Image Processing: A Review

Full text


International Journal of Emerging Technology and Advanced Engineering

Website: (ISSN 2250-2459,ISO 9001:2008 Certified Journal, Volume 4, Issue 6, June 2014)


Image Processing: A Review

Jai Prakash


, Akanksha Gohil


1,2Geetanjali Institute of Technical Studies, Udaipur, Rajasthan, INDIA.

Abstract- Image processing is a form of signal processing in which the input is an image, for example , a photograph or video and as output we get either an image or a set of characteristics corresponding to the image. Image processing can also be defined as a means of conversion between the human visual system and digital imaging devices. A proper study of typical Image processing systems is done. All components of Image processing, their application and interrelations between them are thoroughly examined i.e., input devices, output devices and software, its application, the current research going on Image Processing and its need in the future.

Keywords--I.P. image processing, A.I.P. Analog Image Processing, D.I.P. Digital Image Processing, I.E Image Enhancement, I.R Image Restoration.


Image processing is a process of taking an image as an input, perform some operations on it, in order to manipulated the image which include enhancing, reducing rotating etc. or extracting some useful information from it and producing the desired output. It is a method in which input is an image (like a video or photograph) and the output may be image or characteristics related to that image. In I.P an image is treated as a 2-D signal when operations are being applied to it.

This technology is growing at a very fast rate, as it has numerous applications in the field of engineering, business and computer science technology.

Image Processing is used in various applications such as: • Remote Sensing

• Medical Imaging

• Non-destructive Evaluation • Forensic Studies

• Textiles

• Material Science • Military

• Film industry • Document processing • Graphic arts

• Printing Industry

Image processing basically includes the following three steps.

Input: Inputting the image using image scanner or by digital photography technology.

Operation: Analyzing and manipulating the image which includes image enhancement, reduction, rotation, compression and visualizing patterns etc. that are not visible to human eyes.

Output: In the end we get our desired output which can be an altered image or some characteristics of that image or a repot based on this image analysis.


The purpose of image processing is divided into 5 groups. They are:

1. Visualization - Observe the objects that are not visible.

2. Image enhancement and restoration - To create a better image.

3. Image retrieval - Search for the image of interest.

4. Measurement of pattern – Measures various desired objects in an image.

5. Image Recognition – Differentiate between several objects in an image.


I.P works on two different methods:

1. Analog Image Processing

2. Digital Image Processing

1.Analog image processing

In A.I.P manipulation of image is done via some electrical means. In A.I.P technique the input is an analog signal which is fed to various software , for its manipulation and processing, and the final output is an altered visible image. A.I.P techniques can also be use for the hard copies like printouts and photographs.


International Journal of Emerging Technology and Advanced Engineering

Website: (ISSN 2250-2459,ISO 9001:2008 Certified Journal, Volume 4, Issue 6, June 2014)


Figure 1

2. Digital image processing

D.I.P techniques help in manipulation of the digital images by using computers. It takes digital image as input, the system processes and manipulates that image using required software, and gives output in the form of an image. The input may contain some flaws, noise distortions, to overcome such defects and to retrieve the original information, it has to undergo various phases of

processing i.e., Pre-processing, enhancement and

restoration, information extraction to get the final output. Example - Adobe Photoshop.

Figure 2

Figure 3

Application of digital image processing has been commonly found in robotics/intelligent systems, medical imaging, remote sensing, photography and forensics.


1. D.I.P sends image in the form of Codes, which

provides security to the image, but A.I.P sends image in the form of analog signal which is insecure.

2. D.I.P conveys information with greater noise immunity

as compared to A.I.P.

3. D.I.P. technique is cheaper than A.I.P.

4. Using D.I.P technique transmission of signal over large distance can be made possible.

5. Digital signal can be encrypted so that only the intended receiver can decode it, unlike analog signal.



International Journal of Emerging Technology and Advanced Engineering

Website: (ISSN 2250-2459,ISO 9001:2008 Certified Journal, Volume 4, Issue 6, June 2014)


The main focus of their work was to develop medical imaging and character recognition technique, and to create high quality images at the microscopic level.

During this period, equipment and processing costs were very high.

That changed in the 1970s, when digital image processing technique came as cheaper computers and required hardware became available.

This technology became much enhanced when Film and software companies paid much of their attention to it. It became very common by 2000s.


Various I.P. techniques are:

 Image representation

 Image preprocessing

 Image enhancement

 Image restoration

 Image analysis

 Image reconstruction

 Image data compression

A.Image Representation

The most common form to represent natural images and other forms of graphics is by using Bitmap or Raster images. The term bitmap refers to how a given pattern of bits in a pixel maps to a specific color. An example of Image Representation is shown in Figure 2.

