Corpus ID: 7400810

Combining Image Retrieval, Metadata Processing and Naive Bayes Classification at Plant Identification 2013

@inproceedings{Serban2013CombiningIR,
  title={Combining Image Retrieval, Metadata Processing and Naive Bayes Classification at Plant Identification 2013},
  author={Cristina Serban and Alexandra Siriteanu and Claudia Gheorghiu and Adrian Iftene and Lenuta Alboaie and Mihaela Breaban},
  booktitle={CLEF},
  year={2013}
}
This paper aims to combine intuition and practical experience in the context of ImageCLEF 2013 Plant Identification task. We propose a flexible, modular system which allows us to analyse and combine the results after apply- ing methods such as image retrieval using LIRe, metadata clustering and naive Bayes classification. Although the training collection is quite extensive, cover- ing a large number of species, in order to obtain accurate results with our photo annotation algorithm we enriched… Expand
The imageCLEF plant identification task 2013
TLDR
This paper presents a synthesis of ImageCLEF 2013 plant identification task, a system-oriented testbed dedicated to the evaluation of image-based plant identification technologies, and summarizes the retrieval approaches employed by the participating groups and provides an analysis of the main evaluation results. Expand
The ImageCLEF 2013 Plant Identification Task
TLDR
This overview presents more precisely the resources and assessments of task, summarizes the retrieval approaches employed by the participating groups, and provides an analysis of the main evaluation results. Expand
Using Textual and Visual Processing in Scalable Concept Image Annotation Challenge
TLDR
UAIC 1 's system built for participating in the Scalable Concept Image Annotation challenge 2015 is described and a resource that contains triplets is created, where concepts are from the list of concepts provided by the organizers and verb is a relation between concepts. Expand
Using Machine Learning Techniques, Textual and Visual Processing in Scalable Concept Image Annotation Challenge
TLDR
UAIC’s system built for participating in the Scalable Concept Image Annotation challenge 2016 is described and a resource that contains triplets is created, where concepts are from the list of concepts provided by the organizers and verb is a relation between concepts. Expand
Visualizing and enhancing a deep learning framework using patients age and gender for chest x-ray image retrieval
TLDR
This work explores the combination of text metadata, such as patients’ age and gender, with image-based features, for X-ray chest pathology image retrieval using a feature set extracted from a pre-trained deep convolutional network to achieve state-of-the-art results. Expand
Crowdsourcing Biodiversity Monitoring: How Sharing your Photo Stream can Sustain our Planet
TLDR
This paper surveys existing automated plant identification systems through a five-year synthesis of the PlantCLEF benchmark and an impact study of the Pl@ntNet platform, and discusses related research challenges at the frontier of computer science and biodiversity studies. Expand
Location-Based Species Recommendation - GeoLifeCLEF 2019 Challenge
TLDR
A system built with the aim to predict plant species given their location in the context of the GeoLifeCLEF 2019 challenge is presented. Expand
Using Text Processing in a Multimedia Environment. UAIC Activities in MUCKE Project
TLDR
Main activities of UAIC (“Alexandru Ioan Cuza” University) team from the MUCKE project are presented, which involved building the data collection, text processing, diversification in image retrieval and data credibility. Expand
ImageCLEFmed Tuberculosis 2019: Predicting CT Scans Severity Scores using Stage-Wise Boosting in Low-Resource Environments
TLDR
A solution is submitted that addresses the problem of tuberculosis’ severity prediction in low-resource environments by attempting to minimize the information required from the CT scan using a regularized variant of the SAMME.R algorithm. Expand
Exploiting Social Networks. Technological Trends (Habilitation Thesis)
TLDR
The habilitation thesis presents two main directions exploiting data from social networks for text and image processing and creating applications with new technologies: augmented reality, virtual reality, and speech processing with Amazon Alexa. Expand

References

SHOWING 1-9 OF 9 REFERENCES
The ImageCLEF 2013 Plant Identification Task
TLDR
This overview presents more precisely the resources and assessments of task, summarizes the retrieval approaches employed by the participating groups, and provides an analysis of the main evaluation results. Expand
Investigating the Behavior of Compact Composite Descriptors in Early Fusion, Late Fusion and Distributed Image Retrieval
TLDR
This paper investigates the behavior of Compact Composite Descriptors (CCDs) on heterogeneous databases of a larger scale and demonstrates that, even if it is not possible to overcome the semantic gap in image retrieval by fea- ture similarity, it is still possible to increase the retrieval attractiveness. Expand
FCTH: Fuzzy Color and Texture Histogram - A Low Level Feature for Accurate Image Retrieval
TLDR
The extraction of a new low level feature that combines, in one histogram, color and texture information, named FCTH - Fuzzy Color and Texture Histogram - and results from the combination of 3 fuzzy systems, appropriate for accurately retrieving images even in distortion cases. Expand
Image indexing using color correlograms
TLDR
Experimental evidence suggests that this new image feature called the color correlogram outperforms not only the traditional color histogram method but also the recently proposed histogram refinement methods for image indexing/retrieval. Expand
CEDD: Color and Edge Directivity Descriptor: A Compact Descriptor for Image Indexing and Retrieval
This paper deals with a new low level feature that is extracted from the images and can be used for indexing and retrieval. This feature is called "Color and Edge Directivity Descriptor" andExpand
Lire: lucene image retrieval: an extensible java CBIR library
LIRe (Lucene Image Retrieval) is a light weight open source Java library for content based image retrieval. It provides common and state of the art global image features and offers means for indexingExpand
Textural Features Corresponding to Visual Perception
TLDR
The discrepancies between human vision and computerized techniques that are encountered in this study indicate fundamental problems in digital analysis of textures and could be overcome by analyzing their causes and using more sophisticated techniques. Expand
Quad trees a data structure for retrieval on composite keys
TLDR
An optimized tree is defined and an algorithm to accomplish optimization in n log n time is presented, guaranteeing that Searching is guaranteed to be fast in optimized trees. Expand
Overview of the MPEG-7 standard
TLDR
This work presents a high-level overview of the MPEG-7 standard, discussing the scope, basic terminology, and potential applications, and compares the relationship with other standards to highlight its capabilities. Expand