A Multiple Model for Rapid Object Recognition Based on Human Visual System

Humans can effectively recognize objects in complex natural scenes within a fraction of a second. This dominant ability has motivated many computational objectrecognition models. The human visual system hierarchically recognizes object in several processing layers. Along these layersa set of features is extracted by different part of visual system. The different parts of the human visual system have been expertise to specific calculations and perform this task withoutredundancy information. In this process, the activation of neurons, a threshold is present. This threshold transmits usefuland necessary information through cortex processing stream. Each proposed model should be optimized in terms ofoverlapping computation. There is the important note in visualsystem, that when human see the image, type of compressing take place in visual pathway, that it can be a factor reducing theredundancy of information in the visual cortex. In this paper, we improved a hierarchical model, and tacking the threshold andcompression steps are added to the existing algorithms. This would reduce the redundancy and overlapping computation inthe model. On the other hand, with reducing computational errors, while the speed of recognition is increased, the recognition rate has reached a desired value

کلیدواژه ها:

image compression ، multiple model ، object recognition ، receptive field threshold