Figure 4

The intersection of a row and a column is called as pixel. Taking the above example, in Figure 2, the letter 'a' is represented in a 12x14 matrix, the values in the matrix shows the brightness of the pixels. Larger values correspond to brighter areas whereas lower values correspond to the darker areas.

B.Image Pre-processing

Image pre-processing is a technique which is used to enhance the visual inspection reliability on any image. It uses several filter and operations which intensify or reduce certain image details and thus gives an easier and faster evaluation. Example for Image pre-processing filters are:

 Normalization

 Edge filters

 Soft focus, selective focus

 User-specific filter

 Static/dynamic binaries

 Image plane separation

Image Preprocessing also involves the following processes to increase the interpretation of image – Magnification, Reduction, Rotation and Mosaic.


Digital image magnification can also be called as zooming. This technique most commonly employed for two purposes:

 To expand the scale of the image for enhanced visual interpretation

 To match the scale of another image.

To magnify an image by a factor of 2, each pixel of the original image is replaced by a block of 2x2 pixels, all with the same brightness value as the original pixel.

Figure 3 shows an example of 2x image magnification.

Figure 5 Image Magnification



International Journal of Emerging Technology and Advanced Engineering

Website: (ISSN 2250-2459,ISO 9001:2008 Certified Journal, Volume 4, Issue 6, June 2014)


Figure 6 Image Reduction

3. Rotation

Another interesting technique in image processing is Rotation. Rotation means tilting an image on to some angle (90, 180, 270 degrees). While rotating images all the pixels of the image also get rotated with the respected angle.

Figure 5 shows the Rotation of image.

Figure 7 Rotation

4. Mosaic

Mosaic is a process of combining two or more images to form a single large image without disturbing the actual view of image, in such a way that the boundaries of the original images are not visible. Image mosaic not only help us to create a large image view using small images, but the resultant image can also be used for creating a 3D environment such that users can view the surrounding scene with real images.

Figure 8 Image Mosaic

C. Image Enhancement

Sometimes when the images are captured, they lack in contrast, color, and brightness due to limited illumination or some other reasons. Images may contain some sort of noise. Image enhancement is useful in extracting a particular feature, analyzing the image and displaying a better image. It is a technique comprising of several processes that help in improving the interpretation of image, for examples the contrast and edge enhancement,

pseudo-coloring, noise filtering, sharpening, and

magnifying. Enhancement algorithms used are generally interactive and application-dependent.

Some of the enhancement techniques are:

 Contrast stretching

 Noise Filtering

 Histogram modification

i. Contrast stretching:

Contrast stretching (also called Normalization) is a process to improve an image by stretching the range of intensity of its colors values to display a better image without distortion. Some images (e.g. Over water bodies, deserts, dense forests, snow, clouds and under hazy condition over heterogeneous regions) are homogeneous i.e., they do not have much change in their color levels. In such condition color stretching is to bring an image to a range which is more normal to the senses.


International Journal of Emerging Technology and Advanced Engineering

Website: (ISSN 2250-2459,ISO 9001:2008 Certified Journal, Volume 4, Issue 6, June 2014)


Figure 9 contrast stretching

ii.Noise filtering

Noise filtering is used to filter the unwanted information from an image. It is also used to remove various types of noises and distortion from the images. Mostly this feature is interactive and application dependent.

Figure 10 noise removal

iii. Histogram Modification

Histogram of an image displays the graphical representation of tonal distribution of the image .

It provides a total description of the appearance of an image. The type and amount of enhancement obtained depends on the nature of the specified histogram. Histogram has a lot of importance in image enhancement. It reflects the characteristics of image. By using the histogram, image characteristics can be modified. Example is Histogram Equalization.

Histogram equalization is a nonlinear graphical representation that redistributes pixel, such that every pixel have same range of value. The result approximates a flat histogram. Therefore, contrast is increased at the peaks and lessened at the tails.

Figure 11 histogram equalized output

D. Image restoration

Image restoration is the operation of taking a corrupted/distorted/noisy image as an input and converting it into a clean original image. Distortion or corruption may get produced in many ways such as motion blur, noise, and camera miss-focus. Image restoration is different from image enhancement as I.E is designed to produce an enhanced version of the original image which results into a better and pleasant image , but I.R produces the real image, it may not be better or pleasant but gives us the real data of the. The purpose of image restoration is to undo defects which degrade an image.

E.Image Analysis

Image analysis is analyzing the whole image and taking out meaningful information from images, by using D.I.P. technique. Image Analysis uses pattern recognition, digital geometry, and signal processing to get us the desired output. Examples of image analysis techniques are:

 2D and 3D object recognition,

 Image segmentation,

 Motion detection e.g. Single particle tracking,

 Video tracking,

 Optical flow,

 Medical scan analysis,

 3D Pose Estimation,

 Automatic number plate recognition.

