Abstract
We propose the integration of color and texture cues as an improvement of a rough set–based segmentation approach, previously implemented using only color features. Whereas other methods ignore the information of neighboring pixels, the rough set–based approximations associate pixels locally. Additionally, our method takes into account pixel similarity in both color and texture features. Moreover, our approach does not require cluster initialization because the number of segments is determined automatically. The color cues correspond to the a and b channels of the CIELab color space. The texture features are computed using a standard deviation map. Experiments show that the synergistic integration of features in this framework results in better segmentation outcomes, in comparison with those obtained by other related and state-of-the-art methods.
Highlights
Image segmentation has been a central problem in computer vision for many years
Four widely used metrics are adopted for the assessment of segmentation algorithms: Probabilistic Rand Index (PRI),37 Variation of Information (VoI),38 Global Consistency Error (GCE),36 and the Boundary Displacement Error (BDE)
We show that the best results for the GCE and the BDE measures are achieved by the proposed RCT method
Summary
Image segmentation has been a central problem in computer vision for many years. Its importance lies on its use as a preanalysis of images in many applications, such as object recognition, tracking, scene understanding, and image retrieval, among others. This is because the histogram-based methods do not require a priori information about the image (e.g., the number of classes to use or cluster initialization) These histogram-based techniques identify the representative objects within the scene as significant. Depending on the number of peaks, a set of thresholds is established and a multithreshold segmentation is carried out Disadvantages of these approximations include the sensitivity to noise and intensity variations, the difficulty to identify significant peaks in the histogram, and the absence of spatial relationship information among neighboring pixels. We propose the integration of features in a rough set–based segmentation approach using color and texture cues ( on, referred to as RCT) This approximation has the advantage of considering the spatial correlation and similarity of neighboring pixels, whereas other methods only process the images at pixel level.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
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.