Lung CT image retrieval based on intelligent selection of multi-dimensional characteristics
Lihong Zhang · Journal of Computer Applications · 2010
In allusion to that the single feature and manual setting multi-dimensional weighting features cannot satisfy the needs of Content Based Image Retrieval(CBIR) more and more,a new algorithm of multi-dimensional features vector weighting based on the cluster of training samples was presented.The algorithm needed to manually build up the training sample set,extract the multi-dimensional features like color,texture and shape of each element,and then used the genetic algorithm to find out the most optimal weighting coefficient sequence of feature vector set.Finally,it calculated the proper value of the training sample set using the sequence to retrieve the sample.Proved by the experiment,this algorithm can improve the classification accuracy compared to other algorithms and has a high accuracy in differentiating two clusters with high similarity.