Automatic Acquisition of Image Filtering and Object Extraction Procedures from Ground-Truth Samples

Knowledge- and sample-based learning approaches play a pivotal role in image processing. However, the acquisition and integration of expert knowledge (for the former) and providing a sufficiently large number of training samples (for the latter) are generally hard to perform and time-consuming tasks. Hence, learning image processing tasks from a few gold/groundtruth samples, prepared by the user, is highly desirable. This paper demonstrates how the combination of an optimizer (e.g., genetic algorithm) and image processing tools (e.g., parameterized morphology operations) can be used to generate image processing procedures for image filtering and object extraction. For this purpose, the approach receives the original and the user-prepared image (filtered image or image with extracted target object) as a gold sample which reflects the user’s expectations. After carrying out the training or optimization phase, the optimal procedure is generated and ready to be applied to new images. The feasibility of our approach is investigated for two individual image processing categories, namely filtering and object extraction, by well-prepared synthetic images. The proposed architecture and the employed methodologies are explained in detail. Experimental results are provided as well.

[1]  Teuvo Kohonen,et al.  An introduction to neural computing , 1988, Neural Networks.

[2]  G. Matheron.  Random Sets and Integral Geometry , 1976 .

[3]  Stephen Marshall,et al.  Parallel genetic algorithms in the optimization of morphological filters: a general design tool , 1997, J. Electronic Imaging.

[4]  Dorothea Heiss-Czedik,et al.  An Introduction to Genetic Algorithms. , 1997, Artificial Life.

[5]  Florence Rossant,et al.  A global method for music symbol recognition in typeset music sheets , 2002, Pattern Recognit. Lett..

[6]  Michael Egmont-Petersen,et al.  Image processing with neural networks - a review , 2002, Pattern Recognit..

[7]  Shigeru Eiho,et al.  Extraction of character string region by a correlation method , 1999 .

[8]  Stephen Marshall,et al.  The use of genetic algorithms in morphological filter design , 1996, Signal Process. Image Commun..

[9]  A. S. Vu.  A computer vision system for automatic knowledge-based configuration of the image processing and hierarchical object recognition , 1999, Proceedings 10th International Conference on Image Analysis and Processing.

[10]  Hamid R. Tizhoosh,et al.  Learning Image Filtering from a Gold Sample Based on Genetic Optimization of Morphological Processing , 2005 .

[11]  Hamid R. Tizhoosh,et al.  Using reinforcement learning for image thresholding , 2003, CCECE 2003 - Canadian Conference on Electrical and Computer Engineering. Toward a Caring and Humane Technology (Cat. No.03CH37436).

[12]  M.M.A. Salama,et al.  Opposition-Based Differential Evolution , 2008, IEEE Transactions on Evolutionary Computation.

[13]  Mitsuo Gen,et al.  Genetic Algorithms & Engineering Optimization , 2000 .

[14]  Magdy M. A. Salama,et al.  Prostate Cancer Spectral Multifeature Analysis Using TRUS Images , 2008, IEEE Transactions on Medical Imaging.

[15]  Hiromitsu Yamada,et al.  Automatic acquisition of hierarchical mathematical morphology procedures by genetic algorithms , 1999, Image Vis. Comput..

[16]  Farhang Sahba,et al.  A coarse-to-fine approach to prostate boundary segmentation in ultrasound images , 2005, Biomedical engineering online.

[17]  Mario Ventresca,et al.  Oppositional Concepts in Computational Intelligence , 2008, Oppositional Concepts in Computational Intelligence.

[18]  Carl G. Looney.  Fuzzy and rule-based image convolution , 2000 .

[19]  Pierre Soille,et al.  Mathematical Morphology and Its Applications to Image Processing , 1994, Computational Imaging and Vision.

[20]  Soille Pierre,et al.  Mathematical Morphology and Its Applications to Image and Signal Processing , 2011, Lecture Notes in Computer Science.

[21]  Shahryar Rahnamayan,et al.  Automated Snake Initialization for the Segmentation of the Prostate in Ultrasound Images , 2005, ICIAR.

