A robust visual method for assessing the relative performance of edge-detection algorithms

Heath, Michael D.; Sarkar, Sudeep; Sanocki, Thomas; Bowyer, Kevin W.

doi:10.1109/34.643893

Cited by 411 publications

(259 citation statements)

References 44 publications

Supporting

Mentioning

241

Contrasting

Unclassified

Order By: Relevance

“…Gradient estimation from the original 'shapes' test image was used in the comparison. The dashed lines show the comparative results for an implementation of the Spann and Wilson method [11] and a Canny edge-detector [48] with a hysteresis based thresholding. The parameters of the Canny implementation were chosen separately for each input image to produce the most pleasing qualitative results.…”

Section: Resultsmentioning

confidence: 99%

“…performance on simple shapes and those with sharp features (corners) (figure 7), performance on complex boundary shape ( figure 9(a)-(c)), performance at low inter-class contrast in the presence of noise (graphs 10, 11), Additionally, comparative results are presented using implementations of a quad-tree technique ( [11]), and supervised region-only (MAP estimation using ICM [26], figure 14) and boundary-only methods (Canny edge detection [48], figure 13). …”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Unsupervised image segmentation combining region and boundary estimation

Bhalerao

Wilson

2001

Image and Vision Computing

View full text Add to dashboard Cite

An integrated approach to image segmentation is presented that combines region and boundary information using maximum a posteriori estimation and decision theory. The algorithm employs iterative, decision-directed estimation performed on a novel multiresolution representation. The use of a multiresolution technique ensures both robustness in noise and efficiency of computation, while the model-based estimation and decision process is flexible and spatially local, thus avoiding assumptions about global homogeneity or size and number of regions. A comparative evaluation of the method against region-only and boundary-only methods is presented and is shown to produce accurate segmentations at quite low signal-to-noise ratios.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Unsupervised image segmentation combining region and boundary estimation

Bhalerao

Wilson

2001

Image and Vision Computing

View full text Add to dashboard Cite

show abstract

“…The bottom row in Fig. 3 allows us to compare our results (orange image) with state-of-the-art but edge-only algorithms in computer vision, i.e., Bergholm, Canny, Iverson and Nalwa, see Heath et al (2000) and also http://marathon.csee.usf.edu/edge/edge detection.html. This site shows 12 results of each method obtained with different parameter selections.…”

Section: Line and Edge Detection And Classificationmentioning

confidence: 99%

Multi-scale lines and edges in V1 and beyond: Brightness, object categorization and recognition, and consciousness

Rodrigues

Buf

2009

Biosystems

View full text Add to dashboard Cite

a b s t r a c tIn this paper we present an improved model for line and edge detection in cortical area V1. This model is based on responses of simple and complex cells, and it is multi-scale with no free parameters. We illustrate the use of the multi-scale line/edge representation in different processes: visual reconstruction or brightness perception, automatic scale selection and object segregation. A two-level object categorization scenario is tested in which pre-categorization is based on coarse scales only and final categorization on coarse plus fine scales. We also present a multi-scale object and face recognition model. Processing schemes are discussed in the framework of a complete cortical architecture. The fact that brightness perception and object recognition may be based on the same symbolic image representation is an indication that the entire (visual) cortex is involved in consciousness.

show abstract

“…There has been progress both in theoretical modeling of performance [3][4][5] and in empirical performance characterization [6][7][8][9]. Ramesh et al [3] follow a theoretical solution to the problem of parameter selection.…”

Section: Related Workmentioning

confidence: 99%

Modeling Parameter Space Behavior of Vision Systems Using Bayesian Networks

Sarkar

Chavali

2000

Computer Vision and Image Understanding

View full text Add to dashboard Cite

The performance of most vision systems (or subsystems) is significantly dependent on the choice of its various parameters or thresholds. The associated parameter search space is extremely large and nonsmooth; moreover, the optimal choices of the parameters are usually mutually dependent on each other. In this paper we offer a Bayesian network-based probabilistic formalism, which we call the parameter dependence networks (PDNs), to model, abstract, and analyze the parameter space behavior of vision systems. The various algorithm parameters are the nodes of the PDN and are associated with probabilistic beliefs about the optimality of their respective values. The links between the nodes capture the direct dependencies between them and are quantified by conditional belief functions. The PDN structure captures the interdependence among the parameters in a concise and explicit manner. We define information theoretic measures, based on these PDNs, to quantify the global parameter sensitivity and the strength of the interdependence of the parameters. These measures predict the general ease of parameter tuning and performance stability of the system. The PDNs can also be used to stochastically sample the parameter space, to select optimal parameter sets (e.g., in performance evaluation studies), and to choose parameters, given constraints on the choice of some parameters. We also offer a strategy based on stochastic learning automata to generate training data to automatically build these PDNs. The team of learning automata stochastically samples the parameter space in a nonuniform manner with more samples near optimal values. These nonuniform samples are used to infer both the dependency structure and the conditional probabilities of the PDN. We demonstrate the process of construction of the PDN for an isolated vision module with 4 parameters (an edge detector), a coupling of two vision modules with a total of 7 parameters (a small edge grouping module), and a combination of three vision modules with 21 parameters (a complex perceptual organization module).

show abstract

A robust visual method for assessing the relative performance of edge-detection algorithms

Cited by 411 publications

References 44 publications

Unsupervised image segmentation combining region and boundary estimation

Unsupervised image segmentation combining region and boundary estimation

Multi-scale lines and edges in V1 and beyond: Brightness, object categorization and recognition, and consciousness

Modeling Parameter Space Behavior of Vision Systems Using Bayesian Networks

Contact Info

Product

Resources

About