EdgeFlow: a technique for boundary detection and image segmentation

Ma, Wei‐Ying; Manjunath, B.S.

doi:10.1109/83.855433

Cited by 277 publications

(24 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To detect vessel edges, we used a set of four oriented kernels, known as difference of offset Gaussian filters (DoOG filters) to measure the local gradient in the image [17, 18]. For example, in order to measure the local gradient along the x -direction in the image, the appropriate DoOG kernel is constructed by taking the difference of two copies of Gaussian kernels displaced along the x -axis.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Cryo-image Analysis of Tumor Cell Migration, Invasion, and Dispersal in a Mouse Xenograft Model of Human Glioblastoma Multiforme

et al. 2011

View full text Add to dashboard Cite

Purpose The goals of this study were to create cryo-imaging methods to quantify characteristics (size, dispersal, and blood vessel density) of mouse orthotopic models of glioblastoma multiforme (GBM) and to enable studies of tumor biology, targeted imaging agents, and theranostic nanoparticles. Procedures Green fluorescent protein-labeled, human glioma LN-229 cells were implanted into mouse brain. At 20–38 days, cryo-imaging gave whole brain, 4-GB, 3D microscopic images of bright field anatomy, including vasculature, and fluorescent tumor. Image analysis/visualization methods were developed. Results Vessel visualization and segmentation methods successfully enabled analyses. The main tumor mass volume, the number of dispersed clusters, the number of cells/cluster, and the percent dispersed volume all increase with age of the tumor. Histograms of dispersal distance give a mean and median of 63 and 56 μm, respectively, averaged over all brains. Dispersal distance tends to increase with age of the tumors. Dispersal tends to occur along blood vessels. Blood vessel density did not appear to increase in and around the tumor with this cell line. Conclusion Cryo-imaging and software allow, for the first time, 3D, whole brain, microscopic characterization of a tumor from a particular cell line. LN-229 exhibits considerable dispersal along blood vessels, a characteristic of human tumors that limits treatment success.

show abstract

Section: Methodsmentioning

confidence: 99%

“…The last parameter determines the slope of the filter around the zero crossing point of the kernel. To find the best parameters for vessel enhancement, we kept the offset parameter proportional to the standard deviation parameter; specifically, we used offset = 4σ [18]. Then, we experimented to find the best σ and truncation size.…”

Section: Methodsmentioning

confidence: 99%

Cryo-image Analysis of Tumor Cell Migration, Invasion, and Dispersal in a Mouse Xenograft Model of Human Glioblastoma Multiforme

et al. 2011

View full text Add to dashboard Cite

show abstract

“…Segmentation of labeling is important in localization performance and boundary localization [44]. It uses grouping and segmentation as an initial estimate of objects in the image by setting the threshold on the feature grouping algorithm especially in estimating the number of areas [45].…”

Section: Literature Reviewmentioning

confidence: 99%

Computer Vision and Image Processing: A Paper Review

Wiley

Lucas

2018

Int. J. Art. Intell. Research

177

View full text Add to dashboard Cite

Computer vision has been studied from many persective. It expands from raw data recording into techniques and ideas combining digital image processing, pattern recognition, machine learning and computer graphics. The wide usage has attracted many scholars to integrate with many disciplines and fields. This paper provide a survey of the recent technologies and theoretical concept explaining the development of computer vision especially related to image processing using different areas of their field application. Computer vision helps scholars to analyze images and video to obtain necessary information, understand information on events or descriptions, and scenic pattern. It used method of multi-range application domain with massive data analysis. This paper provides contribution of recent development on reviews related to computer vision, image processing, and their related studies. We categorized the computer vision mainstream into four group e.g., image processing, object recognition, and machine learning. We also provide brief explanation on the up-to-date information about the techniques and their performance.

show abstract

“…Otherwise, non-uniformity arising from overlapping shadows and the yarn card background color would be regarded as the yarn color itself, degrading the accuracy of the color measurement and imposing problems in color reproduction and communication. 7 With multispectral imaging systems, yarn color measurement is made possible by a color-region segmentation technique which is able to detect and extract the yarn color from the captured image mainly using two approaches: clustering algorithms, e.g., fuzzy c-means clustering algorithm, 8 and image segmentation methods, e.g., edge-based, 9 graph-based, 10 histogram-based 11 and region-based methods. 12 This helps to minimize the yarn specimen handling time, needing no human hand or winding machine to make them in yarn card wound form beforehand.…”

Section: Introductionmentioning

confidence: 99%

Yarn Color Measurement and Reproduction by a Multispectral Imaging System

Tang¹,

Xin²

2015

jist

View full text Add to dashboard Cite

Conventionally, measuring and thus reproducing yarn color is mainly done in an indirect way, involving the preparation of yarns in card or even fabric forms, which consumes both time and labor. A direct yarn color measurement and reproduction method based on a multispectral imaging system would be one solution to avoid this problem. In this research, 100% raw cotton yarn hanks dyed using several reactive colorants, being different sample sets, were measured by both a spectrophotometer in yarn card form and a multispectral imaging system innovatively in yarn form itself, for back-prediction and fore-prediction matching comparisons. Experimental results showed that the multispectral imaging system can perform closed-loop color reproduction satisfactorily by yarn form color measurements, with color difference means all within industrial tolerance. This new method is capable of shortening the yarn specimen handling time and, more importantly, giving more accurate yarn color measurements without the influence of neighboring colors, so as to give improved coloration accuracy.

show abstract

EdgeFlow: a technique for boundary detection and image segmentation

Cited by 277 publications

References 44 publications

Cryo-image Analysis of Tumor Cell Migration, Invasion, and Dispersal in a Mouse Xenograft Model of Human Glioblastoma Multiforme

Cryo-image Analysis of Tumor Cell Migration, Invasion, and Dispersal in a Mouse Xenograft Model of Human Glioblastoma Multiforme

Computer Vision and Image Processing: A Paper Review

Yarn Color Measurement and Reproduction by a Multispectral Imaging System

Contact Info

Product

Resources

About