IBM Research Australia at LifeCLEF2014: Plant Identification Task. Chen, Q., Abedini, M., Garnavi, R., & Liang, X.
abstract   bibtex   
In this paper, we present the system and learning strategies that were applied by the IBM Research team to the plant identification task of LifeCLEF 2014. Plant identification is one of the most popular fine-grained categorization tasks. To ensure high classification accuracy, we have utilised strong visual features together with fusion of robust machine learning techniques. Our proposed system involves automatic delineation of the region of interest (e.g. plant’s leaf, flower, etc.) in the given image, followed by extracting multiple complementary low level features. The features have been then encoded into the sophisticated Fisher Vector representation which enables accurate classification with linear classifiers. We have also applied the recent development of deep learning. More importantly our system combines multiple source of information, i.e. integrates organ annotation with image data, and adopts fusion of classifiers which has led to great results. The extensive experiments demonstrate the effectiveness of the proposed system, where three (out of four) of our submissions outperforms all submissions by other teams, therefore the team achieves the first place in LifeCLEF 2014 Plant task.
@article{chen_ibm_nodate,
	title = {{IBM} {Research} {Australia} at {LifeCLEF}2014: {Plant} {Identification} {Task}},
	abstract = {In this paper, we present the system and learning strategies that were applied by the IBM Research team to the plant identification task of LifeCLEF 2014. Plant identification is one of the most popular fine-grained categorization tasks. To ensure high classification accuracy, we have utilised strong visual features together with fusion of robust machine learning techniques. Our proposed system involves automatic delineation of the region of interest (e.g. plant’s leaf, flower, etc.) in the given image, followed by extracting multiple complementary low level features. The features have been then encoded into the sophisticated Fisher Vector representation which enables accurate classification with linear classifiers. We have also applied the recent development of deep learning. More importantly our system combines multiple source of information, i.e. integrates organ annotation with image data, and adopts fusion of classifiers which has led to great results. The extensive experiments demonstrate the effectiveness of the proposed system, where three (out of four) of our submissions outperforms all submissions by other teams, therefore the team achieves the first place in LifeCLEF 2014 Plant task.},
	language = {en},
	author = {Chen, Qiang and Abedini, Mani and Garnavi, Rahil and Liang, Xi},
	pages = {12}
}

Downloads: 0