Color image segmentation guided by a color gradient network

Wangenheim, Aldo von; Bertoldi, Rafael F.; Abdala, Daniel Duarte; Richter, Michael M.

doi:10.1016/j.patrec.2007.05.009

Cited by 16 publications

(13 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this context, the comparison against the EDISON method is new and was chosen because of its quality and robustness. The subjective comparisons against the RHSEG [8] method shown in [4] where not included into this experiment because RHSEG needs user interaction, which can introduce a subjective bias, and is therefore not suited to be tested with the proposed validation methodology.…”

Section: Objectives and Validation Methodologymentioning

confidence: 99%

“…The GNM [4] was developed to deal with segmentation problems where objects in the scene are represented by gradually varying color shades, as they often are found in outdoor scenes. This technique employs a novel segmentation strategy and was developed for robust and fast image segmentation.…”

Section: Gradient Network Methodsmentioning

confidence: 99%

“…With this additional feature, the algorithm becomes more robust when applied to images with such characteristics. Therefore, even when the neighborhood contains regions too dark or too illuminated it will search for the best possible gradient path in the graph [4].…”

Section: Gradient Network Methodsmentioning

confidence: 99%

“…A color gradient based region-growing post-segmentation method [4] that starts from an initial pre-segmented image and computes a gradient network that spans the entire image. It finds locally connected gradients that show an organized pattern, representing ordered color variations of a same object.…”

Section: Imentioning

confidence: 99%

“…In this paper we present for the first time a ground truthbased objective qualitative validation of our previously presented gradient network approach for image segmentation [4] and analyze its performance in conjunction with another method [1], providing a novel color scene segmentation approach that is extremely fast. It is intended to be used as a two-step approach that shows satisfactory results when applied to natural color scenes, while not showing poorer performance than state-of-the-art methods.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Fast two-step segmentation of natural color scenes using hierarchical region-growing and a color-gradient network

Wangenheim¹,

Bertoldi²,

Abdala³

et al. 2008

J. Braz. Comp. Soc.

Self Cite

View full text Add to dashboard Cite

We present evaluation results with focus on combined image and efficiency performance of the Gradient Network Method to segment color images, especially images showing outdoor scenes. A brief review of the techniques, Gradient Network Method and Color Structure Code, is also presented. Different region-growing segmentation results are compared against ground truth images using segmentation evaluation indices Rand and Bipartite Graph Matching. These results are also confronted with other well established segmentation methods (EDISON and JSEG). Our preliminary results show reasonable performance in comparison to several state-of-art segmentation techniques, while also showing very promising results comparatively in the terms of efficiency, indicating the applicability of our solution to real time problems.

show abstract

Section: Objectives and Validation Methodologymentioning

confidence: 99%

Section: Gradient Network Methodsmentioning

confidence: 99%

Section: Gradient Network Methodsmentioning

confidence: 99%

Section: Imentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Fast two-step segmentation of natural color scenes using hierarchical region-growing and a color-gradient network

Wangenheim¹,

Bertoldi²,

Abdala³

et al. 2008

J. Braz. Comp. Soc.

Self Cite

View full text Add to dashboard Cite

show abstract

A Color Image Segmentation Method Based on Improved K-Means Clustering Algorithm

Jin

Kou

Liu

et al. 2013

Lecture Notes in Electrical Engineering

View full text Add to dashboard Cite

A Fast Pavement Location Approach for Autonomous Car Navigation

Rateke

Justen

Chiarella

et al. 2014

Lecture Notes in Computer Science

View full text Add to dashboard Cite

This paper describes a fast image segmentation approach designed for pavement detection in a moving camera. The method is based on a graph-oriented segmentation approach where gradient information is used temporally as a system of discontinuities to control merging between adjacent regions. The method presumes that the navigable path usually is located at specific positions on the scene, and a predefined set of seed points is used to locate the region of interest. The obtained results shown the proposed approach is able to accurately detect in an inexpensive computation manner the navigable path even in non-optimum scenarios such as miss-painted or unpaved dirt roads. Validation was conducted using a dataset with 701 samples of navigable paths, presenting a very high precision for real-time applications.

show abstract

Color image segmentation guided by a color gradient network

Cited by 16 publications

References 9 publications

Fast two-step segmentation of natural color scenes using hierarchical region-growing and a color-gradient network

Fast two-step segmentation of natural color scenes using hierarchical region-growing and a color-gradient network

A Color Image Segmentation Method Based on Improved K-Means Clustering Algorithm

A Fast Pavement Location Approach for Autonomous Car Navigation

Contact Info

Product

Resources

About