Segmentation of natural images based on super pixel and graph merging

Sanjoy K. Saha, Department of Computer Science and Engineering, Jadavpur University, Kolkata, India. Email: sks_ju@yahoo.co.in Abstract The task of natural image segmentation is one of the most researched topics of computer vision. There are mainly two principal approaches for the task, the statistical approach and the supervised approach. The proposed methodology segments natural images combining a set of statistical algorithms. First, the image is preprocessed to enhance the edges. Weighted average of the denoised image and its derivatives is the preprocessed output. Thereafter, an energy based super pixelation is applied to over segment the image. Finally, a connectivity graph is built where nodes correspond to super pixels and edges connect the adjacent super pixels. The adjacent super pixels are merged based on the confidence value defined in terms of their textural and colour similarity. Proposed methodology has been applied on the images of BSDS500 dataset. Performance of the proposed work has been compared with that of other works based on detected edge maps. Few works generate ultrametric contour maps (UCM). To compare the performance with those works, UCM is also generated by the proposed methodology. To do so images at multiple scales are considered. It is observed that the output of segmentation is better in case of the proposed methodology. Proposed methodology is much faster than others. Thus, makes it suitable for real time application in robot vision.

• Publication year

  2020

• Venue

  IET Computer Vision

• Publication date

  2020-12-09

• Fields of study

  Computer Science

• Identifiers
  DOI 10.1049/cvi2.12008
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Semantic Projection Network for Zero- and Few-Label Semantic Segmentation

  2019cited by this paper
• ACE: Adapting to Changing Environments for Semantic Segmentation

  2019cited by this paper
• Improved Image Segmentation via Cost Minimization of Multiple Hypotheses

  2018influential reference
• Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation

  2018cited by this paper
• What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?

  2017cited by this paper
• Segmentation of Natural Image Based on Colour Cohesion and Spatial Criteria

  2017cited by this paper
• Multi-task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics

  2017cited by this paper
• DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs

  2016cited by this paper
• RefineNet: Multi-path Refinement Networks for High-Resolution Semantic Segmentation

  2016cited by this paper
• Attention to Scale: Scale-Aware Semantic Image Segmentation

  2015cited by this paper
• Learning Deconvolution Network for Semantic Segmentation

  2015cited by this paper
• Multiscale Combinatorial Grouping for Image Segmentation and Object Proposal Generation

  2015cited by this paper
• DeepContour: A deep convolutional feature learned by positive-sharing loss for contour detection

  2015cited by this paper
• Image segmentation by generalized hierarchical fuzzy C-means algorithm

  2015cited by this paper
• SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation

  2015cited by this paper
• Weakly-and Semi-Supervised Learning of a Deep Convolutional Network for Semantic Image Segmentation

  2015cited by this paper
• Deep neural networks are easily fooled: High confidence predictions for unrecognizable images

  2014cited by this paper
• Material recognition in the wild with the Materials in Context Database

  2014cited by this paper
• Image Segmentation UsingHigher-Order Correlation Clustering

  2014cited by this paper
• Probabilistic Graphlet Cut: Exploiting Spatial Structure Cue for Weakly Supervised Image Segmentation

  2013cited by this paper
• SEEDS: Superpixels Extracted Via Energy-Driven Sampling

  2012cited by this paper
• Non-Local Means Denoising

  2011cited by this paper
• Contour Detection and Hierarchical Image Segmentation

  2011influential reference
• New insight at level set & Gaussian mixture model for natural image segmentation

  2011cited by this paper
• Natural Image Segmentation Based on Tree Equipartition, Bayesian Flooding and Region Merging

  2011cited by this paper
• Natural Image Segmentation with Adaptive Texture and Boundary Encoding

  2009cited by this paper
• Image Segmentation by Probabilistic Bottom-Up Aggregation and Cue Integration

  2007cited by this paper
• Color Image Segmentation Based on Mean Shift and Normalized Cuts

  2007cited by this paper
• Color clustering and learning for image segmentation based on neural networks

  2005cited by this paper
• Efficient Graph-Based Image Segmentation

  2004influential reference
• Evaluation of similarity measurement for image retrieval

  2003cited by this paper
• Natural Image Statistics for Natural Image Segmentation

  2003cited by this paper
• Perceptual metrics for image database navigation

  1999cited by this paper
• The Bhattacharyya metric as an absolute similarity measure for frequency coded data

  1998cited by this paper
• Normalized cuts and image segmentation

  1997cited by this paper
• A comparative study of texture measures with classification based on featured distributions

  1996influential reference
• Submitted to Ieee Transactions on Pattern Analysis and Machine Intelligence Learning to Detect Natural Image Boundaries Using Local Brightness, Color, and Texture Cues

  year unknowncited by this paper

• Noise Removal from the Image Using Convolutional Neural Networks-Based Denoising Auto Encoder

  2024cites this paper
• An Extensive Survey on Superpixel Segmentation: A Research Perspective

  2023cites this paper
• Survey on Video Colorization: Concepts, Methods and Applications

  2023cites this paper
• Superpixel segmentation algorithm based on local network modularity increment

  2022cites this paper
• An Improved Denoising Algorithm for Removing Noise in Color Images

  2022cites this paper
• Robust and effective image preprocessing conglomerate method for denoising of both grayscale and color images

  2021cites this paper