Generalized visual concept detection
| Autor: | Banu Oskay Acar, Unal Zubari, Hakan Sevimli, A. Aydi Alatan, Ersin Esen, Ezgi Can Ozan, K. Berker Logoglu, Tugrul K. Ates, A. Muge Sevinc, Ahmet Saracoglu, Medeni Soysal, Mashar Tekin |
|---|---|
| Rok vydání: | 2010 |
| Předmět: |
Training set
Computer science business.industry Feature extraction ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION k-means clustering Codebook Scale-invariant feature transform Pattern recognition Scale invariance TRECVID Object detection Set (abstract data type) Support vector machine Histogram Test set Computer vision Artificial intelligence business Cluster analysis Transform coding |
| Zdroj: | 2010 IEEE 18th Signal Processing and Communications Applications Conference. |
| DOI: | 10.1109/siu.2010.5650360 |
| Popis: | For efficient indexing and retrieval of video archives, concept detection stands as an important problem. In this work, a generalized structure that can be used for detection of diverse and distinct concepts is proposed. In the system, MPEG-7 Descriptors and Scale Invariant Transform (SIFT) are utilized as visual features. Furthermore, visual features are transformed by codebooks which are constructed by k-Means clustering. On the other hand, classification is performed on the distribution of visual features over the codebook. Proposed system is firstly tested against an elementary concept. Afterwards for a set of concepts system performance is reported on the TRECVID 2009 test set. It has been observed that with a sufficiently large training set high performance can be achieved with this method. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|