A Color Image Segmentation Using Inhibitory Connected Pulse Coupled Neural Network

Abstract

Abstract.A Pulse Coupled Neural Network (PCNN) is a kind of numerical model of cat visual cortex and it can explain synchronous dynamics of neurons' activity in the visual cortex. On the other hand, as an engineering application, it is shown that the PCNN can applied to the image processing, e.g. segmentation, edge enhancement, and so on. The PCNN model consists of neurons and two kind of inputs, namely feeding inputs and linking inputs with leaky integrators. These inputs lead to discrete time evolution of its internal state and neurons generate spike output according to the internal state. The linking and feeding inputs are received from the neurons' receptive field which is defined by excitatory synaptic weights. In this study, we propose a PCNN with inhibitory connections and describe an application to a color image segmentation. In proposed model, inhibitory connections are defined by negative synaptic weights among specific neurons which detect RGB component of particular pixel of the image. Simulation results show successful results for the color image segmentation.

The Content-Based Image Retrieval using the Pulse Coupled Neural Network

“…The model was also shown in our previous studies [15][16] [23][24] [25]. Figure 1 shows a schematic model of the neuron in the PCNN.…”

“…Because of these characteristics of the PCNN, it is effective to implement to the hardware such as a FPGA. The hardware implementation of the PCNN using the FPGA had been studied and shown its validity in [15] preceding study [20].…”

Hardware implementation of IC-PCNN for the color image segmentation

“…To achieve a color image processing, we had proposed the Inhibitory Connected Pulse Coupled Neural Network(IC-PCNN) [10]. The IC-PCNN is a model that is introduced the inhibitory connections to the conventional PCNN.…”

“…However only the gray-scale images are used in the PCNN application because of its configuration. To adopt the PCNN to the color image processing, we had proposed the Inhibitory Connected PCNN (IC-PCNN) as an extended model of the PCNN [10]. Where, in our study, the IC-PCNN was applied to the color image segmentation.…”

An Automatic Parameter Adjustment Method of Pulse Coupled Neural Network for Image Segmentation

“…To achieve a pattern segmentation, 2D PCNN which has latticed connection is used and one neuron in the network corresponds to one pixel of the image [11]- [19].…”