Segmentation of natural scenes

Bhanu, Bir; Parvin, Bahram

doi:10.1016/0031-3203(87)90076-8

Cited by 45 publications

(11 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Nowadays there are a lot of image segmentation methods, which can be divided into three categories: feature-based clustering [5][6][7] , model-based [8][9][10] and region-based [11][12][13] . Feature-based methods usually use clustering for image segmentation, and the color and texture of the image can be used as features.…”

Section: Introductionmentioning

confidence: 99%

Image Segmentation Based on Multi-direction Gabor Filters

Li¹,

Wei²,

Zhang³

et al. 2017

dtetr

View full text Add to dashboard Cite

1Aiming at the over-segmentation problem that traditional segmentation methods are prone to affect by noise, a region-based method that extracting adaptive coarse edge by using multi-direction Gabor filters is proposed. Firstly, extract the multi-direction magnitude responses by using imaginary part of Gabor filter and get the gradient magnitude at each pixel, then use the adaptive threshold method to extract coarse edge. Secondly, watershed transform on the coarse edge map to get the initial over-segmentation result. Finally, on the premise of not exceeding the region merging cost, the initial segmented regions are merged iteratively. The experimental results show that compared with Canny, region growing and LOG methods, the proposed method relieves the over-segmentation problem effectively and the average computational complexity has been reduced by about 21.5%.

show abstract

Section: Introductionmentioning

confidence: 99%

Image Segmentation Based on Multi-direction Gabor Filters

Li¹,

Wei²,

Zhang³

et al. 2017

dtetr

View full text Add to dashboard Cite

show abstract

“…In this paper we are concerned with region-based segmentation. The ability to carry out such a process automatically has been a topic of much research in computer vision [5,9,1,14]. One of the difficulties with all segmentation techniques has been to quantify their success with respect to a particular application.…”

Section: Machine Segmentationmentioning

confidence: 99%

“…The first step is to define a pairwi.se area-based comparison between regions a m and b n , where 6,,is the region having the largest overlap with region a m : (1) where N is the number of regions in segmentation a and A is the total area of the image. To provide the required symmetry, the metric is defined as:…”

mentioning

confidence: 99%

Automatic Interpretation of Outdoor Scenes.

Campbell¹,

Mackeown²,

Thomas

et al. 1995

Procedings of the British Machine Vision Conference 1995

View full text Add to dashboard Cite

This paper describes recent work on a neural network approach to outdoor scene interpretation. The results of evaluating a range of automatic region-based segmentation techniques based on a new segmentation quality metric are presented. The optimal technique is used to segment images of natural outdoor scenes. A powerful set of features designed for outdoor scene analysis is extracted from regions in the segmented images and used to train a neural network to recognise eleven different classes of objects, including sky, road, building and vegetation. The system is tested on a large number of images which have been hand-labelled to provide ground-truth segmentations and interpretations. This fully automated system achieves an impressive mean classification accuracy of 81.4% per image on unseen data, and runs in approximately 1 CPU minute on a Sun SPARCstation 20.

show abstract

“…The procedure classifies a given data set through a certain number of clusters [8] [9]. A prior knowledge of number of clusters is must for K-means clustering algorithm.…”

Section: K-means Clustering Algorithmmentioning

confidence: 99%

“…K-means is simple unsupervised learning algorithms that solve the well-known clustering problem [7] [8]. The procedure classifies a given data set through a certain number of clusters [8] [9].…”

Section: K-means Clustering Algorithmmentioning

confidence: 99%

A Novel Optimum Real-Time Color Reduction on FPGA Based on Swarm Intelligence

Assar¹

2015

International Journal of Advanced Research in Computer and Comm

View full text Add to dashboard Cite

Data clustering is a popular approach for automatically finding set of objects into a specific number of clusters. Clustering is largely used in many fields including text mining, information retrieval and pattern grouping. Particle Swarm Optimization (PSO) is a population-based optimization algorithm modelled after the simulation of social behaviour of bird flocks and widely used for optimize problem solving. In clustering problem PSO gives optimal solution but takes long time (so called iterations) to find the optimum solution. The hybrid PSO and K-means algorithm is developed to automatically detect the cluster centers of geometrical structure data sets. The proposed algorithm gives the benefits for each of two-merged algorithms. K-means is fast algorithm, PSO optimize the solution. The implementation of the hybrid K-means PSO structure is realized in hardware. The clustering based on hybrid K-means PSO architecture is described by different technique for hardware description (i.e. block diagram) and implemented on field programmable gate array (FPGA). Its feasibility is verified by experiments. Results show that the proposed architecture implemented on the FPGA has a good clustering technique especially for testing with color reduction for true color video.

show abstract

Segmentation of natural scenes

Cited by 45 publications

References 9 publications

Image Segmentation Based on Multi-direction Gabor Filters

Image Segmentation Based on Multi-direction Gabor Filters

Automatic Interpretation of Outdoor Scenes.

A Novel Optimum Real-Time Color Reduction on FPGA Based on Swarm Intelligence

Contact Info

Product

Resources

About