No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Interactive ec-based signal processing
Abstract
We introduce new types of signal processing for which the characteristics of the signal processing filters are designed automatically by interactive evolutionary computation (IEC) based on human perception, such as hearing or vision. We first describe our existing works that use this approach, such as recovering distorted speech and hearing-aid fitting, as well as other related works in this field. Next, we evalu-ate the capabilities of visual-based image signal processing using IEC and compare it with conventional linear filters for the tasks of edge detection, high pass filtering, and horizon-tal / vertical component filtering. The experimental com-parisons show that the performances of both methods are similar, which means that the new approach, without a pri-ori knowledge on signal processing, is useful when signal processing users are not signal processing experts such as is the case in medical image processing or photo-retouch design.
... Medical image processing is typical of such cases. Interactive evolutionary computation (IEC) is one solution which allows signal processing application users to design signal processing systems based on user hearing or vi- sion [4, 5, 6]. In this paper, we focus on IEC-based image processing and evaluate how visual-based image filter design works well without any image processing knowledge. ...
... Therefore, if we use filters which are able to exceed the permitted range, in order for the process to proceed correctly we must explicitely limit the output pixel values to the correct range. For more details on algebraic filters in IEC image processing see [6]. ...
... In our experiments we use the schematic shown inFig. 10 with parametric filters (algebraic filters are discussed in [6]). The input image is filtered by an initial set of random filters (F1,F2,...F9) and filtered images are displayed for evaluation . ...
We apply an interactive evolutionary computa-tion technique to processing images in medical and other fields, analyze the performance of the image enhancement, and dis-cuss its capabilities and possibilities for further improvement. We first show our system scheme and the design of the user interface and then show experimental results of the image en-hancement. Next, we also propose an idea for a new interactive genetic programming method that, in addition to the arith-metic operators, also has image processing operators in gen-erated mathematical equations to increase its performance for image processing.
... Interactive evolutionary computation (IEC) is a method used to optimize target systems based on human subjective evaluation and has been applied in several fields such as the arts, engineering and education [6]. Image processing is one of these applications, and some research regarding its efficacy has been presented [3,4,5,7]. This paper is a consecutive work to our papers [1,2,7], which focused on the IEC-based optimization of algebraic and complex parametric filters for image enhancement. ...
... Image processing is one of these applications, and some research regarding its efficacy has been presented [3,4,5,7]. This paper is a consecutive work to our papers [1,2,7], which focused on the IEC-based optimization of algebraic and complex parametric filters for image enhancement. ...
... The objective of this paper is to design image filters with few tunable parameters than normal filter modeling and study the performance of IEC for optimizing them. Adjustment of brightness, contrast or gamma modifiers present a common type of such a filter. 1 We use an approach that is coherent with our previous work [1,2,7] and analyze results according to the past results obtained with different types of filters. ...
We discuss the use of interactive evolutionary computation for designing and optimizing image enhancement filters with fewer parameters than normal filter model. We present a method to speed up this optimization by combining interactive and non-interactive evaluation.
... Medical image processing is a typical such case. Interactive evolutionary computation (IEC) is one of solution to allow signal processing users to design signal processing systems based on users' hearing or vision [5, 6, 4]. In this paper, we focus on IEC-based image processing and and evaluate how visual-based image filter design works well without any image processing knowl* * This work is supported by Japan Society for the Promotion of Science (JSPS). ...
... In our experiments we used the scheme onFigure 10 with parametric filters (algebraic filters are discussed in [6]). The input image is filtered by initial random set of filters (F1,F2,...F9) and filtered images are displayed for evaluation. ...
We apply interactive evolutionary computation technique to processing images in medical and other fields, analyze its performance of image enhancement, and discuss its capability and further improve-ment. We first show our system scheme and the design of user interface and then show experimental results of image enhancement. We also propose an idea of new interactive genetic programming that has not only arithmetical operators but also image processing operators in generated mathematical equations to increase its performance for image processing.
... To show usefulness of the proposed method, they generate filters for edge detection, high-pass and horizontal-vertical component extraction. The system can make same functional filters without pre-knowledge [8]. R. Jaksa et al. create image processing filter by combination of various filters using IEC. ...
Due to developing mobile devices and providing services like mobile blogs, people can easily share their thought and experience, at any place and any time. A picture is an important datum to record and share their thought and experience, while we can easily take pictures with a mobile device that has a camera in it. However, the quality is usually poor without image refinement. Many mobile devices provide a simply interface to improve the quality, but require knowledge of predefined filters or image enhancement to control the parameters. It causes the user to feel inconvenient in mobile environments for their real-time editing pictures. In this paper, we propose a novel image enhancement interface in consideration of the accessibility to the mobile environment and various constraints. A usability test with various images has been conducted to show its usefulness, and the proposed interface achieved better performance than the other through the SUS test.
Color image quantization is one of the most widely used image processing techniques, where the number of colors used in the image is to be reduced to a specific value.[2] The aim of the task is to minimize the distortion from the original image. In previous studies, this has been measured using the distance between the original color and the transformed color of corresponding pixels. This concept is straightforward and can easily be calculated, and thus has been used as a general measure. However, to find the color tuple which minimizes the difference is known to be NP-hard.[3] Therefore, a number of studies have been performed using several optimization techniques.
