Unsupervised learning segmentation for dynamic speckle activity images
This work addresses segmentation for biological tissue assessment using dynamic speckle images, but it appears incremental as it builds on existing techniques with descriptor selection.
The paper tackled the problem of segmenting dynamic laser speckle images to identify biological tissue regions by proposing decision models based on Computational Intelligence techniques, resulting in significant improvements over single-descriptor methods.
This paper proposes the design of decision models based on Computational Intelligence techniques applied to image sequences of dynamic laser speckle. These models aim to identify image regions of biological specimens illuminated by a coherent beam coming from a laser. The field image is pseudo colored using a Self Organizing Map projection. This process is carried out using a set of descriptors applied to the intensity variations along time in every pixel of an image sequence. The models use descriptors selected to improve effectiveness, depending on the specific application. We present two examples of the application of the proposed techniques to assess biological tissues. The results obtained are encouraging and significantly improve those obtained using a single descriptor.