Table 3 - uploaded by Hamid R. Tizhoosh
Content may be subject to copyright.
Source publication
![Fig. 1. Uncertainty/imperfect knowledge in image processing [20]](profile/Hamid-Tizhoosh/publication/303652426/figure/fig5/AS:668313579429901@1536349782676/Uncertainty-imperfect-knowledge-in-image-processing-20_Q320.jpg)
Medical images in radiation therapy, especially megavoltage images (MVIs), are often very poor in quality because of imaging physics. For a reliable patient set-up verification by tracking of relevant features, better in-treatment images are necessary. We use reliable neural and fuzzy image processing techniques to enhance the image quality. In thi...
Context in source publication
Context 1
... output of the inference system is a aggregation matrix (Fig. 11) quantifying the image quality and is represented by five non-symmetric membership functions. The if-then rules are formulated heuristically as listed in Table 3. The most simple way to generate images using the aggregation matrix is to build a convex combination. ...
Similar publications
Fingerprint verification is one of the most reliable personal identification methods. Most automatic systems for fingerprint comparison are based on minutiae matching. Minutiae are essentially terminations and bifurcations of the ridgelines that constitute a fingerprint pattern. Automatic minutiae detection is an extremely critical process, especia...
Purpose: Cherenkov imaging is now clinically available to track the course of radiation therapy as a treatment verification tool. The aim of this work was to discover the benefits of always-on Cherenkov images as a novel incident detection and quality improvement system through retrospective review of imaging in our center. Methods: Continuous imag...
This paper presents a new approach for image enhancement. Traditional filters are usually employed to suppress the noise, but often lead to a blurred or enhanced edge that enforces noise. An edge-preserving algorithm for digital images based on spatial autocorrelation is proposed. The spatial statistical calculation is used as a threshold for adapt...
Finger vein patterns contain highly discriminative characteristics, which are difficult to be forged due to residing underneath the skin. Several pieces of research have been carried out in this field but there is still an unresolved issue when data capturing and processing is of low quality. Low-quality data have caused errors in the feature extra...
Citations
... Finally, the MOS (Mean Opinion Score) is calculated as the total quality measurement. In [44,50]' some different contrast adaptation techniques are compared where the index of fuzziness is used as quality measure. In regards to human subjectivity, it is more appropriate to use MOS instead of an amount of image fuzziness (Table 1). ...
... Tizhoosh et ai. [50][51][52]introduced an observer-dependent system which consists of five phases (top image in Fig. 19). These phases are as follows: Image enhancement by different algorithms, extraction of objective quality criteria for image contrast, learning the fuzzy measure (subjective quality evaluation), aggregation (concerning different images and different observers), and finally, inference (final quality measurement for each image). ...
Image enhancement is one of the fundamental tasks in image processing. Fuzzy techniques offer a suitable framework for the development of new methods because they are nonlinear and knowledge-based. In this work, we give an overview of existing fuzzy image enhancement techniques, where contrast adaptation methods and filtering techniques are considered.
The article discusses the influence of ANN topology on its efficiency in solving the problem of increasing the image resolution. An empirical approach is used to establish the fact and determine the nature of the influence. At the beginning of the article, the most commonly used topological techniques for constructing an ANN, which are used to solve the problem of increasing the image resolution, are described. Then, the process of creating an ANN is described based on the above topologies. After that, the learning process of ANN is described. A supervised learning algorithm was used to train the networks, and a set of 7 000 images was used as training data. At the end of the article, an assessment of the efficiency of the trained ANN is carried out, through which the effectiveness of topological solutions is determined. To assess the performance of an artificial neural network, a validation dataset of 100 image is used. Two algorithms are used to assess the quality of enhanced images: SSIM and PSNR. The interpretation of the results obtained is also given.
Megavoltage images (MVIs) are used in radiation therapy for verification of the patient's position during cancer treatment. Due to the physics of imaging devices, the quality of MVI is very poor. In this work, we propose a hybrid neuro-fuzzy system consisting of fuzzy techniques and neural nets for knowledge-based enhancement of MVIs. The fuzzy enhancement includes different contrast adaptation techniques and also soft filtering, respectively. A modified associative memory is trained using a priori knowledge for image restoration. In order to consider the subjective demands of physicians, an observer-dependent overall system for contrast adaptation is also proposed.
Document analysis systems require documents in electronic format. An image acquisition and display system for scanning and
saving documents is presented, whereby the recognition capability (for example, series-connected OCR systems) is improved
by correction components. Components for improving image acquisition, archiving documents and for reducing compression errors
during archiving are integrated in the overall solution. The deployed components are suitably trained artificial neural networks.
The projected improvements are assessed.
Image quality assessment is an important issue addressed in various image processing applications such as image/video compression and image reconstruction. The peak signal-to-noise ratio (PSNR) with the L(2)-metric is commonly used in objective image quality assessment. However, the measure does not agree very well with the human visual perception in many cases. A fuzzy image metric (FIM) is defined based on Sugeno's (1977) fuzzy integral. This new objective image metric, which is to some extent a proper evaluation from the viewpoint of the judgment procedure, is closely approximates the subjective mean opinion score (MOS) with a correlation coefficient of about 0.94, as compared to 0.82 obtained using the PSNR. Compared to the L(2)-metric, we demonstrate that a better performance can be achieved in fractal coding by using the proposed FIM.
