
extensive degrees because of the always developing significance of logical representation (of
regularly expansive scale complex logical/trial information). Illustrations incorporate
microarray information in hereditary research, or ongoing multi-resource portfolio exchanging
account. Before going to handling a picture, it is changed over into an advanced frame.
Digitization incorporates inspecting of picture and quantization of tested qualities. In the wake
of changing over the picture into bit data, preparing is performed. This preparing system might
be Image improvement, Image reclamation, and Image pressure.

Target recognition is technology in the field of computer vision for finding and identifying
objects in an image or video sequence. Humans recognize a multitude of objects in images
with little effort, despite the fact that the image of the objects may vary somewhat in different
view points, in many different sizes and scales or even when they are translated or rotated.
Objects can even be recognized when they are partially obstructed from view. This task is still
a challenge for computer vision systems. Many approaches to the task have been implemented
over multiple decades. The algorithm is based on a combination of Gabor representation of
face object images improves locality preserving projection for target recognition and it is easy
to change the illumination and facial expression different orientation of different objects.

Since the 2000s, the field of Target Recognition has advanced in parallel with similar work in
the commercial sector and academia, involving industrial automation, medical imaging,
surveillance and security, video analytics, and space-based imaging. Technologies of interest
to both the commercial and defense sector include low-power processors, novel sensors,
increased system autonomy, people detection, robotics, rapid search of vast amounts of data
(Big Data), undersea inspection, and remote medical diagnosis. The bulk of funding in some
of these areas has recently shifted from the defense to the commercial sector. More money is
spent on computer animation for Hollywood movies than for the synthesis of forward-looking
infrared (FLIR) and synthetic aperture radar (SAR) imagery. The search engine companies are
investing much more in neural networks compared to the defense companies. Well-funded
brain research programs are investigating the very basis of human vision and cognitive
processing. The days of specialized military processors (e.g., VHSIC) are largely over.
Reliance is now on chips in high-volume production. Highly packaged sensors (visible,
LADAR, and radar) combined with massively parallel processors are advancing rapidly for
the automotive industry to meet new safety standards. Millions of systems will soon be
produced per year. Current advanced driver assistance systems (ADAS) can detect
pedestrians, animals, bicyclists, road signs, traffic lights, cars, trucks, and road markers.

4
1.4.1 Image pre-processing
Image pre-processing is used for operations on images at the lowest level of abstraction. The
pre-processing do not increase image information content but decrease it if entropy is an
information measure. For example as histogram equalization, it modifies the brightness and
contrast of the image, making the image look more clear. The other example is to remove the
noise on the image and improve the quality of edge detection.

Figure 1.2 Grayscale Image

1.4.2 Color detection

In this part, we are going to describe how to detect the primary color of the images. There are
too many types of color model we can use, like RGB, HSV, and GREY. We use RGB model
because we need to calculate the mean of the color. The image is presented as x by y by 3
matrix (here x is the width of the image, y is the height of the image), iteration each pixel and
store the value of R, G, and B. After that, the mean of each channel will be calculated. We do
not calculate the whole primary color of the Image.

1.5 Problem Statement

Target recognition was done for years by playing the baseband signal to the operator.
Listening to this signal, trained radar operators can identify various pieces of information
about the illuminated target, such as the type of vehicle it is, the size of the target, and can
potentially even distinguish biological targets. However, there are many limitations to this
approach. The operator must be trained for what each target will sound like, if the target is
traveling at a high speed it may no longer be audible, and the human decision component
makes the probability of error high. However, this idea of audibly representing the signal did
provide a basis for automated classification of targets.

5
1.6 Project Objectives
The objectives to develop this system are:
1. To explore Gabor Feature in Image Processing.
2. To be able to recognize or detect targets in order to extract information
3. Develop the program that can detect the target using image processing.
4. The processing of input images are improved.

1.7 Project Scope

The scope of this project is to develop a target recognition by using image processing. In other
to implement this system we have to use MATLAB Toolbox to achieve the objectives of the
project. Thus, the focuses of this project are:
1. To implement the system in order to recognize the target.
3. Extract the data from the target image by using digital image processing toolbox.
4. Recognize the target test image from the bunch of database images.

1.8 Motivation
In general, Digital image processing is one of the important aspects for new technologies. We
have tried to develop robust target recognition software using an MATLAB Platform. There
are many additional uses of the Software, such as recognition of faces, palms, fingerprints. It
can also be extended to standard Face detection systems using only image analysis. This
Software is easy to use; it is very user friendly in nature and gives output at runtime. This
platform doesn’t require compiler for execution. It just executes each sentence as it is written
in code. This increases productivity and coding efficiency, this makes language more versatile.

1.8 Outlines of Thesis

Chapter 1 Gives General introduction about Target Recognition algorithm using Gabor
feature.
Chapter 2 Represents the literature review regarding target recognition technology.
Chapter 3 Describes the design methodology.
Chapter 4 Result and analysis
Chapter 5 Conclusion & future Scope
Chapter 6. Critical review and reflections