Skip to Main Content
This paper describes a system for content-based retrieval of facial images from an image database. The system includes feature extraction based on expert-assisted feature selection, spatial feature measurement, feature and shape representation, feature information compression and organization, search procedures, and pattern-matching techniques. The system uses novel data structures to represent the extracted information. These structures include attributed graphs for representing local features and their relationships, n-tuple of mixed mode data, and highly compressed feature codes. For the retrieval phase, a knowledge-directed search technique that uses a hypothesis refinement approach extracts specific features for candidate identification and retrieval. The overall system, the components, and the methodology are described. The system has been implemented on an IBM Personal System/2® running Operating System/2®. Examples demonstrating the performance of the system are included.
Note: The Institute of Electrical and Electronics Engineers, Incorporated is distributing this Article with permission of the International Business Machines Corporation (IBM) who is the exclusive owner. The recipient of this Article may not assign, sublicense, lease, rent or otherwise transfer, reproduce, prepare derivative works, publicly display or perform, or distribute the Article.