Digital

DIGITAL IMAGE PROCESSING

ABSTRACT Image Processing is processing of the image so as to reveal the inner details of the image for further investigation. With the advent of digital computers, Digital Image Processing has started revolutionizing the world with its diverse applications. The field of Image Processing continues, as it has since the early 1970’s, on a path of dynamic growth in terms of popular and scientific interest and number of commercial applications. Considering the advances in the last 30 years resulting in routine application of image processing to problems in medicine, entertainment, law enforcement, and many others. The discipline of Digital Image Processing covers a vast area of scientific and engineering knowledge. Modern digital technology has made it possible to manipulate multi-dimensional signals with systems that range from simple digital circuits to advanced parallel computers. It’s built on a foundation of one- and two-dimensional signal processing theory and overlaps with such disciplines as Artificial Intelligence (Scene understanding), information theory (image coding), statistical pattern recognition (image

classification), communication theory (image coding and transmission), and microelectronics (image sensors, image processing hardware). Image processing has revolutionized in various fields. Examples include mapping internal organs in medicine using various scanning technologies (image reconstruction from projections), automatic fingerprint recognition (pattern recognition and image coding) and HDTV (video coding). Digital Image This paper discusses what is image processing, stages in image processing, problems and applications, diseases that are dioganized, future enhancement and future of digital image processing.

INTRODUCTION: The term digital image processing generally refers to processing of a two dimensional picture by a digital computer. In a broader context, it implies digital processing of any two dimensional data. A digital image is an array of real or complex numbers represented by a finite number of bits. An image given in the form of a transparency, slide, photograph, or chart is first digitized and stored as a matrix of binary digits in computer memory. Digital image processing has a broad spectrum of applications such as remote sensing via satellites and other space crafts, image transmission and storage for business applications, medical processing, radar, sonar, and acoustic image processing, robotics and automated inspection of industrial parts. In medical application one is concerned with processing of chest X-rays, cineangiograms, projection images of transaxial tomography, and other medical images that occur in radiology, nuclear magnetic resonance (NMR), and ultrasonic scanning. These

images may be used for patient screening and monitoring or detection of tumors or other disease in patients. Steps in Image processing: The main steps involved in any image processing applications are as follows: Image acquisition: In order to process any image the image must be acquired so as to perform the necessary processing. Images are generated by the combination of an illumination source and the reflection or absorption of energy from that source by the elements of the scene being imaged. The illumination may originate from a source of electromagnetic energy such as radar, infrared, or X-Ray image. Depending on the nature of the source the illumination energy is either reflected or transmitted through the object of interest. Special sensors are available for scanning the images. Image compression: Image compression solves the problem of reducing the amount of data required to represent the image. The basis of compression lies in removal of redundant data that might be useful for the purpose of storage. Image compression also plays a main role in transmitting data through Internet. Image enhancement: Enhancement as the name indicates is to enhance the image so as to bring the details of the parts of the image which are obscured due to some distortion in the image. The principal objective behind image enhancement is to process the image so that it results in an image which is more suitable for the particular application where that image is applied than the original image. Enhancement of the image using Filters:

Image segmentation: Segmentation of the image is to subdivide a image into its constituent regions or objects. Image segmentation algorithms generally are based on one of two basic properties of intensity values: discontinuity and similarity. In the first category, approach is to partition the image based on abrupt changes in intensity, such as edges of the image. The second approach is to partition the image into regions that are similar according to set of predefined criteria.

APPLICATIONS: There are a wide variety of fields where Image Processing is applied. Some of them include  bio-medicine  analyzing geographical conditions  weather analysis  Remote sensing. Considering the importance of Image Processing in the field of Bio-Medicine the proposed system “OPTHALMIC ANALYSIS AND DETECTION” was developed and is explained in detail. Objective of the Proposed System:  The proposed system aims at taking the input images as the photographic images scanned and to compare and contrast the same image in several aspects with the normal image and study and display the various homologous, analogous characteristics and to display the medical conclusions by studying the innermost parts of the eye.  The main aim of our project is to develop software, which will take a biological image, in this case, the human eye, and to completely analyze it and to detect certain common, yet chronic diseases.

Basic Principle:   



Store the standard defective eye in the database. Scan the photographic image of the patient. Compare the images using Digital Image Processing techniques. Infer the disease and suggest remedial measures.

Diseases that are diagnosed:     Features:

Glaucoma Cornea ulcer Diabetic Retinopathy Iritis

 The proposed software system uses the general method of processing a two dimensional picture by a digital computer.  In the proposed system, the image which is inputted can either be transparencies, slide photographs, X-ray or a chat.  Uses the general Image Processing techniques. Basic Technique involved: Pseudo coloring technique is used for the purpose of the comparison. As the name suggests pseudo coloring means false coloring. Different parts of the eye are assigned colors to make the process of comparison easier. In Turbo C the color ranges from 0 to 15.The process of matrix addition is used during the comparison of the images. If in this process if the value of addition exceeds 15 the final value will be assigned to 15 and this condition indicates the defect because the assigned color for the value 15 will be different when compared to the value obtained. Glaucoma: Glaucoma is caused by a number of different eye diseases, which in most cases produce increased pressure within the eye. A backup of fluid in the eye causes this elevated pressure. Over time, it causes damage to the optic nerve. Through early detection, diagnosis and treatment, the software can help to preserve the vision. Sample image of a person’s eye affected by Glaucoma

Symptoms: • Generally No Symptoms • Blind Spots will be on Vision or side or Peripheral • Blurred vision • Severe Eye pain • Headache

Diabetic Retinopathy:  Diabetic retinopathy is a complication of diabetes and a leading cause of blindness.

