Explicit Haar–Schauder multiwavelet filters and algorithms. Part II: Relative entropy-based estimation for optimal modeling of biomedical signals

2019 ◽  
Vol 17 (05) ◽  
pp. 1950038 ◽  
Author(s):  
Makerem Zemni ◽  
Malika Jallouli ◽  
Anouar Ben Mabrouk ◽  
Mohamed Ali Mahjoub
Keyword(s):  
Image Processing ◽  
Relative Entropy ◽  
Simulation Study ◽  
Wavelet Theory ◽  
Biomedical Signal ◽  
New Approach ◽  
Biomedical Signals ◽  
Image Processing And Analysis ◽  
Signal Image ◽  
Optimal Modeling

Biomedical signal/image processing and analysis are always fascinating tasks in scientific researches, both theoretical and practical. One of the powerful tools in such topics is wavelet theory which has been proved to be challenging since its discovery. One of the best measures of the optimality of reconstruction of signals/images is the well-known Shannon’s entropy. In wavelet theory, this is very well known and researchers are familiar with it. In the present work, a step forward is proposed based on more general wavelet tools. New approach is proposed for the reconstruction of signals/images provided with multiwavelets Shannon-type entropy to evaluate the order/disorder of the reconstructed signals/images. Efficiency and accuracy of the approach is confirmed by a simulation study on several models such as ECG, EEG and DNA/Proteins’ signals.

Validation of a new image analysis procedure for quantifying filamentous bacteria in activated sludge

2014 ◽  
Vol 70 (6) ◽  
pp. 955-963 ◽  
Author(s):  
Ewa Liwarska-Bizukojc ◽  
Marcin Bizukojc ◽  
Olga Andrzejczak
Keyword(s):  
Image Processing ◽  
Image Analysis ◽  
Activated Sludge ◽  
Analysis Procedure ◽  
Automated Image Analysis ◽  
Filamentous Bacteria ◽  
Image Processing And Analysis ◽  
Manual Counting ◽  
Analysis Application ◽  
Activated Sludge Systems

Quantification of filamentous bacteria in activated sludge systems can be made by manual counting under a microscope or by the application of various automated image analysis procedures. The latter has been significantly developed in the last two decades. In this work a new method based upon automated image analysis techniques was elaborated and presented. It consisted of three stages: (a) Neisser staining, (b) grabbing of microscopic images, and (c) digital image processing and analysis. This automated image analysis procedure possessed the features of novelty. It simultaneously delivered data about aggregates and filaments in an individual calculation routine, which is seldom met in the procedures described in the literature so far. What is more important, the macroprogram performing image processing and calculation of morphological parameters was written in the same software which was used for grabbing of images. Previously published procedures required using two different types of software, one for image grabbing and another one for image processing and analysis. Application of this new procedure for the quantification of filamentous bacteria in the full-scale as well as laboratory activated sludge systems proved that it was simple, fast and delivered reliable results.

Microdeformations in Sands by Digital Image Processing and Analysis

1996 ◽  
Vol 1548 (1) ◽  
pp. 31-37 ◽  
Author(s):  
Scott A. Raschke ◽  
Roman D. Hryciw ◽  
Gregory W. Donohoe
Keyword(s):  
Image Processing ◽  
Digital Image Processing ◽  
Digital Image ◽  
Small Scale ◽  
Two Dimensional ◽  
Localized Deformation ◽  
Displacement Fields ◽  
Particulate Media ◽  
Image Processing And Analysis ◽  
Video Images

Laboratory experiments are typically performed on particulate media to study stress-deformation behavior and to verify or calibrate computer models from controlled or measured boundary stresses and displacements. However, such data do not permit the formation of shear bands, displacement fields within flowing granular media, and other small-scale localized deformation phenomena to be identified. Described are two semiautomated computer vision techniques for accurately determining the two-dimensional displacement field in granular soils from video images obtained through a transparent planar viewing window. The techniques described are applicable for studying the behavior of particulate media under plane strain and certain axisymmetric test conditions. Digital image processing and analysis routines are used in two different computer programs, Tracker and Tracer, Tracker uses a graphical user interface that allows individual particles to be selected and tracked through a sequence of digital video images. A contrast edge detection algorithm delineates the two-dimensional projected boundaries of particles. The location of the centroid of each particle selected for tracking is determined from the boundary to quantify the trajectory of each particle. Tracer maps the trace or trajectory of specially dyed fluorescent particles in a sequence of video frames. A thresholding technique segments individual particle trajectories. Together, Tracker and Tracer provide a set of tools for identifying small-scale displacement fields in particulate assemblies deforming under either quasi-static or rapid loading (such as gravity flow).

scholarly journals Image Processing and Analysis in Biomechanics

2010 ◽  
Vol 2010 (1) ◽  
Author(s):  
João Manuel R. S. Tavares ◽  
R. M. Natal Jorge
Keyword(s):  
Image Processing ◽  
Image Processing And Analysis

scholarly journals Versatile Framework for Medical Image Processing and Analysis with Application to Automatic Bone Age Assessment

2018 ◽  
Vol 2018 ◽  
pp. 1-13 ◽  
Author(s):  
Chen Zhao ◽  
Jungang Han ◽  
Yang Jia ◽  
Lianghui Fan ◽  
Fan Gou
Keyword(s):  
Image Processing ◽  
Deep Learning ◽  
Medical Image ◽  
Deep Neural Networks ◽  
Medical Image Processing ◽  
Bone Age ◽  
Age Assessment ◽  
Image Processing And Analysis ◽  
Learning Technique ◽  
Bone Age Assessment

Deep learning technique has made a tremendous impact on medical image processing and analysis. Typically, the procedure of medical image processing and analysis via deep learning technique includes image segmentation, image enhancement, and classification or regression. A challenge for supervised deep learning frequently mentioned is the lack of annotated training data. In this paper, we aim to address the problems of training transferred deep neural networks with limited amount of annotated data. We proposed a versatile framework for medical image processing and analysis via deep active learning technique. The framework includes (1) applying deep active learning approach to segment specific regions of interest (RoIs) from raw medical image by using annotated data as few as possible; (2) generative adversarial Network is employed to enhance contrast, sharpness, and brightness of segmented RoIs; (3) Paced Transfer Learning (PTL) strategy which means fine-tuning layers in deep neural networks from top to bottom step by step to perform medical image classification or regression tasks. In addition, in order to understand the necessity of deep-learning-based medical image processing tasks and provide clues for clinical usage, class active map (CAM) is employed in our framework to visualize the feature maps. To illustrate the effectiveness of the proposed framework, we apply our framework to the bone age assessment (BAA) task using RSNA dataset and achieve the state-of-the-art performance. Experimental results indicate that the proposed framework can be effectively applied to medical image analysis task.

Sign in / Sign up

Export Citation Format

Share Document