A novel approach for shape-based object recognition with curvelet transform. (November 2016)

• Record Type: Journal Article
• Authors: Mani, M.; Potukuchi, D.; Satyanarayana, Ch.
• Is Part Of: International journal of multimedia information retrieval. Volume 5:Number 4(2016)
• Page Start: 219
• Page End: 228
• Publication Date: 2016-11
• Subjects: Feature vector -- Shape -- Object recognition -- Curvelet transform -- Thin plate splines; Information retrieval -- Periodicals; Multimedia systems -- Periodicals; 025.524
• DOI: 10.1007/s13735-016-0107-6
• Languages: English
• ISSNs: 2192-6611

Abstract

Abstract In this work, we revisit multi-resolution analysis (MRA) methods for object recognition. We find an optimal sparse representation of an image using a second-generation Fast Discrete Curvelet Transform (FDCT) and present a novel curvelet approach based on thin plate splines (TPS). Measurement of local deformation at each FDCT coefficient is detailed. Specific deformations in the TPS-based curve-let transformation are identified by minimization (Curvature) of total bending energy. Shape toning is processed through the Euclidean distance. Results of implementation of proposed descriptor for five standard databases are analyzed, while their comparison with other revealed relative efficiency.