14-08-2012, 10:24 AM
object Recognition:
object recognition.docx (Size: 703 KB / Downloads: 21)
INTRODUCTION
What is object recognition?
According to “computer science vision” Object Recognition is the task of finding a given object 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 viewpoints, in many different sizes / scale 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 in general.If the near visual system of the object does operate using particulate features, then it is possible that the mechanisms of avian visualisation differ substantially from the mechanisms of human visualisation. The avian visual system does differ significantly in the underlying compared to the primate visual system. However, there are analogous pathways and structures. It seems somewhat premature to accept the assumption that the avian (near foveal) visual system differs vastly from our own in terms of the mechanisms of object recognition.A perceived object is analyzed by the visual system, which parses the object into its constituent geons. Then, the interrelations are determined, which include aspects such as relative location and size (e.g., the lamp shade is left-of, below, and larger-than the fixture). The geons and interrelations of the perceived object are matched against stored structural descriptions.
Idea about object Recognition:
Imagine waiting for incoming passengers at the arrivalgate at the airport. Your visual system can easily findfaces and identify whether one of them is yourfriend’s. or not . In its general form, it is a very difficultcomputational problem. computational work in objectRecognition considers the recognition problem as aSupervised learning problem.The main computational difficulty is the problemOf variability.A vision system needs to generalize across huge or large Variations in the appearance of anobject such as a face, due for instance to viewpoint, illumination or occlusions.
The goal of computer vision is to develop the algorithms and representations that will enable a machine to autonomously analyze visual information. As such, object recognition is a fundamental vision problem: put simply, what’s in the picture, and where? Recognition remains challenging in large part due to the significant variations exhibited by real-world images. Partial occlusions, viewpoint changes, varying illumination, cluttered backgrounds, and intra-category appearance variations all make it necessary to develop exceedingly robust models of categories. In this course we will survey and discuss current computer vision literature on object and category recognition. The goals of the course will be to understand current approaches to some important problems in visual recognition, to actively analyze their strengths and weaknesses, and to begin to identify interesting open questions and possible directions for future research. Topics will include part-based models for recognition, invariant local features, bags of features, local spatial constraints, shape descriptors and matching, learning similarity measures, fast indexing methods, recognition with text and images, the role of context in recognition, and unsupervised category discovery.
At the same time, the system needs to maintainspecificity. It is important here to note that anobject can be recognized at a variety of levels of specificity:
a cat can be recognized as “my cat” on theindividual level, or more broadly on thecategorical level as “cat”, “dog”, “fox” etc.
The learning module’s input is an image,its outputIs a label(value), for either the class of the objectin the image (is it a cat?) or its individual identity(is it my friend’s face?).
For simplicity , we describe a “learning module “as a binary classifier that gives an output of either“yes” or “no.”
Approach:
1. Appearance-based methods
* . Edge matching /detection
* . Grayscale matching
2. Feature-based methods
3.MEMORY-BASED OBJECT RECOGNITION
*Objects look different under varying conditions:
Changes in lighting or color
Changes in viewing direction
Changes in size / shape
Edge detection:
A/c to computer science vision it is fundamental tools in image processing .particularly in theareas of features detection and features extraction which aim at identifying point in digital image at which image brightness changes
sharply or more formally has discontinuity.