Population-Based Incremental Interactive Concept Learning for Image Retrieval by Stochastic String Segmentations

Abstract

We propose a method for concept-based medical image retrieval that is a superset of existing semantic-based image retrieval methods. We conceive of a concept as an incremental and interactive formalization of the user's conception of an object in an image. The premise is that such a concept is closely related to a user's specific preferences and subjectivity and, thus, allows to deal with the complexity and content-dependency of medical image content. We describe an object in terms of multiple continuous boundary features and represent an object concept by the stochastic characteristics of an object population. A population-based incrementally learning technique, in combination with relevance feedback, is then used for concept customization. The user determines the speed and direction of concept customization using a single parameter that defines the degree of exploration and exploitation of the search space. Images are retrieved from a database in a limited number of steps based upon the customized concept. To demonstrate our method we have performed concept-based image retrieval on a database of 292 digitized X-ray images of cervical vertebrae with a variety of abnormalities. The results show that our method produces precise and accurate results when doing a direct search. In an open-ended search our method efficiently and effectively explores the search space.

Optimal embedding for shape indexing in medical image databases

“…Most of the current shape retrieval systems simply apply a brute-force search of all the images/shapes in the database (e.g. [11, 12, 17, 20, 52]). Brute-force search scales only linearly with the size of the database, and can be limiting as the database grows.…”

“…Brute–force search is used in most of the existing research prototype image databases [11, 12, 17, 20, 52]. These databases handle at most a few thousand images and brute–force search is not too expensive.…”

Improving image retrieval efficiency using a fuzzy inference model and genetic algorithm

“…c E Aj(xi)= I, for all i e Nn (4) n 0 k<lIAJ(xk)<n for all keNc. (5) The fuzzy clustering finds the partitions and the associated clusters by which the structure of the data is well represented. After all the feature vectors are classified, the correlation will be strong within clusters and weak between clusters.…”

“…Region-based image retrieval (RBIR) [4], which is closer to humans' visual perception, attempts to bridge the gap at object-level. Recently, genetic algorithms (GA) have been used to improve image retrieval efficiency [5][6]. The GA based systems attempts to obtain what the users are looking for by the means of evolution computation.…”