Bag–of–Colors for Biomedical Document Image Classification

Herrera, Alba García Seco de; Markonis, Dimitrios; Müller, Henning

doi:10.1007/978-3-642-36678-9_11

Cited by 13 publications

(4 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A set of low‐level visual descriptors is selected from the descriptor bank of ParaDISE (Schaer, Markonis, & Müller, ; Markonis et al, 2017) and their combination is explored (García Seco de Herrera, Markonis, Schaer, et al, 2013) to optimize the outcomes. The following descriptors are chosen after the performance tests on a different ImageCLEF database; Bag of Visual Words (BoVW) using the Scale Invariant Feature Transform (SIFT) ( Lowe, ) with a spatial pyramid matching ( Lazebnik, Schmid, & Ponce, ) (BoVW‐SPM) —each image is represented by a histogram symbolizing a set of local descriptors represented in visual words from a previously learned vocabulary; spatial information is added to the BoVW‐SIFT descriptor; Bag of Colors (BoC) ( García Seco de Herrera, Markonis, & Müller, ) with an n × n spatial grid (Grid BoC) —each image is represented by a histogram symbolizing the colors from a previously learned vocabulary; spatial information is added to the BoC descriptor; Color and Edge Directivity Descriptor (CEDD) (Chatzichristofis & Boutalis, )—color and texture information is produced by a 144 bin histogram. Little computation is needed for its extraction; Tamura texture (Tamura, Mori, & Yamawaki, )—this descriptor extracts six visual properties: coarseness, contrast, directionality, line‐likeness, regularity, and roughness.…”

Section: Case–based Retrieval Techniquesmentioning

confidence: 99%

Shangri–La: A medical case–based retrieval tool

Herrera

Schaer

Müller

2017

Asso for Info Science & Tech

Self Cite

View full text Add to dashboard Cite

Large amounts of medical visual data are produced in hospitals daily and made available continuously via publications in the scientific literature, representing the medical knowledge. However, it is not always easy to find the desired information and in clinical routine the time to fulfil an information need is often very limited. Information retrieval systems are a useful tool to provide access to these documents/images in the biomedical literature related to information needs of medical professionals. Shangri-La is a medical retrieval system that can potentially help clinicians to make decisions on difficult cases. It retrieves articles from the biomedical literature when querying a case description and attached images. The system is based on a multi-modal retrieval approach with a focus on the integration of visual information connected to text. The approach includes a queryadaptive multi-modal fusion criterion that analyses if visual features are suitable to be fused with text for the retrieval. Furthermore, image modality information is integrated in the retrieval step. The approach is evaluated using the ImageCLEFmed 2013 medical retrieval benchmark and can thus be compared to other approaches. Results show that the final approach outperforms the best multi-modal approach

show abstract

Section: Case–based Retrieval Techniquesmentioning

confidence: 99%

Shangri–La: A medical case–based retrieval tool

Herrera

Schaer

Müller

2017

Asso for Info Science & Tech

Self Cite

View full text Add to dashboard Cite

show abstract

“…The info table is then updated, including the modality information and the subfigure URLs. The method presented in [42] was used for the modality classification. The method proposed in [43] was used for the compound figure separation.…”

Section: • Latefusion Seekermentioning

confidence: 99%

“…For the visual indexing, BoVW and Bag-of-Colors (BoC) [42] representations were used as shape and color features of the images. E2LSH was used as an ANN indexing method.…”

Section: • Latefusion Seekermentioning

confidence: 99%

The Parallel Distributed Image Search Engine (ParaDISE)

Markonis¹,

Schaer²,

García³

et al. 2017

Preprint

Self Cite

View full text Add to dashboard Cite

Image retrieval is a complex task that differs according to the context and the user requirements in any specific field, for example in a medical environment. Search by text is often not possible or optimal and retrieval by the visual content does not always succeed in modelling high-level concepts that a user is looking for. Modern image retrieval techniques consists of multiple steps and aim to retrieve information from large-scale datasets and not only based on global image appearance but local features and if possible in a connection between visual features and text or semantics.This paper presents the Parallel Distributed Image Search Engine (ParaDISE), an image retrieval system that combines visual search with text-based retrieval and that is available as open source and free of charge. The main design concepts of ParaDISE are flexibility, expandability, scalability and interoperability. These concepts constitute the system, able to be used both in real-world applications and as an image retrieval research platform.Apart from the architecture and the implementation of the system, two use cases are described, an application of ParaDISE in retrieval of images from the medical literature and a visual feature evaluation for medical image retrieval. Future steps include the creation of an open source community that will contribute and expand this platform based on the existing parts. Index Terms medical image retrieval; image retrieval systems; large-scale image retrieval; image retrieval evaluation I. INTRODUCTIONImage retrieval just like general information retrieval is a popular and frequent activity in many fields such as journalism [1] and medicine [2]. In certain cases, describing with keywords the images to retrieve is often not possible or optimal. Content-based image retrieval (CBIR) is an alternative approach to image search that uses the visual content of the image to find similar images. Querying by image example can be really time efficient, especially with the use of user interaction techniques such as relevance feedback [3], which allows quick query refinement by marking relevant results. However, due to the use of low-level visual characteristics, such as color, shape and texture, by CBIR in order to represent an image, it is difficult to describe high-level concepts, e.g. a pathology found in an X-ray. This is particularly important in difficult cases, e.g. medical image retrieval where

show abstract

“…The same features are used as in [16] to measure only the effect of semisupervised learning on the classifiers used: color and edge directivity descriptor (CEDD) [8]; bag of visual words using scale-invariant feature transform (BoVW-SIFT) [25]; fuzzy color and texture histogram (FCTH) [9]; bag of colors (BoC) [15]; and fuzzy color histogram (FCH) [19].…”

Section: Multi-modal Featuresmentioning

confidence: 99%

Semi–supervised Learning for Image Modality Classification

García

Markonis

Joyseeree

et al. 2015

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Searching for medical image content is a regular task for many physicians, especially in radiology. Retrieval of medical images from the scientific literature can benefit from automatic modality classification to focus the search and filter out non-relevant items. Training datasets are often unevenly distributed regarding the classes resulting sometimes in a less than optimal classification performance. This article proposes a semi-supervised learning approach applied using a k-Nearest Neighbour (k-NN) classifier to exploit unlabelled data and to expand the training set. The algorithmic implementation is described and the method is evaluated on the ImageCLEFmed modality classification benchmark. Results show that this approach achieves an improved performance over supervised k-NN and Random Forest classifiers. Moreover, medical case-based retrieval benefits from the modality filter.

show abstract

Bag–of–Colors for Biomedical Document Image Classification

Cited by 13 publications

References 31 publications

Shangri–La: A medical case–based retrieval tool

Shangri–La: A medical case–based retrieval tool

The Parallel Distributed Image Search Engine (ParaDISE)

Semi–supervised Learning for Image Modality Classification

Contact Info

Product

Resources

About