Description: In this project, we intend to segment natural images by combing colour and texture information. For this we will be using an unsupervised image segmentation framework (referred to as CTex) that is based on the adaptive inclusion of color and texture in the process of data partition. It is new formulation for the extraction of color features that will evaluate the input image in a multispace color representation. To achieve this, we will be using the opponent characteristics of the RGB and YIQ color spaces where the key component will be the inclusion of the Self Organizing Map (SOM) network in the computation of the dominant colors and estimation of the optimal number of clusters in the image. The texture features will be computed using a multichannel texture decomposition scheme based on Gabor filtering. Platform: |
Size: 347136 |
Author:rupesh |
Hits:
Description: this was the code for SOM based brain image segmentation which can segment brain image and finally the segmented labelled image was represent as a color label. this code segment the tumor spot of an given brain image and represent as a color label. we can use T1 and T2 weighted brain image. Platform: |
Size: 1131520 |
Author:vasanth |
Hits:
Description: 用自组织映射网络进行聚类分析，然后可以用于颜色识别，图像分割(Clustering analysis using self-organizing mapping network can then be used for color recognition, image segmentation) Platform: |
Size: 69632 |
Author:GG987
|
Hits:
Search - SOM image segmentation