A Semi-Automatic Indexing System for Cell Images

Abstract

A method is described that can be used for annotating and indexing an arbitrary set of images with texts collateral to the images. The collateral texts comprise digitised texts, e.g. journal papers and newspapers in which the images appear, and digitised speech, e.g. a commentary on the contents of the images. The annotation dasiavectorpsila comprises image features and keywords in the collateral texts; our method can be used to generate both the image features and keywords automatically. Terminology extraction techniques are incorporated into the system to form a domain specific lexicon, which can then be used or help to annotate the images. Our method can be used as the basis of the autonomous learning of associations between images and their collateral descriptions, for example using Kohonen feature maps. We focus on images that show the migration and the division of cells within live systems. We show how the annotations can be collected by using the state-of-the-art speech recognition techniques that convert audio input into descriptive text on cell migration. A system based on the method has been developed and has reduced the annotation time to around two minutes per image, on a set of 429 cell images - which is significantly smaller than 5 minutes for manual annotation.