Variational multichannel multiclass segmentation using unsupervised lifting with CNNs
This is an incremental improvement for researchers in image segmentation, offering a flexible multiclass approach without requiring labeled data.
The authors tackled unsupervised image segmentation by combining a variational energy functional with convolutional neural networks to decompose and segment multiple image regions, achieving performance comparable to another multiphase segmentation method on texture and medical images.
We propose an unsupervised image segmentation approach, that combines a variational energy functional and deep convolutional neural networks. The variational part is based on a recent multichannel multiphase Chan-Vese model, which is capable to extract useful information from multiple input images simultaneously. We implement a flexible multiclass segmentation method that divides a given image into $K$ different regions. We use convolutional neural networks (CNNs) targeting a pre-decomposition of the image. By subsequently minimising the segmentation functional, the final segmentation is obtained in a fully unsupervised manner. Special emphasis is given to the extraction of informative feature maps serving as a starting point for the segmentation. The initial results indicate that the proposed method is able to decompose and segment the different regions of various types of images, such as texture and medical images and compare its performance with another multiphase segmentation method.