Paper Info
Title
Image-Feature Extraction for Protein Crystallization: Integrating Image Analysis and Case-Based Reasoning
Abstract
This paper describes issues related to integrating image anal- ysis techniques into case-based reasoning. Although the ap- proach is generic, a high-throughput protein crystallization problem is used as an example. Our solution to the crystal- lization problem is to store outcomes of experiments as im- ages, extract important image features, and use them to auto- matically recognize different crystallization outcomes. Sub- sequently, we use the outcomes of image classification to per- form case-based planning of crystallization experiments for new proteins. Knowledge-discovery techniques are used to extract general principles for crystallization. Such principles are applicable to the adaptation phase of case-based reason- ing. The motivation for automated image-feature extraction is twofold: (1) the human interpretation/analysis of image content is subjective, and (2) many problem domains require reasoning with large databases of uninterpreted images. In this paper we present the design and implementation of our integrated system, as well as some preliminary experimental results.
Year
Venue
Keywords
2001
IAAI
image-feature extraction,case-based reasoning,integrating image analysis,protein crystallization,knowledge discovery,image classification,high throughput,image analysis,image features,integrable system,case base reasoning
Field
DocType
ISBN
Protein crystallization,Data mining,Feature (computer vision),Computer science,Image content,Feature extraction,Crystallization,Artificial intelligence,Contextual image classification,Case-based reasoning,Machine learning
Conference
1-57735-134-7
Citations 
PageRank 
References 
1
0.37
17
Authors
8
Name
Order
Citations
PageRank
Igor Jurisica161645.55
Phil Rogers210.37
Janice I. Glasgow3392127.97
Suzanne Fortier4395.11
Joseph R. Luft550.86
Melissa A. Bianca610.37
Robert J. Collins750.86
George T. DeTitta810.37