Abstract| We propose two interactive evo-lutionary computation (IEC) methods that al-low users to actively participate in an EC search. This is di erent from a conventional IEC in which the search and evaluation are performed by the EC and the user, respec-tively. The rst method is one in whic h in-formation obtained from an IEC searc h is ex-plicitly incorporated in to the EC search for the next generation using on-line kno wledge embedding. The second is a method that in-troduces a 2-D visualization of an n-D search-ing space. The acceleration of EC conver-gence and the user interface w ere experimen-tally evaluated for both methods.
In this paper we present an approach to the interactive development of programs for image enhancement with Genetic Programming (GP) based on pseudo- colour transformations. In our approach the user drives GP by deciding which in- dividual should be the winner in tourna- ment selection. The presence of the user does not only allow running GP without a fitness function but it also transforms GP into a very efficient search procedure capable of producing effective solutions to real-life problems in only hundreds of evaluations. In the paper we also propose a strategy to further reduce user inter- action: we record the choices made by the user in interactive runs and we later use them to build a model which can re- place him/her in longer runs. Experi- mental results with interactive GP and with our user-modelling strategy are also reported.
Knowledge acquisition systems for image enhancement procedures have been developed using Java. Based on genetic algorithms (GAs), the systems can optimize procedures for enhancing target components in the digital images of plants in fields. Using rough objective images given by users as a standard image for evaluating fitness, it can provide appropriate filtering operations and their parameters. To improve convergence, interactive selection, which selects a promising individual by human intention instead of the fitness function, has been introduced. Consequently, the combination of the fitness function and interactive selection has contributed to rapid convergence of the processing.
We propose Visualized EC/IEC as an evolutionary computation (EC) and interactive EC (IEC) with visualizing individuals in a multi-dimensional searching space in a 2-D space. This visualization helps us envision the landscape of an n-D searching space, so that it is easier for us to join an EC search by indicating the possible global optimum estimated in the 2-D mapped space. We first compare four mapping methods from the points of view of computational time, convergence speed, and visual easiness to grasp whole EC landscape with five benchmark functions and 28 subjects. Then, we choose self-organizing maps for the projection of individuals onto a 2-D space and experimentally evaluate the effect of visualization using a benchmark function. The experimental result shows that the convergence speed of GA with human search on the Visualized space is at least five times faster than a conventional GA. © 2002 Elsevier Science B.V. All rights reserved.
We propose Visualized IEC as an interactive evolutionary
computation (IEC) with visualizing individuals in a multidimensional
searching space in a 2D space. This visualization helps us envision the
landscape of an n-D searching space; so that it is easier for us to join
an EC search, by indicating the possible global optimum estimated in the
2D mapped space. We experimentally evaluate the effect of visualization
using a benchmark function. We use self-organizing maps for this
projection of individuals onto a 2D space. The experimental result shows
that the convergence speed of the GA with human search on the visualized
space is at least five times faster than a conventional GA
This paper introduces our research into the use of soft computing
techniques for hearing impairment compensation and physical
rehabilitation. Evolutionary computation (EC) is used for fitting
hearing aids based on an interactive EC and the user's preferences for
sound. This technology allows hearing aid users to optimize their
hearing aids in any acoustic environment without professional
assistance. The virtual reality (VR) system for physical rehabilitation
allows patients to train their muscles and reflexes according to the
level of their physical condition
This paper investigates the application of an interactive GA to
speech signal processing. Three users design a filter to enhance speech
using the interactive GA. The quality of the three 3 filters are
evaluated on speech samples by 32 subjects on the basis of 2 subjective
criteria. The authors' results show that the interactive GA is effective
for this task from a statistical test point of view
We survey the research on interactive evolutionary computation
(IEC). The IEC is an EC that optimizes systems based on subjective human
evaluation. The definition and features of the IEC are first described
and then followed by an overview of the IEC research. The overview
primarily consists of application research and interface research. In
this survey the IEC application fields include graphic arts and
animation, 3D computer graphics lighting, music, editorial design,
industrial design, facial image generation, speed processing and
synthesis, hearing aid fitting, virtual reality, media database
retrieval, data mining, image processing, control and robotics, food
industry, geophysics, education, entertainment, social system, and so
on. The interface research to reduce human fatigue is also included.
Finally, we discuss the IEC from the point of the future research
direction of computational intelligence. This paper features a survey of
about 250 IEC research papers
Design and Development of an IEC-based Hearing Aids Fitting System
- M Ohsaki
- H Takagi
Ohsaki, M. and Takagi, H., " Design and Development
of an IEC-based Hearing Aids Fitting System, " in 4th
Asia Fuzzy System Symposium (AFSS'00), Tsukuba,
Japan, pp.543–548 (May, 2000).
An Experimental Study for Automatically Generating Image Filter Sequence by Using Simulated Breeding
- T Mutoh
- N Komagata
- K Ueda
Mutoh, T., Komagata, N., and Ueda, K., " An Experimental Study for Automatically Generating Image Filter Sequence by Using Simulated Breeding, " Workshop on Interactive Evolutionary Computation, pp. 7–
12, Fukuoka, Japan (Mar., 1998) (in Japanese).