[22]  Ralph E. Jacobson,et al.  An Evaluation of Image Quality Metrics , 1995 .

[23]  Louis A. Tamburino,et al.  An evolutionary learning system for synthesizing complex morphological filters , 1996, IEEE Trans. Syst. Man Cybern. Part B.

[24]  Stephen Marshall,et al.  Genetic algorithm optimization of multidimensional grayscale soft morphological filters with applications in film archive restoration , 2003, IEEE Trans. Circuits Syst. Video Technol..

[25]  John H. Holland,et al.  Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .

[26]  Deryn Graham,et al.  Knowledge-based image processing systems , 1997, Applied computing.

[27]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[28]  Robert M. Haralick,et al.  Toward the automatic generation of mathematical morphology procedures using predicate logic , 1990, [1990] Proceedings Third International Conference on Computer Vision.

[29]  S. Rahnamayan,et al.  Solving large scale optimization problems by opposition-based differential evolution (ODE) , 2008 .

[30]  Shahryar Rahnamayan,et al.  Opposition versus randomness in soft computing techniques , 2008, Appl. Soft Comput..

[31]  Shahryar Rahnamayan,et al.  A novel population initialization method for accelerating evolutionary algorithms , 2007, Comput. Math. Appl..

[32]  Chang Wook Ahn,et al.  On the practical genetic algorithms , 2005, GECCO '05.

[33]  M. Muneyasu,et al.  Optimization of gray scale morphological opening for noise removal in texture images , 2004, The 2004 47th Midwest Symposium on Circuits and Systems, 2004. MWSCAS '04..

[34]  R. E. Jacobson,et al.  The relationship between objective and subjective image quality criteria , 1993 .

[35]  Kaoru Arakawa.  Fuzzy rule-based image processing , 1997, Int. J. Imaging Syst. Technol..

[36]  Alexander Gammerman,et al.  Computational Learning and Probabilistic Reasoning , 1996 .

[37]  Igor Aleksander,et al.  Introduction to Neural Computing , 1990 .

[38]  Bülent Sankur,et al.  Survey over image thresholding techniques and quantitative performance evaluation , 2004, J. Electronic Imaging.

[39]  Stanley R Sternberg,et al.  Grayscale morphology , 1986 .

[40]  Hyun Seung Yang,et al.  Robust image segmentation using genetic algorithm with a fuzzy measure , 1996, Pattern Recognit..

[41]  Hamid R. Tizhoosh,et al.  Image thresholding using type II fuzzy sets , 2005, Pattern Recognit..

[42]  Isabelle Bloch,et al.  A fuzzy model for optical recognition of musical scores , 2004, Fuzzy Sets Syst..

[43]  Shigeru Eiho,et al.  Extraction of character string region by a correlation method , 1998, Systems and Computers in Japan.

[44]  Shahryar Rahnamayan,et al.  Image thresholding using micro opposition-based Differential Evolution (Micro-ODE) , 2008, 2008 IEEE Congress on Evolutionary Computation (IEEE World Congress on Computational Intelligence).

[45]  Jean Serra,et al.  Image Analysis and Mathematical Morphology , 1983 .

[46]  Hamid R. Tizhoosh,et al.  Fuzzy Image Enhancement: An Overview , 2000 .

[47]  Hamid R. Tizhoosh,et al.  Application of reinforcement learning for segmentation of transrectal ultrasound images , 2008, BMC Medical Imaging.

[48]  DeLiang Wang,et al.  Unsupervised Learning: Foundations of Neural Computation , 2001, AI Mag..

[49]  Ying Li,et al.  Eye detection by using fuzzy template matching and feature-parameter-based judgement , 2001, Pattern Recognit. Lett..

[50]  Hamid R. Tizhoosh,et al.  Fuzzy Image Processing , 2000, Computer Vision and Applications.

[51]  Goldberg,et al.  Genetic algorithms , 1993, Robust Control Systems with Genetic Algorithms.