Gastroscopy Image Compression with Dictionary Selection and 1-bit Sensing Matrix

Gastrointestinal image analysis plays a key role in endoscopy, while the contradiction between the large number of gastroscopy images and limited samples of specified disease makes the compression and storage tasks much more difficult. In this work, a dictionary selection approach is developed for gastroscopy image sparse representation and compressed sensing with limited training set. Meanwhile, sensing optimization is developed considering 1-bit quantification which can reduce the storage and accelerate the process. The results of compression experiments show that our dictionary selection scheme outperforms DCT dictionary and K-SVD dictionary learning algorithm in limited training set scenarios. Moreover, dictionary selection scheme is also applied to image inpainting task and shows a better performance compared with DCT dictionary and K-SVD dictionary.

• Publication year

  2018

• Venue

  International Conference on Digital Signal Processing

• Publication date

  2018-11-01

• Fields of study

  Medicine, Computer Science

• Identifiers
  DOI 10.1109/ICDSP.2018.8631703
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Intelligent Bearing Fault Diagnosis Method Combining Compressed Data Acquisition and Deep Learning

  2018cited by this paper
• SDL: Saliency-Based Dictionary Learning Framework for Image Similarity

  2018cited by this paper
• Image inpainting based on an improved K-SVD counterpart algorithm

  2017cited by this paper
• Adaptive Greedy Dictionary Selection for Web Media Summarization

  2017influential reference
• Scalable gastroscopic video summarization via similar-inhibition dictionary selection

  2016cited by this paper
• Block recursive least squares dictionary learning algorithm

  2016cited by this paper
• Identification of lesion images from gastrointestinal endoscope based on feature extraction of combinational methods with and without learning process

  2016cited by this paper
• Composition of Binary Compressed Sensing Matrices

  2016cited by this paper
• Deterministic Compressed Sensing Matrices: Construction via Euler Squares and Applications

  2015cited by this paper
• Deep sparse feature selection for computer aided endoscopy diagnosis

  2015cited by this paper
• Designing robust sensing matrix for image compression

  2015cited by this paper
• Compressed-Sensing-Enabled Video Streaming for Wireless Multimedia Sensor Networks

  2014cited by this paper
• Deterministic Construction of Sparse Sensing Matrices via Finite Geometry

  2014cited by this paper
• Compressed Sensing

  2012cited by this paper
• Matrices With Small Coherence Using $p$-Ary Block Codes

  2012cited by this paper
• A Fast Compressed Sensing Approach to 3D MR Image Reconstruction

  2011cited by this paper
• Detection of Small Bowel Polyps and Ulcers in Wireless Capsule Endoscopy Videos

  2011cited by this paper
• Computer-Aided Decision Support Systems for Endoscopy in the Gastrointestinal Tract: A Review

  2011cited by this paper
• Greedy Dictionary Selection for Sparse Representation

  2011cited by this paper
• Recursive Least Squares Dictionary Learning Algorithm

  2010cited by this paper
• L1-L2 Optimization in Signal and Image Processing

  2010cited by this paper
• An Introduction To Compressive Sampling

  2008cited by this paper
• Optimized Projections for Compressed Sensing

  2007cited by this paper
• $rm K$-SVD: An Algorithm for Designing Overcomplete Dictionaries for Sparse Representation

  2006influential reference
• Robust uncertainty principles: exact signal reconstruction from highly incomplete frequency information

  2004cited by this paper
• Greed is good: algorithmic results for sparse approximation

  2004cited by this paper
• Optimally sparse representation in general (nonorthogonal) dictionaries via ℓ1 minimization

  2003cited by this paper
• A wavelet tour of signal processing

  1998cited by this paper
• Ieee Transactions on Image Processing the Contourlet Transform: an Efficient Directional Multiresolution Image Representation

  year unknowncited by this paper

• No citing papers are available for this paper.