A Two-Stage Probabilistic Approach for Object Recognition
Citations
67 citations
45 citations
Cites background from "A Two-Stage Probabilistic Approach ..."
...In [10], a joint Gaussian model of feature locations is assumed; similarly, other recognition approaches assume that the distribution of object features in an image can be described by a Markov random field [24][7][25] or an object-specific model such as a body plan[14]....
[...]
41 citations
37 citations
16 citations
Cites background from "A Two-Stage Probabilistic Approach ..."
...Similar ideas have been applied mostly to the problems of object detection, extraction and classification in other classes of digital images [24]....
[...]
References
41,772 citations
18,761 citations
"A Two-Stage Probabilistic Approach ..." refers methods or result in this paper
...In a way, this is similar to the line-process model [ 7 ] for differentiating edge and non-edge elements....
[...]
...The differences are: the present model makes use of relational measurements of any orders because contextual constraints play a stronger role in high level problems, whereas the model in [ 7 ] uses only unary observation....
[...]
...Global optimizers such as simulated annealing (SA) [11, 7 ] also iterate based on local energy changes....
[...]
...The present model can be compared to the coupled MRF model of [ 7 ] in that there are two coupled MRFs, one for line processes (edges) and one for intensities; and a line process variable can be on or off depending on the difference between the two neighboring intensities....
[...]
...This framework, advocated by Geman and Geman (1984) andothers, enables us to develop algorithms for a variety of vision problems system-atically using rational principles rather than relying on ad hoc heuristics....
[...]
4,490 citations
"A Two-Stage Probabilistic Approach ..." refers methods in this paper
...The ICM algorithm [2] iteratively maximizes local conditional distributions in a way as a \greedy method"....
[...]
2,744 citations
"A Two-Stage Probabilistic Approach ..." refers methods in this paper
...Here, an object model is represented by local object features, such as points, line segments or regions, subject to various constraints [3, 8, 6, 17]....
[...]
1,771 citations
"A Two-Stage Probabilistic Approach ..." refers background or methods or result in this paper
...Global optimizers such as simulated annealing (SA) [11, 7] also iterate based on local energy changes....
[...]
...This framework, advocated by Geman and Geman (1984) andothers, enables us to develop algorithms for a variety of vision problems system-atically using rational principles rather than relying on ad hoc heuristics....
[...]
...The present model can be compared to the coupled MRF model of [7] in that there are two coupled MRFs, one for line processes (edges) and one for intensities; and a line process variable can be on or o depending on the di erence between the two neighboring intensities....
[...]
...The di erences are: the present model makes use of relational measurements of any orders because contextual constraints play a stronger role in high level problems, whereas the model in [7] uses only unary observation....
[...]
...In a way, this is similar to the line-process model [7] for di erentiating edge and non-edge elements....
[...]