Bag-of-Features Codebook Generation by Self-Organisation

Kinnunen, Teemu; Kämäräinen, Joni-Kristian; Lensu, Lasse; Kälviäinen, Heikki

doi:10.1007/978-3-642-02397-2_15

Cited by 7 publications

(8 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Our main contribution is that we introduce the selforganisation principle and the Kohonen map (SOM) as a novel solution to unsupervised visual object categorisation problem. That completes our previous work where we showed that the SOM outperforms the baseline algorithm, k-means, for codebook generation [7]. Now, the self-organisation principle is exercised at the all levels of unsupervised BoF.…”

Section: Introductionmentioning

confidence: 57%

“…We generated various size codebooks, first using the k-means (kmeans -SOM) as in the original study, and then using the SOM as in [7] for the codebook generation (SOM -SOM). In our method, the classification was done unsupervised using the SOM instead of a SVM classifier.…”

Section: Methodsmentioning

confidence: 99%

“…In the third step, a codebook is constructed using the descriptors. In the original model the codebook generation is performed during the training phase using clustering algorithms, such as the k-means [2] or SOM [7]. In the best methods, however, the training ground truth is used to refine and probe more efficient codebooks [5,10].…”

Section: Visual Object Categorisation 21 General Bag-of-features Frmentioning

confidence: 99%

See 2 more Smart Citations

Unsupervised Visual Object Categorisation via Self-organisation

Kinnunen

Kämäräinen

Lensu

et al. 2010

2010 20th International Conference on Pattern Recognition

Self Cite

View full text Add to dashboard Cite

Visual object categorisation (VOC) has become one of the most actively investigated topic in computer vision.In the mainstream studies, the topic is considered as a supervised problem, but recently, the ultimate challenge has been posed: Unsupervised visual object categorisation. Hitherto only a few methods have been published, all of them being computationally demanding successors of their supervised counterparts. In this study, we address this problem with a simple and effective method: competitive learning leading to selforganisation (self-categorisation). The unsupervised competitive learning approach is implemented using the Kohonen self-organising map algorithm (SOM). The SOM is used to perform the both unsupervised codebook generation and object categorisation. We present our method in detail and compare results to the supervised approach.

show abstract

Section: Introductionmentioning

confidence: 57%

Section: Methodsmentioning

confidence: 99%

Section: Visual Object Categorisation 21 General Bag-of-features Frmentioning

confidence: 99%

See 1 more Smart Citation

Unsupervised Visual Object Categorisation via Self-organisation

Kinnunen

Kämäräinen

Lensu

et al. 2010

2010 20th International Conference on Pattern Recognition

Self Cite

View full text Add to dashboard Cite

show abstract

“…Xu [11] obtained visual vocabulary using DENCLUE clustering algorithm based on the sift feature extraction. Kinnunen [12] challenged the mainstream approach of vocabulary generation by demonstrating that the competitive learning principle in the self-organizing map (SOM) can provide similar and usually superior results to the K-Means clustering method.…”

Section: Introductionmentioning

confidence: 99%

Generating Discriminative Visual Vocabulary Based on Fusion of Features

Chang-sheng

2013

2013 IEEE International Conference on Green Computing and Communications and IEEE Internet of Things and IEEE Cyber, Physical A

View full text Add to dashboard Cite

Constructing a discriminative visual vocabulary is important in image categorization. Most visual vocabularies are built on a clustering method such as K-Means to cluster feature vectors of image patches. And the clustering methods ignore the different impacts of features to build a more discriminative visual vocabulary. In this paper a discriminative visual vocabulary generating method based on fusion of multiple features is proposed. The Dempster-Shafer (D-S) evidence theory is applied to explore the visual similarity among different features so that features have different effects on clustering to achieve a more discriminative visual vocabulary. The experimental results showed that our method achieved better classification accuracies of image categorization on both the Support Vector Machine (SVM) classifier and the Naive Bayes (NB) classifier. It demonstrated that our visual vocabulary is more discriminative than the vocabulary built on K-Means clustering method.Index Terms-visual vocabulary, feature fusion, DempsterShafer evidence theory

show abstract

“…Outras possíveis formas de gerar o dicionário têm sido apresentadas em trabalhos, com resultados similares. Em Kinnunen et al (2009), utiliza-se mapas auto-organizáveis (Self-Organising Map -SOM), já em Zhang et al (2010) é proposta uma abordagem estatística.…”

