Techniques for still image scene classification and object detection

Authors:
Ville Viitaniemi;Jorma Laaksonen
Affiliations:
Laboratory of Computer and Information Science, Helsinki University of Technology, TKK, Finland;Laboratory of Computer and Information Science, Helsinki University of Technology, TKK, Finland
Venue:
ICANN'06 Proceedings of the 16th international conference on Artificial Neural Networks - Volume Part II
Year:
2006

Citing 2
Cited 6

Self-Organizing Maps

Self-Organizing Maps
PicSOM-self-organizing image retrieval with MPEG-7 content descriptors

IEEE Transactions on Neural Networks

Learning to Localize Objects with Structured Output Regression

ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part I
Improving object detection with boosted histograms

Image and Vision Computing
Use of image regions in context-adaptive image classification

SAMT'06 Proceedings of the First international conference on Semantic and Digital Media Technologies
A fast online incremental learning method for object detection and pose classification using voting and combined appearance modeling

Image Communication
A variational statistical framework for object detection

ICONIP'11 Proceedings of the 18th international conference on Neural Information Processing - Volume Part II
Variational learning of finite Dirichlet mixture models using component splitting

Neurocomputing

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper we consider the interaction between different semantic levels in still image scene classification and object detection problems. We present a method where a neural method is used to produce a tentative higher-level semantic scene representation from low-level statistical visual features in a bottom-up fashion. This emergent representation is then used to refine the lower-level object detection results. We evaluate the proposed method with data from Pascal VOC Challenge 2006 image classification and object detection competition. The proposed techniques for exploiting global classification results are found to significantly improve the accuracy of local object detection.