F.Image Reconstruction


International Journal of Emerging Technology and Advanced Engineering

Website: (ISSN 2250-2459,ISO 9001:2008 Certified Journal, Volume 4, Issue 6, June 2014)


The following Figure shows the reconstruction of a real- time MRI report image.

Figure 12

G. Image Segmentation

Image segmentation is the process of sub dividing a digital image into its multiple segments (set of pixels, also known as super pixels). Segmentation helps to simplify the representation of an image making it more meaningful and easier to analyze. Image segmentation is used to locate objects and boundaries (lines, curves, etc.) in images. e.g., in autonomous air-to-ground target acquisition, suppose we want to identifying vehicles on a road, the first step is to segment the road from the image and then to segment the contents of the road down to vehicles. Image thresholding techniques are used for image segmentation.

Figure 13

(This is a model of a segmented femur. It shows the outer surface (red), the surface between compact bone and spongy bone (green) and the surface of the bone marrow (blue).


Classification is the technique used to extract the information in digital remote sensing.

A classification unit is defined as the image segment which is based on classification decision. A classification unit could be a pixel, a group of adjacent neighboring pixels or the whole image. Conventional multispectral classification techniques use spectral signatures of a classification unit to perform class assignments.

Contextual classification refers to the use of spatial, temporal, and other related information, in addition to the spectral information of a classification unit in the classification of an image. It is the pixel that is used as the classification unit.

Figure 14 image classification

In Supervised classification sample pixels from an image are selected which are representative of the specific classes and these are then directed to the image processing software to use these training sites as reference to classify the other pixels in the image. According to the user’s knowledge these training sites (also known as the testing sets) are selected. User set the condition to check the similar pixels to group them together. These bounds are often set based on the spectral characteristics of the training area, plus or minus a certain increment (often based on "brightness" or strength of reflection in specific spectral bands). The images are classified into number of designated number of classes.

In unsupervised classification user does not provide any sample class the outcome is based on the software analysis. Computer determines which pixels are related and are grouped into a single class. Algorithm of the software and the desired number of output classes are specified by the user. However, the user must have knowledge of the area being classified when the groupings of pixels with common characteristics produced by the computer have to be related to actual features on the ground (such as wetlands, developed areas, coniferous forests, etc.).

I. Image Restoration


International Journal of Emerging Technology and Advanced Engineering

Website: (ISSN 2250-2459,ISO 9001:2008 Certified Journal, Volume 4, Issue 6, June 2014)


Original quality of an image can be restored by inverting the physical degradation phenomenon such as defocus, linear motion, atmospheric degradation and additive noise..

Figure 15 Image restoration

J. Image Compression

Compression is a very essential tool for archiving image data, image data transfer on the network etc. There are various techniques used to lossy and lossless compressions. Many techniques are used for image compression, one of most popular compression techniques, JPEG (Joint Photographic Experts Group) uses Discrete Cosine Transformation (DCT) based compression technique. Currently wavelet based compression techniques are used for higher compression ratios with minimal loss of data

Figure 16 wavelet image compression

K. Applications

1.Intelligent Transportation Systems – This technique can be used to determine automated number plate and traffic sign.

2.Remote Sensing – In this application the sensor mounted on the remote satellite and on the aircraft captures the image of the earth’s surface. Then these images are sent to the earth’s station.

This technique is used to interpret the objects and regions are used in flood control, city planning, resource mobilization, agricultural production monitoring, etc.

3. Moving object tracking – In this application the motion parameter and the visual of an object are recored. The different types of approach to track an object are:

 Motion based tracking

 Recognition based tracking

4. Defense surveillance – Aerial surveillance methods are used to continuously keep an eye on the land and oceans. This application is also used to locate the types and formation of naval vessels of the ocean surface. The important duty is to divide the various objects present in the water body part of the image. The different parameters such as length, breadth, area, perimeter, compactness are set up to classify each of divided objects. It is important to recognize the distribution of these objects in different directions that are east, west, north, south, northeast, northwest, southeast and south west to explain all possible formations of the vessels. We can interpret the entire oceanic scenario from the spatial distribution of these objects.

5. Biomedical Imaging techniques – For medical diagnosis, different types of imaging tools such as X- ray, Ultrasound, computer aided tomography (CT) etc are used. The diagrams of X- ray, MRI, and computer aided tomography (CT) are given below.

