An Algorithm for Designing Optimal Gabor Filter for Segmenting Multi-Textured Images

Abstract

This paper presents a method for the design of single Gabor filter for segmenting multi-textured images. The features are extracted by filtering with a linear filter and estimating the local energy of the filter response. Gabor filters have been applied successfully to the segmentation of textured images. Previous investigators have used bank of filters, where the filter parameters were predetermined and not optimized for particular task. A model of feature extraction process is required for the optimization, which is developed and assessed to get a single Gabor filter.

The approach is assessed by supervised segmentation experiments and includes the design of Gabor filter, Gaussian filter, classifier and post processing. The classifier uses minimum distance algorithm and post processing uses morphological operators to remove spurious misclassifications. Results are presented that confirm the efficiency of the post processing method and support underlying mathematical models.

Indexing terms:

• Texture
• Segmentation
• Texture analysis
• Gabor filter
• Gaussian function
• minimum distance classifier

Additional information

Notes on contributors

M H Kolekar

Maheshkumar H Kolekar received first degree in Electronics Engineering from Shivaji University, Kolhapur and acquired master's degree from SGGS College of Engineering and Technology, Nanded. His master's dissertation deals with ‘Image Segmentation’. At present serving in Electronics and Telecommunication Engineering department of Dr Babasaheb Ambedkar Technological University, Lonere. He is a life member of various organizations viz ISTE, IETE and CSI. He authored several papers published in National level journals and conferences. He has conducted AICTE-ISTE sponsored national level two weeks short-term training programme on ‘Digital Image Processing and Pattern Recognition’. His field of interest includes Digital Image Processing, Digital Signal Processing, Fuzzy Logic and Neural Network.