Section: Bag Of Visual Wordsunclassified

Detecção de cenas em segmentos semanticamente complexos

Lopes¹

View full text Add to dashboard Cite

Dedico esse trabalho a meus pais e à minha noiva, que sempre me apoiaram e ajudaram em todos os momentos. AgradecimentosAgradeço em primeiro lugar a Deus, por ter me iluminado durante todo o desenvolvimento do trabalho, dando a paciência e a inspiração necessária para sua realização.Agradeço também, a meu orientador, pelos infindáveis conselhos e por sua orientação sempre tão pertinente.Agradeço aos professores das matérias realizadas no mestrado, que certamente contribuíram beneficamente para a realização dessa pesquisa.Agradeço aos colegas e amigos do laboratório de pesquisa, que sempre me apoiaram e me deram forças nos momentos de desânimo.Agradeço ao CNPq pelo auxílio financeiro, processo n°134245/2011-3. Agradeço à FAPESP pelo auxílio financeiro, processo n°2011/05238-0, Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP). "As opiniões, hipóteses e conclusões ou recomendações expressas neste material são de responsabilidade do(s) autor(es) e não necessariamente refletem a visão da FAPESP". Resumo Diversas áreas da Computação (Personalização e Adaptação de Conteúdo, Recuperação de Informação, entre outras) se beneficiam da segmentação de vídeo em unidades menores de informação. A literatura apresenta diversos métodos e técnicas cujo objetivo é identificar essas unidades. Uma limitação é que tais técnicas não tratam o problema da detecção de cenas em segmentos semanticamente complexos, definidos como trechos de vídeo que apresentam mais de um assunto ou tema, e cuja semân-tica latente dificilmente pode ser determinada utilizando-se somente uma única mídia. Esses segmentos são muito relevantes, pois estão presentes em diversos domínios de vídeo, tais como filmes, noticiários e mesmo comerciais.A presente Dissertação de Mestrado propõe uma técnica de segmentação de vídeo capaz de identificar cenas em segmentos semanticamente complexos. Para isso utiliza a semântica latente alcançada com o uso de Bag of Visual Words para agrupar os segmentos de um vídeo. O agrupamento é baseado em multimodalidade, analisando-se características visuais e sonoras de cada vídeo e combinando-se os resultados por meio da estratégia fusão tardia. O presente trabalho demonstra a viabilidade técnica em reconhecer cenas em segmentos semanticamente complexos. The literature reports lots of techniques and methods, whose goal is to identify these units. One of these techniques' limitations is that they don't handle scene detection in semantically complex segments, which are defined as video snippets that present more than one subject or theme, whose latent semantics can hardly be determined using only one media. Those segments are very relevant, since they are present in multiple video domains as movies, news and even television commercials. This Master's dissertation proposes a video scene segmentation technique able to detect scenes in semantically complex segments. In order to achieve this goal it uses latent semantics extracted by the Bag of Visual Words to group a video segments. This grouping process is based on multimodalit...

show abstract

Bag-of-Features Codebook Generation by Self-Organisation

Cited by 7 publications

References 15 publications

Unsupervised Visual Object Categorisation via Self-organisation

Unsupervised Visual Object Categorisation via Self-organisation

Generating Discriminative Visual Vocabulary Based on Fusion of Features

Detecção de cenas em segmentos semanticamente complexos

Contact Info

Product

Resources

About