A Spatial-pyramid scene categorization algorithm based on locality-aware sparse coding

Dang Duy Thang, Shintami C. Hidayati, Yung Yao Chen, Wen-Huang Cheng, Shih Wei Sun, Kai Lung Hua*

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

Abstract

Scene recognition has a wide range of applications, such as object recognition and detection, content-based image indexing and retrieval, and intelligent vehicle and robot navigation. In particular, natural scene images tend to be very complex and are difficult to analyze due to changes of illumination and transformation. In this study, we investigate a novel model to learn and recognize scenes in nature by combining locality constrained sparse coding (LCSP), Spatial Pyramid Pooling, and linear SVM in end-to-end model. First, interesting points for each image in the training set are characterized by a collection of local features, known as codewords, obtained using dense SIFT descriptor. Each codeword is represented as part of a topic. Then, we employ LCSP algorithm to learn the codeword distribution of those local features from the training images. Next, a modified Spatial Pyramid Pooling model is employed to encode the spatial distribution of the local features. For the final stage, a linear SVM is employed to classify local features encoded by Spatial Pyramid Pooling. Experimental evaluations on several benchmarks well demonstrate the effectiveness and robustness of the proposed method compared to several state-of-the-art visual descriptors.

Original languageEnglish
Title of host publicationProceedings - 2016 IEEE 2nd International Conference on Multimedia Big Data, BigMM 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages342-345
Number of pages4
ISBN (Electronic)9781509021789
DOIs
StatePublished - 16 Aug 2016
Event2nd IEEE International Conference on Multimedia Big Data, BigMM 2016 - Taipei, Taiwan
Duration: 20 Apr 201622 Apr 2016

Publication series

NameProceedings - 2016 IEEE 2nd International Conference on Multimedia Big Data, BigMM 2016

Conference

Conference2nd IEEE International Conference on Multimedia Big Data, BigMM 2016
CountryTaiwan
CityTaipei
Period20/04/1622/04/16

Fingerprint Dive into the research topics of 'A Spatial-pyramid scene categorization algorithm based on locality-aware sparse coding'. Together they form a unique fingerprint.

Cite this