Efficient image understanding based on the Markov random field model and error backpropagation network

Kim, Il Y.; Yang, Hyun Seung

doi:10.1109/icpr.1992.201595

Cited by 5 publications

(3 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They consider an interpretation of a scene as an MRF and define the optimal matching as the MAP estimate of the MRF. Other works in MRF-based recognition can be found in (Grenander and Y. Chow 1991;Baddeley and van Lieshout 1992;Friedland and Rosenfeld 1992;Kim and Yang 1992;Cooper et al 1993). This contradicts the promises of MAP-MRF modeling.…”

Section: Work In Relational Matchingmentioning

confidence: 99%

“…MRF modeling provides one approach to optimization-based object recognition (Modestino and Zhang 1989;Cooper 1990;Baddeley and van Lieshout 1992;Kim and Yang 1992;Li 1994a). MRF modeling provides one approach to optimization-based object recognition (Modestino and Zhang 1989;Cooper 1990;Baddeley and van Lieshout 1992;Kim and Yang 1992;Li 1994a).…”

Section: Application In Mrf Object Recognitionmentioning

confidence: 99%

See 1 more Smart Citation

Markov Random Field Modeling in Computer Vision

1995

Computer Science Workbench

984

779

View full text Add to dashboard Cite

Section: Work In Relational Matchingmentioning

confidence: 99%

Section: Application In Mrf Object Recognitionmentioning

confidence: 99%

Markov Random Field Modeling in Computer Vision

1995

Computer Science Workbench

984

779

View full text Add to dashboard Cite

“…Many systems which attempt to identify all of the pixels in an object require fully supervised training data that has the objects segmented or extremely obvious [29,15,9,16,31,26,2,18,32,8,11,21,10,28]. Training data that contains pixel level segmentations is extremely tedious to obtain, however, so such systems are not able to scale to large datasets.…”

Section: Introductionmentioning

confidence: 99%

A framework for learning to recognize and segment object classes using weakly supervised training data

Pantofaru¹,

Hebert²

2007

Procedings of the British Machine Vision Conference 2007

View full text Add to dashboard Cite

The continual improvement of object recognition systems has resulted in an increased demand for their application to problems which require an exact pixel-level object segmentation. In this paper, we illustrate an example of an object class recognition and segmentation system which is trained using weakly supervised training data, with the goal of examining the influence that different model choices can have on its performance. In order to achieve pixel-level labeling for rigid and deformable objects, we employ regions generated by unsupervised segmentation as the spatial support for our image features, and explore model selection issues related to their representation. Numerical results for pixel-level accuracy are presented on two challenging and varied datasets.

show abstract

Fast Labelling of Natural Scenes Using Enhanced Knowledge

Hayashi

Kudo

Tanida

et al. 2001

Pattern Analysis & Applications

View full text Add to dashboard Cite

A new technique for labelling natural scenes is proposed. This technique labels disjoint regions on an image of a natural scene on the basis of knowledge about the relationship among objects. The proposed technique consists of three stages: (1) segmentation, (2) initial labelling, and (3) label improvement. One of the most promising previous techniques uses simulated annealing to find the solution, while our technique uses local hill-climbing with enhanced knowledge for speeding up the processing. Local hill-climbing is known to be easy to be captured by a local minimum. We solved this problem by enhancing the knowledge being used as constraints for the search. Our knowledge represents 1-to-n relationships among regions, pair-wise relationships of regions, and relative locations of the regions to the image. In addition, we introduced two region features: an entropy in intensity; and a linearity of contours of each region. The linearity evaluation aims to distinguish artificial objects from natural objects. The validity of the technique is supported by some experiments. These experiments showed that the proposed technique is much faster with the almost same accurate.

show abstract

Efficient image understanding based on the Markov random field model and error backpropagation network

Cited by 5 publications

References 7 publications

Markov Random Field Modeling in Computer Vision

Markov Random Field Modeling in Computer Vision

A framework for learning to recognize and segment object classes using weakly supervised training data

Fast Labelling of Natural Scenes Using Enhanced Knowledge

Contact Info

Product

Resources

About