Title :
Automatic images classification based on multi-features combined with MIL
Author :
Liu, Yang ; Bai, Tiegang
Author_Institution :
Coll. of Autom. Eng., Shenyang Aerosp. Univ., Shenyang, China
Abstract :
This paper presents a novel method for image classification. For classification, use a multiple instance learning (MIL) framework to describe the features as instances. By using a discriminative approach, we embeded each image into instance-based space and the coordinates of the image in that space are used for classification using the k-nearest neighbor algorithm. Experiments shows that the approach is useful for image classification.
Keywords :
image classification; learning (artificial intelligence); MIL; automatic image classification; discriminative approach; k-nearest neighbor algorithm; multiple instance learning; Bismuth; Computer vision; Feature extraction; Histograms; Image color analysis; Image edge detection; Vectors; KNN; MIL framework; image classification;
Conference_Titel :
Image and Signal Processing (CISP), 2011 4th International Congress on
Conference_Location :
Shanghai
Print_ISBN :
978-1-4244-9304-3
DOI :
10.1109/CISP.2011.6100021