Texture recognition using a non-parametric multi-scale statistical model

Bonet, Jordi; Viola, Paul A.

doi:10.1109/cvpr.1998.698672

Cited by 66 publications

(48 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In discriminant imaging analysis, mixture models such as normal, normal mixture, or histograms are used. For example flexible histogram approach [8,9], classifications of several target features may be conducted by treating pixels as a set of independent samples drawn from a mixture distribution [10]. A distribution of feature vectors using Parzen windows was modelled.…”

Section: Summary Accuracy Measuresmentioning

confidence: 99%

Three validation metrics for automated probabilistic image segmentation of brain tumours

Zou

Wells

Kikinis

et al. 2004

Statistics in Medicine

View full text Add to dashboard Cite

SUMMARYThe validity of brain tumour segmentation is an important issue in image processing because it has a direct impact on surgical planning. We examined the segmentation accuracy based on three twosample validation metrics against the estimated composite latent gold standard, which was derived from several experts' manual segmentations by an EM algorithm. The distribution functions of the tumour and control pixel data were parametrically assumed to be a mixture of two beta distributions with different shape parameters. We estimated the corresponding receiver operating characteristic curve, Dice similarity coefficient, and mutual information, over all possible decision thresholds. Based on each validation metric, an optimal threshold was then computed via maximization. We illustrated these methods on MR imaging data from nine brain tumour cases of three different tumour types, each consisting of a large number of pixels. The automated segmentation yielded satisfactory accuracy with varied optimal thresholds. The performances of these validation metrics were also investigated via Monte Carlo simulation. Extensions of incorporating spatial correlation structures using a Markov random field model were considered.

show abstract

Section: Summary Accuracy Measuresmentioning

confidence: 99%

Three validation metrics for automated probabilistic image segmentation of brain tumours

Zou

Wells

Kikinis

et al. 2004

Statistics in Medicine

View full text Add to dashboard Cite

show abstract

“…; x K Þ. For k 2 ½½0; K, Similarly to recent work on texture analysis [2], [15], we exploit scale co-occurrences to characterize spatial image motion properties. For l 2 ½½0; L À 1, the scale co-occurrence distribution À l ðxÞ is given by:…”

Section: Temporal Multiscale Gibbs Modelsmentioning

confidence: 99%

“…Statistical modeling has already proven its ability to supply flexible, general, and efficient frameworks for classification and recognition issues. In particular, the introduction of probabilistic models, such as Gibbs random fields, has led to important advances for texture analysis [2], [15], [20]. Probabilistic models have also been considered for temporal texture synthesis and recognition [7], [16], [17], but the developed solutions are suited for appearance change modeling and not really for general motion information analysis.…”

Section: Related Workmentioning

confidence: 99%

Motion recognition using nonparametric image motion models estimated from temporal and multiscale co-occurrence statistics

Fablet

Bouthémy

2003

IEEE Trans. Pattern Anal. Machine Intell.

View full text Add to dashboard Cite

Abstract-A new approach for motion characterization in image sequences is presented. It relies on the probabilistic modeling of temporal and scale cooccurrence distributions of local motion-related measurements directly computed over image sequences. Temporal multiscale Gibbs models allow us to handle both spatial and temporal aspects of image motion content within a unified statistical framework. Since this modeling mainly involves the scalar product between cooccurrence values and Gibbs potentials, we can formulate and address several fundamental issues: model estimation according to the ML criterion (hence, model training and learning) and motion classification. We have conducted motion recognition experiments over a large set of real image sequences comprising various motion types such as temporal texture samples, human motion examples, and rigid motion situations.

show abstract

“…Furthermore, if the spatial intensity gradient is sufficiently distributed in terms of direction in the vicinity of pixel , an appropriately weighted average of in a local neighborhood can be used as a relevant motion-related quantity. More precisely, we consider the following expression: (5) where is a small window centered on , its size the square root of the average of the squared magnitude of the spatial gradient within window (6) is a predetermined constant related to the noise level in uniform areas. This motion-related measurement forms a more reliable quantity than the normal flow, yet simply computed from the intensity function and its derivatives.…”

Section: B Local Motion-related Measurementsmentioning

confidence: 99%

“…We have defined a similarity measure based on the Kullback-Leibler (KL) divergence [4], [6]. Let and be the two sequences of motion-related measurements associated to videos and and, and the two estimated models on them using the method from the previous section.…”

Section: A Statistical Similarity Measure Related To Motion Activitymentioning

confidence: 99%

Nonparametric motion characterization using causal probabilistic models for video indexing and retrieval

Fablet¹,

Bouthémy²,

Pérez³

2002

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

Abstract-This paper describes an original approach for content-based video indexing and retrieval. We aim at providing a global interpretation of the dynamic content of video shots without any prior motion segmentation and without any use of dense optic flow fields. To this end, we exploit the spatio-temporal distribution, within a shot, of appropriate local motion-related measurements derived from the spatio-temporal derivatives of the intensity function. These distributions are then represented by causal Gibbs models. To be independent of camera movement, the motion-related measurements are computed in the image sequence generated by compensating the estimated dominant image motion in the original sequence. The statistical modeling framework considered makes the exact computation of the conditional likelihood of a video shot belonging to a given motion or more generally to an activity class feasible. This property allows us to develop a general statistical framework for video indexing and retrieval with query-by-example. We build a hierarchical structure of the processed video database according to motion content similarity. This results in a binary tree where each node is associated to an estimated causal Gibbs model. We consider a similarity measure inspired from Kullback-Leibler divergence. Then, retrieval with query-by-example is performed through this binary tree using the maximum a posteriori (MAP) criterion. We have obtained promising results on a set of various real image sequences.

show abstract

Texture recognition using a non-parametric multi-scale statistical model

Cited by 66 publications

References 11 publications

Three validation metrics for automated probabilistic image segmentation of brain tumours

Three validation metrics for automated probabilistic image segmentation of brain tumours

Motion recognition using nonparametric image motion models estimated from temporal and multiscale co-occurrence statistics

Nonparametric motion characterization using causal probabilistic models for video indexing and retrieval

Contact Info

Product

Resources

About