 It occurs when diabetes damages the tiny blood vessels inside the retina, the light-sensitive tissue at the back of the eye Sample image of person’s eye affected by Diabetic Retinopathy

Symptoms:  A few specks of blood, or spots, "floating" in the vision are seen.  Hemorrhages tend to happen more than once, often during sleep. Cornea ulcer: A corneal ulcer is an open sore in the cornea, the clear and round front part of the eye through which light passes. Tissue loss because of inflammation produces an ulcer. The ulcer can either be located in the center of the cornea and greatly affect the vision or be placed in the periphery and not affect it so much.

Image of person’s eye affected by Cornea Ulcer

Symptoms:  Severe Pain  Eyes may become sensitive to bright light. Iritis:

 Iritis a form of Anterior Uveitis is a term for an inflammatory disorder of the colored part of the eye (iritis).  Iritis is an inflammation inside the eye, the condition is potentially sight threatening. Symptoms:  Light sensitivity  Red eye  Blurred vision Image of patient’s eye with IRITIS

Various processes involved: The process of image processing i.e. comparison of the images can be done using the below mentioned four classes of algorithms. Each class of algorithms is explained considering a disease. Quadrant processes These processes alter the arrangement of the pixels in an image based on the geometric transformation. This algorithm compares the database image containing the standard defective eye of a person affected by the disease (Glaucoma taken here) with that of a person affected by the disease. It takes the entire image, compares by processing the image through Digital Image Processing techniques and determines whether the patient’s eye is affected by the disease. Detection of Glaucoma through Image Processing (Quadrant Process):

Image of standard defective eye Image of the Patient’s eye. Area processes: These processes alter the pixel value in the image based only upon the original value of the pixel and possibly its location within an image and the values that surround it. In this algorithm X and Y coordinates are given as the input. So the processing is done in that particular area and the results indicate whether the disease is affected in that part of the eye. This is to check the accurate area where the disease is concentrated inside the human eye. Detection of Diabetic Retinopathy through Image Processing (Area Process):

Image of standard defective eye

Image of patient’s eye with Diabetic Retinopathy The area inside the box marked in the image is checked for the disease and the results displays whether the patient’s eye is affected by the image. Frame processes: These processes alter the pixel values within an image based on the pixel values in one or more additional images. In the frame process, both the database image of the

standard defective eye and that of the image of the patient’s eye affected by the disease are separated into different frames.

Detection of Glaucoma using Frame Process

Standard defective image

Image taken from Patient’s eye

So the images are compared within a particular frame, and detects whether the disease is present in that frame which obviously indicates whether the image is present in that part of the eye. Whenever the program is executed it takes the frame and compares inside that part of the frame. Point processes: These processes alter the pixel value in the image based only upon the original value of the pixel and possibly its location within an image. In the point process a single point (pixel) is checked. During the execution the point that is to be compared with the database image and the sample image is entered. The point process checks whether the disease is present at that point.

Processing the image to detect Cornea Ulcer (Point Process)

Standard database image

Image of person’s eye Affected by Cornea Ulcer On executing the source code it asks for the pixel to be compared. On entering the pixel value, it compares those to images at the entered position and checks if disease is present at that point. In this case the point marked within the image is checked and it detects whether the disease is present at that point. Advantages Of the Proposed System over the Existing System:       

Process of Comparison is simpler Hardware requirements are minimized. Point precision can be achieved showing the defective portion. Layman can use the software. Time consumption is minimal. Internal image structure of the eye can be diagnosed. Explores so far unexplored areas of the human eye.

FUTURE ENHANCEMENTS:  Increase the number of diseases that can be detected.  Image Compression techniques to reduce storage. Future of Image Processing: Image signal processing is a fast growing field, and little can be predicted of what would be possible 50 years from now. However, key areas of research are being directed includes improving the traditional tools for compression, transmission, modulating, coding and encryption. On going efforts should be made in developing open standards to ensure inter-operability. With our appetite for media rich and bandwidth hungry resources increasing, and the majority of users still relying on the Plain Old Telephone system for the Internet, there is increasing bottleneck in information delivery.

Current research projects:

The measurement of the degree of opacification in a posterior lens capsule following cataract and intraocular lens implantation surgery. The development of a set of tools, algorithms and technologies for the Conflict Detection and Resolution in a wide range of real time applications within Railways and Metros networks. The development and implementation of a screening system based on digital fundus image for the early detection of diabetic retinopathy. The application of neural networks to the FADS problem in nuclear medicine.

Conclusion: Thus the statement “Image Processing has Revolutionized the world we live in” exactly fits because of the diverse applications of the image processing in various fields.

References: 1. William K. Pratt, “Digital Image Processing”, Wiley eastern publications, 3rd

edition. 2. Rafael C. Gonzalez, Richard E. Woods, “Digital Image Processing”, Addison Wesley publications. 3. K.R.rao, M.A.Narasimhan and K.Revuluri. “Image Data Processing by Hadamard

Haar Transforms.” IEEE TRANS. Computers C-23, no.9 (September 1975): 888-896. 4. Anil K. Jain. “Fundamentals of Digital Image Processing.” Prentice- Hall of India publications