GEOMETRY-CONSTRAINED SPATIAL PYRAMID ADAPTATION FOR IMAGE CLASSIFICATION

Date

2014-10-30

Author

Tasli, H. Emrah
Sicre, Ronan
Gevers, Theo
Alatan, Abdullah Aydın

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

41
views

0
downloads

This paper proposes a geometry-constrained spatial pyramid adaptation approach for the image classification task. Scene geometry is used as an input parameter for generating the spatial pyramid definitions. The resulting region adaptation is performed in accordance with the predefined geometric guidelines and underlying image characteristics. Using an approximate global geometric correspondence, exploits the idea that images of the same category share a spatial similarity. This assumption is evaluated and justified in an object classification framework, in which generated region segments are used as an enhancement to the widely utilized "spatial pyramid" method. Fixed region pyramids are replaced by the proposed locally coherent geometrically consistent region segments. Performance of the proposed method on object classification framework is evaluated on the 20 class Pascal VOC 2007 dataset. The proposed method shows consistent increase in the mean average precision (MAP) score for different experimental scenarios.

Subject Keywords

Image classification, Spatial pooling, Region segmentation

URI

https://hdl.handle.net/11511/55041

Conference Name

IEEE International Conference on Image Processing (ICIP)

Collections

Department of Electrical and Electronics Engineering, Conference / Seminar

Suggestions

OpenMETU
Core

Spatial control of a smart beam Kircali, Omer Faruk; Yaman, Yavuz; Nalbantoglu, Volkan; Şahin, Melin; Karadal, Fatih Mutlu; Ulker, Fatma Demet (2008-08-01) This study presents the design and implementation of a spatial H(infinity) controller for the active vibration control of a smart beam. The smart beam was modeled by assumed-modes method that results in a model including large number of resonant modes. The order of the model was reduced by direct model truncation and the model correction technique was applied to compensate the effect of the contribution of the out of range modes to the dynamics of the system. Additionally, spatial identification of the beam...
Shape : representation, description, similarity and recognition Arıca, Nafiz; Yarman Vural, Fatoş Tunay; Department of Computer Engineering (2003) In this thesis, we study the shape analysis problem and propose new methods for shape description, similarity and recognition. Firstly, we introduce a new shape descriptor in a two-step method. In the first step, the 2-D shape information is mapped into a set of 1-D functions. The mapping is based on the beams, which are originated from a boundary point, connecting that point with the rest of the points on the boundary. At each point, the angle between a pair of beams is taken as a random variable to define...
Low-Level Hierarchical Multiscale Segmentation Statistics of Natural Images Akbaş, Emre (2014-09-01) This paper is aimed at obtaining the statistics as a probabilistic model pertaining to the geometric, topological and photometric structure of natural images. The image structure is represented by its segmentation graph derived from the low-level hierarchical multiscale image segmentation. We first estimate the statistics of a number of segmentation graph properties from a large number of images. Our estimates confirm some findings reported in the past work, as well as provide some new ones. We then obtain ...
DIRECTIONALLY ADAPTIVE SUPER-RESOLUTION Turgay, Emre; Akar, Gözde (2009-11-10) In this paper a novel direction adaptive super-resolution (SR) image reconstruction method is proposed. The proposed maximum a-posteriori (MAP) based estimator uses gradient direction for optimal noise reduction while preserving the edges. Compared to the other edge-preserving methods, the proposed algorithm uses gradient direction in addition to the gradient amplitude for optimum regularization. The method comprises a gradient amplitude and direction estimation stage where a gradient direction map is obtai...
Multi-image region growing for integrating disparity maps Leloglu, UĞUR MURAT; Halıcı, Uğur (1999-01-01) In this paper, a multi-image region growing algorithm to obtain planar 3-D surfaces in the object space from multiple dense disparity maps, is presented. A surface patch is represented by a plane equation and a set of pixels in multiple images. The union of back projections of all pixels in the set onto the infinite plane, forms the surface patch. Thanks to that hybrid representation of planar surfaces, region growing (both region aggregation and region merging) is performed on all images simultaneously. Pl...

Citation Formats

H. E. Tasli, R. Sicre, T. Gevers, and A. A. Alatan, “GEOMETRY-CONSTRAINED SPATIAL PYRAMID ADAPTATION FOR IMAGE CLASSIFICATION,” presented at the IEEE International Conference on Image Processing (ICIP), Paris, FRANCE, 2014, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/55041.