02-05-2011, 11:22 AM
Presented By
Saurabh P. Bahurupi
[attachment=13210]
ABSTRACT
Computer Vision & Image Processing are the two distinct fields which are closely co-related with each other. In computer vision, we analyze the input image and obtain an understanding or make a decision. The goal is the emulation of the visual capability of human beings using computers. In other words, computer vision is making the machine see as we do! In image processing, we attempt to manipulate the input image to obtain a “better” image.
In fact where image processing ends and fields computer vision start. Computer vision is the construction of explicit, meaningful descriptions of physical objects from their images. The outputs of computer vision are a description or an interpretation or some quantitative measurements of the structures in the 3D scene. Image processing and pattern recognition are among many techniques computer vision employs to achieve its goals. Computer Vision, also known As Image Analysis, Scene Analysis, Image Understanding, Image Processing, Computer Graphics, Pattern Recognition, Robotics, Artificial Intelligence.
Following are the area where we find application of Computer Vision & Image Processing Robotics, Medicine, Security, Transportation, Industrial, automation, Image/video databases, pattern reorganization and many more.
Chapter 1
INTRODUCTION
1.1 Image
Before introducing the image processing we first see what is image. “An image (from Latin imago) is an artifact, usually two dimensional (a picture), that has a similar appearance to some subject—usually a physical object or a person” [2].
An image defined in the "real world" is considered to be a function of two real variables, for example, a(x,y) with a as the amplitude (e.g. brightness) of the image at the real coordinate position (x,y).A digital image a[m,n] described in a 2D discrete space is derived from an analog image a(x,y) in a 2D continuous space through a sampling process that is frequently referred to as digitization. The 2D continuous image a(x,y) is divided into N rows and M columns.The intersection of a row and a column is termed a pixel. The value assigned to the integer coordinates [m,n] with {m=0,1,2,...,M1}and {n=0,1,2,...,N1} is a[m,n].
Fig 1.1 Image Acquisition
Common image formats include:
– 1 sample per point (B&W or Grayscale)
– 3 samples per point (Red, Green, and Blue)
– 4 samples per point (Red, Green, Blue, and “Alpha”, a.k.a. Opacity)
1.2 Image Processing
Image Processing is any form of signal processing for which the input is an image, such as photographs or frames of video; the output of image processing can be either an image or a set of characteristics or parameters related to the image. Most image processing techniques involve treating the image as a two dimensional signal and applying standard signal processing techniques to it.
An image processing operation typically defines a new image g in terms of an existing image f. The simplest operations are those that transform each pixel in isolation. These pixel to pixel operations can be written:
1.3 Computer Vision
Computer vision is the science and technology of machines that see. As a scientific discipline, computer vision is concerned with the theory for building artificial systems that obtain information from images. The image data can take many forms, such as a video sequence, views from multiple cameras, or multi dimensional data from a medical scanner. Computer vision is concerned with modeling and Computer replicating human vision using computer software and hardware. Computer vision (image understanding) is a discipline that studies how to reconstruct, interpret and understand a 3Dscene from its 2D images in terms of the properties of the structures present in the scene.fig.1.3 shows the summery view of Computer Vision operation.
Computer vision overlaps significantly with the fields shown in Fig 1.4. The important field as given below
1.3.1 Image processing
1.3.2 Pattern recognition, and
1.3.3 Photogrammetry
1.3.1 Image processing
Image processing focuses on image manipulation to enhance image quality, to restore an image or to compress/decompress an image. Most computer vision algorithms usually assumes a significant amount of image processing has taken place to improve image quality.
1.3.2 Pattern recognition
Pattern recognition studies various techniques (such as statistical techniques, neural network, support vector machine, etc..) to recognize/classify different patterns
Pattern recognition techniques are widely used in computer vision.
1.3.3 Photogrammetry
Photogrammetry is concerned with obtaining accurate and reliable measurements from images. It focuses on accurate mensuration. Camera calibration and 3D reconstruction are two areas of interest to both computer vision and photogrammetry researchers.
