Finding Salient Regions in Images

Pauwels, Eric J.; Frederix, Greet

doi:10.1006/cviu.1999.0763

Cited by 106 publications

(14 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are three methods for the detection of salient objects in an image; the non-parametric measure [52], the thresh hold based measure in which threshold is manually selected and the modified Hubert index [53]. For the classification of objects in images, image can be divided into foreground and background regions [54].…”

Section: Shape and Regionmentioning

confidence: 99%

Content-Based Image Retrieval Using Texture Color Shape and Region

Shirazi¹,

Umar²,

Naz³

et al. 2016

ijacsa

View full text Add to dashboard Cite

Abstract-Interests to accurately retrieve required images from databases of digital images are growing day by day. Images are represented by certain features to facilitate accurate retrieval of the required images. These features include Texture, Color, Shape and Region. It is a hot research area and researchers have developed many techniques to use these feature for accurate retrieval of required images from the databases. In this paper we present a literature survey of the Content Based Image Retrieval (CBIR) techniques based on Texture, Color, Shape and Region. We also review some of the state of the art tools developed for CBIR.

show abstract

Section: Shape and Regionmentioning

confidence: 99%

Content-Based Image Retrieval Using Texture Color Shape and Region

Shirazi¹,

Umar²,

Naz³

et al. 2016

ijacsa

View full text Add to dashboard Cite

show abstract

“…Classical techniques for finding regions directly include such as region growing by pixel aggregation, region splitting and merging [1]. More recent methods include clustering [15] and texture-based techniques [12]. These methods are effective, but require extensive computation.…”

Section: Problem Statementmentioning

confidence: 99%

Multi-scale feature identification using evolution strategies

Yuan

Zhang

Yuan

et al. 2005

Image and Vision Computing

View full text Add to dashboard Cite

“…A collection of techniques [1][2][3] have been suggested as possible solution to the inherently difficult image segmentation problem. They fall into one of the following categories, namely histogram-based algorithms [4][5][6], edge-based algorithms [7][8][9], region-based algorithms [10][11][12][13][14][15], Markov Random Field-based algorithms [16][17][18] and clustering-based methods [19][20][21]. The watershed transform method, which belongs to the broad class of region-based segmentation approach, is simple to formulate and it can effectively recognize the important closed contours of a given image.…”

Section: Introductionmentioning

confidence: 99%

An Efficient Hillclimbing-based Watershed Algorithm and its Prototype Hardware Architecture

Rambabu

Chakrabarti

2008

J Sign Process Syst Sign Image Video Technol

View full text Add to dashboard Cite

Image segmentation is the process of isolating objects in an input image, that is, partitioning the image into disjoint regions, such that each region is homogeneous with respect to some property, such as gray value or texture. Watershed-based image segmentation has gained much popularity in the field of biomedical image processing and computer vision where large images are not uncommon. Time-critical applications like road traffic monitoring, and steel fissure analysis require fast realization of the segmentation results. The present paper proposes a fast watershed transform based on hillclimbing technique. The complexity of the algorithm has been reduced by doing away with multiplication normally required to form a lower complete image in an intermediate step of the overall segmentation. The reduced complexity makes the algorithm suitable for dedicated hardware implementation. An FPGA-based architecture has been developed to implement the proposed algorithm involving moderate hardware complexity. This architecture enhances the applicability of this algorithm for real-time applications.

show abstract

Finding Salient Regions in Images

Cited by 106 publications

References 15 publications

Content-Based Image Retrieval Using Texture Color Shape and Region

Content-Based Image Retrieval Using Texture Color Shape and Region

Multi-scale feature identification using evolution strategies

An Efficient Hillclimbing-based Watershed Algorithm and its Prototype Hardware Architecture

Contact Info

Product

Resources

About