A Meta-Learning Approach for Recommendation of Image Segmentation Algorithms

There are many algorithms for image segmentation, but there is no optimal algorithm for all kind of image applications. To recommend an adequate algorithm for segmentation is a challenging task that requires knowledge about the problem and algorithms. Meta-learning has recently emerged from machine learning research field to solve the algorithm selection problem. This paper applies meta-learning to recommend segmentation algorithms based on meta-knowledge. We performed experiments in four different meta-databases representing various real world problems, recommending when three different segmentation techniques are adequate or not. A set of 44 features based on color, frequency domain, histogram, texture, contrast and image quality were extracted from images, obtaining enough discriminative power for the recommending task in different segmentation scenarios. Results show that Random Forest meta-models were able to recommend segmentation algorithms with high predictive performance.

[1]  Hamid Jafarkhani,et al.  A combined deep-learning and deformable-model approach to fully automatic segmentation of the left ventricle in cardiac MRI , 2015, Medical Image Anal..

[2]  Ricardo Vilalta,et al.  Metalearning - Applications to Data Mining , 2008, Cognitive Technologies.

[3]  Ashish Issac,et al.  Image processing based method to assess fish quality and freshness , 2016 .

[4]  Zhou Wang,et al.  Objective Quality Assessment of Tone-Mapped Images , 2013, IEEE Transactions on Image Processing.

[5]  Hideo Yokota,et al.  Algorithm Selection for Intracellular Image Segmentation Based on Region Similarity , 2009, 2009 Ninth International Conference on Intelligent Systems Design and Applications.

[6]  Carlos Soares,et al.  A Meta-Learning Method to Select the Kernel Width in Support Vector Regression , 2004, Machine Learning.

[7]  André Carlos Ponce de Leon Ferreira de Carvalho,et al.  Using Genetic Algorithms to Improve Prediction of Execution Times of ML Tasks , 2012, HAIS.

[8]  Ashish Kumar Bhandari,et al.  Tsallis entropy based multilevel thresholding for colored satellite image segmentation using evolutionary algorithms , 2015, Expert Syst. Appl..

[9]  André Carlos Ponce de Leon Ferreira de Carvalho,et al.  A hybrid meta-learning architecture for multi-objective optimization of SVM parameters , 2014, Neurocomputing.

[10]  Takashi Yamaguchi,et al.  Application of particle swarm optimization to similar image search on satellite sensor data , 2012, The 6th International Conference on Soft Computing and Intelligent Systems, and The 13th International Symposium on Advanced Intelligence Systems.

[11]  Sylvio Barbon Junior,et al.  Color energy as a seed descriptor for image segmentation with region growing algorithms on skin wound images , 2014, 2014 IEEE 16th International Conference on e-Health Networking, Applications and Services (Healthcom).

[12]  Leandro Nunes de Castro,et al.  Clustering algorithm selection by meta-learning systems: A new distance-based problem characterization and ranking combination methods , 2015, Inf. Sci..

[13]  Kate Smith-Miles,et al.  A meta-learning approach to automatic kernel selection for support vector machines , 2006, Neurocomputing.

[14]  Luh-Maan Chang,et al.  Automated steel bridge coating rust defect recognition method based on color and texture feature , 2013 .

[15]  Andreas Dengel,et al.  Meta-learning for evolutionary parameter optimization of classifiers , 2012, Machine Learning.

[16]  Shilpa Suresh,et al.  An efficient cuckoo search algorithm based multilevel thresholding for segmentation of satellite images using different objective functions , 2016, Expert Syst. Appl..

[17]  David H. Wolpert,et al.  The Lack of A Priori Distinctions Between Learning Algorithms , 1996, Neural Computation.

[18]  Carlos Soares,et al.  Selecting parameters of SVM using meta-learning and kernel matrix-based meta-features , 2006, SAC '06.

[19]  André Carlos Ponce de Leon Ferreira de Carvalho,et al.  An Experimental Study of the Combination of Meta-Learning with Particle Swarm Algorithms for SVM Parameter Selection , 2012, ICCSA.

[20]  Mario Chica-Olmo,et al.  An assessment of the effectiveness of a random forest classifier for land-cover classification , 2012 .

[21]  Jong-Seok Lee,et al.  A meta-learning approach for determining the number of clusters with consideration of nearest neighbors , 2013, Inf. Sci..

[22]  Nina Sumiko Tomita Hirata,et al.  Image Segmentation Assessment from the Perspective of a Higher Level Task , 2015, 2015 28th SIBGRAPI Conference on Graphics, Patterns and Images.

[23]  Eyke Hüllermeier,et al.  Dependent binary relevance models for multi-label classification , 2014, Pattern Recognit..

[24]  Haiyang Li,et al.  Dynamic particle swarm optimization and K-means clustering algorithm for image segmentation , 2015 .

[25]  Frank Hutter,et al.  Initializing Bayesian Hyperparameter Optimization via Meta-Learning , 2015, AAAI.

[26]  Brijesh Verma,et al.  A novel texture feature based multiple classifier technique for roadside vegetation classification , 2015, Expert Syst. Appl..

[27]  Jing Wang,et al.  Pornographic images recognition based on spatial pyramid partition and multi-instance ensemble learning , 2015, Knowl. Based Syst..

[28]  Andreas Dengel,et al.  Prediction of Classifier Training Time Including Parameter Optimization , 2011, KI.

[29]  T. S. Subashini,et al.  Automatic Classification of Cardiac Views in Echocardiogram Using Histogram and Statistical Features , 2015 .

[30]  Ting Wang,et al.  Color image segmentation using pixel wise support vector machine classification , 2011, Pattern Recognit..

[31]  Petra Perner,et al.  A Study on the Case Image Description for Learning the Model of the Watershed Segmentation , 2009, Trans. Case Based Reason..

[32]  N. Otsu.  A threshold selection method from gray level histograms , 1979 .

[33]  Sylvio Barbon Junior,et al.  Digital image analyses as an alternative tool for chicken quality assessment , 2016 .

[34]  Samir I. Shaheen,et al.  A generalized object detection system using automatic feature selection , 2010, 2010 10th International Conference on Intelligent Systems Design and Applications.

[35]  André Carlos Ponce de Leon Ferreira de Carvalho,et al.  MetaStream: A meta-learning based method for periodic algorithm selection in time-changing data , 2014, Neurocomputing.

[36]  Rongchun Zhao,et al.  Learning-based algorithm selection for image segmentation , 2005, Pattern Recognit. Lett..

[37]  Mehmet Çunkas,et al.  Color image segmentation based on multiobjective artificial bee colony optimization , 2015, Appl. Soft Comput..

[38]  André Carlos Ponce de Leon Ferreira de Carvalho,et al.  Combining meta-learning and search techniques to select parameters for support vector machines , 2012, Neurocomputing.