Rotation invariant fuzzy shape contexts based on Eigenshapes and fourier transforms for efficient radiological image retrieval

Ayed, Alaidine Ben; Kardouchi, Mustapha; Selouani, Sid‐Ahmed

doi:10.1109/icmcs.2012.6320294

Cited by 5 publications

(1 citation statement)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Fushman et al employed a supervised machine learning approach by associating text-based and content-based image information to retrieve clinically relevant images [10]. Ayed proposed a new descriptor for radiological image retrieval based on fuzzy shape contexts, Fourier Transforms and eigenshapes [11]. Camlica et al have proposed both autoencoders and SVM for medical images retrieval [12,13].…”

Section: Brief Review Of Cbir Literaturementioning

confidence: 99%

Generating binary tags for fast medical image retrieval based on convolutional nets and Radon Transform

Liu

Tizhoosh

Kofman

2016

2016 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

Content-based image retrieval (CBIR) in large medical image archives is a challenging and necessary task. Generally, different feature extraction methods are used to assign expressive and invariant features to each image such that the search for similar images comes down to feature classification and/or matching. The present work introduces a new image retrieval method for medical applications that employs a convolutional neural network (CNN) with recently introduced Radon barcodes. We combine neural codes for global classification with Radon barcodes for the final retrieval. We also examine image search based on regions of interest (ROI) matching after image retrieval. The IRMA dataset with more than 14,000 x-rays images is used to evaluate the performance of our method. Experimental results show that our approach is superior to many published works.

show abstract