Figure 17

Some of the applications of Biomedical imaging applications are as follows:


International Journal of Emerging Technology and Advanced Engineering

Website: (ISSN 2250-2459,ISO 9001:2008 Certified Journal, Volume 4, Issue 6, June 2014)


· Lung disease identification-- In X- rays, the regions

that appear dark contain air while region that appears lighter are solid tissues. Bones are more radio opaque than tissues. The ribs, the heart, thoracic spine, and the diaphragm that separates the chest cavity from the abdominal cavity are clearly seen on the X-ray film. 6.Automatic Visual Inspection System – This

application helps the industries to maintain their quality and their productivity of the product.

· Automatic inspection of incandescent lamp filaments – This involves examination of the bulb manufacturing process. If there is non-uniformity in the pitch of the wire then the bulb gets fused within short period of time. In this application, a binary image slice of the filament is created from which the silhouette of the filament is fabricated. These Silhouettes are analyzing the non uniformity in the pitch of the wiring in the lamp. This system is being used by the General Electric Corporation.

· Automatic surface inspection systems – In metal industries it is essential to detect the flaws on the surfaces. In these industries it is essential to detect any aberration on the rolled metal surface in hot and cold rolling mills in the steel manufacturing plants. Image processing techniques such as texture identification, edge detection, fractal analysis etc are used for the detection.

· Faulty component identification – This application is used to identify the faulty components in electronic or electromechanical systems. These faulty components generate a high amount of thermal energy. The Infra-red images are produced from the distribution of thermal energies in the assembly. The faulty components can be identified by analyzing the Infra-red images.

L. Current Research

A wide research is being done in the Image processing technique.

1. Cancer Imaging – Different tools such as PET, MRI, and Computer aided Detection helps to diagnose and be aware of the tumour.

2. Brain Imaging – Focuses on the normal and abnormal development of brain, brain ageing and common disease states.

3. Image processing – This research incorporates structural and functional MRI in neurology, analysis of bone shape and structure, development of functional imaging tools in oncology, and PET image processing software development.

4.Imaging Technology – Development in image technology have formed the requirement to establish whether new technologies are effective and cost beneficial. This technology works under the following areas:

 Magnetic resonance imaging of the knee

 Computer aided detection in mammography

 Endoscopic ultrasound in staging the oesophageal cancer

 Magnetic resonance imaging in low back pain

 Ophthalmic Imaging – This works under two categories:

5.Development of automated software- Analyzes the retinal images to show early sign of diabetic retinopathy 6.Development of instrumentation – Concentrates on

development of scanning laser ophthalmoscope M. Future

We all are in midst of revolution ignited by fast development in computer technology and imaging. Against common belief, computers are not able to match humans in calculation related to image processing and analysis. But with increasing sophistication and power of the modern computing, computation will go beyond conventional, Von Neumann sequential architecture and would contemplate the optical execution too. Parallel and distributed computing paradigms are anticipated to improve responses for the image processing results.

N. Software

Software which is used for development of the image processing is as follows:

Numerous software packages relevant to digital image processing are available on-line, as freeware and/or shareware. The following are representative:

 Open Directory Project: A comprehensive set of links

to image processing and other complementary software.

 CVIPTools: An excellent, interactive program for

image processing and computer vision.

 The FFT Home Page: A resource for FFT programs,

explanations, and benchmarks.

 Technical computing portal (over

20,000 links to technical computing, covering MATLAB, C, Java, Excel, Fortran, and others).

 SPRING: A state of the art GIS and remote sensing


International Journal of Emerging Technology and Advanced Engineering

Website: (ISSN 2250-2459,ISO 9001:2008 Certified Journal, Volume 4, Issue 6, June 2014)



[1] number%3D702214

[2] [3] [4] [5] Rafael C. Gonzalez, Richard Eugene Woods – Digital Image



Figure 5 Image Magnification

Figure 5.

Image Magnification . View in document p.3
Figure 4  2. Reduction Taking the above example, in Figure 2, the letter 'a' is The intersection of a row and a column is called as pixel
Figure 4 2 Reduction Taking the above example in Figure 2 the letter a is The intersection of a row and a column is called as pixel. View in document p.3
Figure 7 Rotation

Figure 7.

Rotation . View in document p.4
Figure 6 Image Reduction

Figure 6.

Image Reduction . View in document p.4
Figure 11 histogram equalized output
Figure 11 histogram equalized output . View in document p.5
Figure 9 contrast stretching
Figure 9 contrast stretching . View in document p.5
Figure 10 noise removal
Figure 10 noise removal . View in document p.5
Figure 14 image classification
Figure 14 image classification . View in document p.6
Figure 15 Image restoration

Figure 15.

Image restoration . View in document p.7
Figure 16 wavelet image compression
Figure 16 wavelet image compression . View in document p.7
Figure 16 wavelet image compression  Figure 17 Some of the applications of Biomedical imaging
Figure 16 wavelet image compression Figure 17 Some of the applications of Biomedical imaging . View in document p.7