Towards Effective Image Classification Using Class-Specific Codebooks and Distinctive Local Features

Date

2015-03-01

Author

Altintakan, Umit Lutfu
Yazıcı, Adnan

Metadata

Show full item record

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

Item Usage Stats

148
views

0
downloads

Local image features, which are robust to scale, view, and orientation changes in images, play a key factor in developing effective visual classification systems. However, there are two main limitations to exploit these features in image classification problems: 1) a large number of key-points are located during the feature detection process, and 2) most of the key-points arise in background regions, which do not contribute to the classification process. In order to decrease the inverse effects of these limitations, we propose a new codebook generation approach through employing a new clustering method that generates class-specific codebooks along with a novel feature selection method in the bag-of-words model. We evaluate the performance of different classification techniques including Naive Bayesian, k-NN, and SVM on distinctive features. Experiments conducted on PASCAL Visual Object Classification collections have shown that the class-specific codebooks along with distinctive image features can significantly improve the classification performances.

Subject Keywords

Bag-of-words, Class-specific codebooks, Distinctive local features, Image classification, Self-organizing maps

URI

https://hdl.handle.net/11511/35664

Journal

IEEE TRANSACTIONS ON MULTIMEDIA

DOI

https://doi.org/10.1109/tmm.2014.2388312

Collections

Department of Computer Engineering, Article

Suggestions

OpenMETU
Core

Topological Navigation Algorithm Design and Analysis Using Spherical Images Şahin, Yasin; Koku, Ahmet Buğra; Department of Mechanical Engineering (2022-8-23) A topological navigation algorithm that has the capability of mapping and localization based on visual contents is proposed. Keypoint detection and feature matching are conducted on spherical images to extract significant features among sequential frames. Robot movement direction is estimated based on historical angle differences of significant features to reach the final destination. The navigation process is supported with visual egocentric localization to gain simultaneous localization and mapping compet...
Fine-Grained Object Recognition and Zero-Shot Learning in Remote Sensing Imagery Sumbul, Gencer; Cinbiş, Ramazan Gökberk; Aksoy, Selim (2018-02-01) Fine-grained object recognition that aims to identify the type of an object among a large number of subcategories is an emerging application with the increasing resolution that exposes new details in image data. Traditional fully supervised algorithms fail to handle this problem where there is low betweenclass variance and high within-class variance for the classes of interest with small sample sizes. We study an even more extreme scenario named zero-shot learning (ZSL) in which no training example exists f...
Partial matching of deformable shapes Cosmo, Luca; Rodola, Emanuele; Bronstein, Michael; Torsello, Andrea; Cremers, Daniel; Sahillioğlu, Yusuf (null; 2016-05-08) Matching deformable 3D shapes under partiality transformations is a challenging problem that has received limited focus in the computer vision and graphics communities. With this benchmark, we explore and thoroughly investigate the robustness of existing matching methods in this challenging task. Participants are asked to provide a point-to-point correspondence (either sparse or dense) between deformable shapes undergoing different kinds of partiality transformations, resulting in a total of 400 matchin...
Moving Object Detction in 2D and 3D Scenes Sırtkaya, Salim; Alatan, Abdullah Aydın; Department of Electrical and Electronics Engineering (2004) This thesis describes the theoretical bases, development and testing of an integrated moving object detection framework in 2D and 3D scenes. The detection problem is analyzed in stationary and non-stationary camera sequences and different algorithms are developed for each case. Two methods are proposed in stationary camera sequences: background extraction followed by differencing and thresholding, and motion detection using optical flow field calculated by أKanade-Lucas Feature Trackerؤ. For non-stationary ...
Development of free and open source software for flow mapping integrated to geographic information systems Güllüoğlu, Naim Cem; Işık, Oğuz; Karahanoğlu, Nurkan; Department of Geodetic and Geographical Information Technologies (2014) Mapping of spatial interaction data is an ongoing challenge for cartographers. In many Geographic Information Systems (GIS) software there is no off-the-shelf functionality for processing and visualizing spatial interactions or geographical flows. Considering the development efforts that have been made in the last few decades to discover the potential of GIS almost in every aspect, handling and visualization of spatial interaction data under GIS remain underutilized. The main objective of this study is to d...

Citation Formats

U. L. Altintakan and A. Yazıcı, “Towards Effective Image Classification Using Class-Specific Codebooks and Distinctive Local Features,” IEEE TRANSACTIONS ON MULTIMEDIA, pp. 323–332, 2015, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/35664.