Complex Object Recognition Using a Biologically Plausible Neural Model
نویسنده
چکیده
The complex object recognition tasks are still one big problem in neurocomputing today. This paper presents a method of detecting and recognizing complex objects, in cluttered environment, in a purely feed-forward way, being able to account for ultra-rapid visual categorization. We used a retinotopic architecture of simple spiking neurons with different types of receptive fields, organized in a hierarchical fashion similar to the mammal visual path. Fast shunting inhibition had been implemented using a rank-order coding similar to that described by S. Thorpe. The main advantage of the neural model proposed is that it accepts a very small number of training examples (4-7) being able to generalize very well. The model has been used to detect faces and automobiles in complex intensity images. Key-words: Scale independence; Rank order coding; Feed-forward; Receptive field; Neurocomputing.
منابع مشابه
Neural field model for the recognition of biological motion patterns
Neurophysiological research has revealed evidence that the recognition of stationary three-dimensional objects in the cortex seems to be based on neurons that encode prototypical twodimensional views of the object. Much less is known about the neural mechanisms for the recognition of complex motion patterns, like biological motion and actions. This paper investigates if complex motion patterns ...
متن کاملModeling attention to salient proto-objects
Selective visual attention is believed to be responsible for serializing visual information for recognizing one object at a time in a complex scene. But how can we attend to objects before they are recognized? In coherence theory of visual cognition, so-called proto-objects form volatile units of visual information that can be accessed by selective attention and subsequently validated as actual...
متن کاملCoupling of Evolution and Learning to Optimize a Hierarchical Object Recognition Model
A key problem in designing artificial neural networks for visual object recognition tasks is the proper choice of the network architecture. Evolutionary optimization methods can help to solve this problem. In this work we compare different evolutionary optimization approaches for a biologically inspired neural vision system: Direct coding versus a biologically more plausible indirect coding usi...
متن کاملA robust and biologically plausible spike pattern recognition network.
The neural mechanisms that enable recognition of spiking patterns in the brain are currently unknown. This is especially relevant in sensory systems, in which the brain has to detect such patterns and recognize relevant stimuli by processing peripheral inputs; in particular, it is unclear how sensory systems can recognize time-varying stimuli by processing spiking activity. Because auditory sti...
متن کاملShetty, Sanketh v. a Biologically Plausible Architecture for Shape Recogni- Tion. (under the Direction of Professor a Biologically Plausible Architecture for Shape Recognition
SHETTY, SANKETH V. A Biologically Plausible Architecture for Shape Recognition. (Under the direction of Professor Wesley E. Snyder). This thesis develops an algorithm for shape representation and matching. The algorithm is an object centered, boundary-based method for shape recognition. Global features of the shape are utilized to define a frame of reference relative to which local shape featur...
متن کامل