Abstract

In computer vision, segmentation refers to the process of subdividing a digital image into constituent regions with homogeneity in some image characteristics. Image segmentation is considered as a pre-processing step for object recognition. The problem of segmentation, being one of the most difficult tasks in image processing, gets more complicated in the presence of random textures in the image. This paper focuses on texture classification, which is defined as supervised texture segmentation with prior knowledge of textures in the image. We investigate a classification method using Gene Expression Programming (GEP). It is shown that GEP is capable of evolving accurate classifiers using simple arithmetic operations and direct pixel values without employing complicated feature extraction algorithms. It is also shown that the accuracy of classification is related to the fact that GEP can detect the regularities of texture patterns. As part of this project, we implemented a Photoshop plug-in that uses the evolved classifiers to identify and select target textures in digital images.

Highlights

  • The goal of texture classification is to partition an unknown sample image into regions that belong to one of a set of known texture classes

  • We explore the possibility of using Gene Expression Programming (GEP) [4] to evolve feature extraction algorithms out of simple arithmetic operations and direct pixel values

  • Does GEP show any advantages compared to Genetic Programming (GP)? To provide satisfactory answers to the above research questions, we developed a software application that uses GEP to generate classifiers for specific textures

Read more

Summary

Introduction

The goal of texture classification is to partition an unknown sample image into regions that belong to one of a set of known texture classes. Texture classification belongs to the wider problem domain of texture segmentation. The goal is to simplify an image into something that is more meaningful and easier to analyze. The image is divided into regions with homogeneity with respect to texture. When texture segmentation is supervised and prior knowledge of textures in the image is available, the problem of texture segmentation is simplified to texture classification

Objectives
Methods
Results
Discussion
Conclusion

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.