Detection and delineation of compact objects using intensity pyramids

Rosenfield, A.; Sher, Awal

doi:10.1016/0031-3203(88)90021-0

Cited by 27 publications

(7 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Upon seeing an image, a person can very easily detect the existence of an object and can extract its boundary in a very short time [17]. Especially for medical images such as CT or MRI, many people can classify organs or tissues without much anatomical knowledge.…”

Section: Introductionmentioning

confidence: 99%

Detecting and visualizing cartilage thickness without a shape model

Cui

et al. 2012

2012 IEEE International Conference on Systems, Man, and Cybernetics (SMC)

View full text Add to dashboard Cite

This paper proposes a cartilage thickness detection and visualization method that does not utilize a shape model. The proposed method consists of three parts: volume of interest (VOI) initialization, bone segmentation, and cartilage thickness visualization. For VOI initialization, a novel 3D U-shape cuboidal filter is proposed to detect individual bones such as the femur, tibia, and patella, and for bone segmentation, a hybrid level-set method is adopted. Finally, a surface normal based approach is presented for measuring and visualizing the cartilage thickness. The advantage of the proposed method compared to other methods is that it does not require a shape model or any training process. The results demonstrate that the proposed method can be used for inspecting cartilage damage and loss.

show abstract

Section: Introductionmentioning

confidence: 99%

Detecting and visualizing cartilage thickness without a shape model

Cui

et al. 2012

2012 IEEE International Conference on Systems, Man, and Cybernetics (SMC)

View full text Add to dashboard Cite

show abstract

“…This is expected to introduce two-fold benefits: the detection of smaller details that would be otherwise overwhelmed by larger texture patterns and the more reliable classification provided by the simultaneous analysis of large uniform regions. Several attempts 11,12,13,7,8,5,9,10,14,15,16 have been made to incorporate multiresolution processing in computer vision algorithms. Our previous works 1,2,3 have described a technique for leather inspection based on the analysis of flow fields (computed from grey level images using the algorithm proposed by Rao e Schunck 4) composed by an angle image (representing at each point the dominant orientation of gradients in a neighbourhood of the textured image after Gaussian smoothing) and by a coherence image (measuring at the same point the accordance the directions of those gradients and the local dominant orientation).…”

Section: Introductionmentioning

confidence: 99%

<title>Multiscale data analysis for leather defect detection</title>

Branca¹,

Attolico²,

Distante³

1996

Machine Vision Applications, Architectures, and Systems Integration V

View full text Add to dashboard Cite

The paper describes some early results obtained by applying a multiscale approach to texture analysis for defect detection on leather surfaces. Texture properties have proved to be a valuable help in charactensing the chaotic structures normally present on leather and the oriented structures typical of defects in spite of the wide range of associated visual appearances. Texture based defect detection can be done effectively by using the coefficients of the projection of a flow field (obtained by the textured image using a method proposed by Rao and Shunck) into a vector space spanned by an appropriate basis function set. Being texture strongly related to scale we propose to extend the work of Rao and Schunck by employing a bank of filters, tuned at different scales, in order to perform the flow field estimation. Measures based on the coherence of outputs are used to determine at each point the scale providing the strongest oriented texture. Results showing the effect of synthesizing multiscale data into a single flow field will be provided.

show abstract

“…Bister [1] actually proved that thin elongated objects cannot be detected. On the other hand, numerous works [2][3][4][5] successfully conduced towards delineating compact forms. Nevertheless, rigid pyramid algorithms are shift-, rotation-and scale-variant *This work has been performed in accordance with the research topics of the group 134 of the CNRS (National Center for Scientific Research).…”

Section: Introductionmentioning

confidence: 99%

On the choice of the first level on graph pyramids

Mathieu

Magnin

1996

J Math Imaging Vis

View full text Add to dashboard Cite

After a brief review and description of the existing graph pyramids used for image processing, particularly stochastic (SP) and adaptive (AP) pyramids, we propose a new strategy to improve the final segmentation provided by such methods. The idea is to translate the image to be segmented into a minimal spanning tree (MST) before building the pyramid. It is shown that the use of an MST in this process improves the results of the pyramidal segmentation. Some experimental results are presented on synthetic and actual images. Finally, a filtering pyramidal algorithm is proposed, using the properties of the minimal spanning tree.

show abstract

Detection and delineation of compact objects using intensity pyramids

Cited by 27 publications

References 2 publications

Detecting and visualizing cartilage thickness without a shape model

Detecting and visualizing cartilage thickness without a shape model

<title>Multiscale data analysis for leather defect detection</title>

On the choice of the first level on graph pyramids

Contact Info

Product

Resources

About