Recognition

Recognition by Components
and the Geon theory
(Biederman's Model)

We recognize hundreds of different 3-dimensional objects every day. We rarely think about how we are able to recognize so many objects, but there has been much research and many theories explaining how this is possible. One of these theories is the Recognition-by-Components Theory. The basic assumption of this theory is that any given view of an object can be represented as an arrangement of simple 3-D shapes called geons. There are many different geons, including such shapes as cylinders and cones, among others. These geons can be combined in many different ways to form countless 3-dimensional objects. According to Irving Biederman, any given person is familiar with about 30,000 objects, and recognizing them requires no more than 

For more information please visit:
http://faculty.mercer.edu/spears_a/studentpages/geon/webpage.html

Object recognition

      Every day we recognize a multitude of familiar and novel objects. We do this with little effort, despite the fact that these objects may vary somewhat in form, color, texture, etc.  Objects are recognized from many different vantage points (from the front, side, or back), in many different places, and in different sizes. Objects can even be recognized when they are partially obstructed from view. 

While it may be obvious that people are capable of recognizing objects under many variations in conditions, it has been thought that pigeons may not possess the same range of capabilities.  It has been proposed that pigeons act as "perceptrons," by analyzing simple features of objects and using those features to recognize objects.  If the pigeon were a perceptron, then it would not be able to  recognize an object that varied slightly in form or was seen from a novel viewpoint because the features would be altered.  Moreover, a pigeon would be unable to discriminate between two objects that contained the same features, but with a different organization.

http://www.pigeon.psy.tufts.edu/avc/kirkpatrick/ = this link talk about how he do the experiment of object recognition  I.   Introduction
         One view of object recognition in pigeons
     


This link is about an introduction to pattern recognition,by Luis Gustavo Martins's slide show, which has include human and machine perception, pattern recognition, the process, the features. there are some slides about fish recognition (a case study), fish classification:
http://www.slideshare.net/lgustavomartins/introduction-to-pattern-recognition