Parallel implementation of exact dilations and multi-scale skeletonization

Luppe, Maximiliam; Costa, Luciano da Fontoura; Roda, Valentin Obac

doi:10.1016/s1077-2014(03)00016-0

Cited by 4 publications

(6 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…As expected, the thinning algorithm for the roots shown in Fig. 2b often displays the medial axis of the roots (Luppe et al, 2003), which is equivalent to the root length (Lebowitz, 1988;Kimura et al, 1999).…”

Section: Application Of Software In Image Samplessupporting

confidence: 61%

“…With the roots located in image, the edge detection method from the OpenCV library was applied to distinguish and label the objects (root segments). Then, each of labelled objects was skeletonized with a multi-scale thinning algorithm (Luppe et al, 2003). This method thins the objects in images by successive deletions of the edge of each object.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

A computational method to assist evaluation of root length of soybean based on digital image processing

et al. 2019

View full text Add to dashboard Cite

The evaluation of the root system is important for better understanding the effects of nutrient management on soil and plant nutri-tion. However, root system studies and culture are slow and show low accuracy. In this context, digital image processing may be an alternative. The objective of this research was to develop a computational method to assist evaluation of the soybean root growth. Initially, the free and open access software, available at: http://rm.deinfo.uepg.br/, was developed in Java platform with the OpenCV library supply through the plug-in JavaCV. To evaluate the software, copper wires with 10 mm, 20 mm, and 50 mm of length manually measured using callipers. They were scanned with a resolution of 300 dpi and then images were loaded in the software. Variation coefficients between 0.01 and 2.99 % were obtained. Subsequently, the samples of soybean roots were scanned and the results of developed software and Safira software were correlated with those from the line-intersect method. The determination coefficients (R² = 0.999) of the developed software, on average, were better than those obtained with Safira software (R² = 0.733), when compar-ing with the line-intersect method. Therefore, the proposed method was accurate for length measurements of soybean roots.

show abstract

Section: Application Of Software In Image Samplessupporting

confidence: 61%

Section: Methodsmentioning

confidence: 99%

A computational method to assist evaluation of root length of soybean based on digital image processing

et al. 2019

View full text Add to dashboard Cite

show abstract

“…It is large potential to reduce the area of the PE if reducing some performance is acceptable for specified applications. In contrast with other works [ 13 , 25 – 21 ], our vision chip gets more efficient performance and programmability. That is benefit from the flexibility of gray-scale mathematical morphology.…”

Section: Discussion Of Performancementioning

confidence: 83%

“…Some application-specific vision chips performing low- and mid-level image processing were developed [ 9 – 12 ], but these chips were designed for specified applications and with a specified architecture. Another vision chip performing exact dilations was presented in [ 13 ], but this one focused on several specific algorithms, such as morphological dilation, multi-scale skeleton and Distance Transform [ 14 ]. They were not programmable or feasible for general purpose applications.…”

Section: Introductionmentioning

confidence: 99%

A 1,000 Frames/s Programmable Vision Chip with Variable Resolution and Row-Pixel-Mixed Parallel Image Processors

Lin

Wang

Zhang

et al. 2009

Sensors

View full text Add to dashboard Cite

A programmable vision chip with variable resolution and row-pixel-mixed parallel image processors is presented. The chip consists of a CMOS sensor array, with row-parallel 6-bit Algorithmic ADCs, row-parallel gray-scale image processors, pixel-parallel SIMD Processing Element (PE) array, and instruction controller. The resolution of the image in the chip is variable: high resolution for a focused area and low resolution for general view. It implements gray-scale and binary mathematical morphology algorithms in series to carry out low-level and mid-level image processing and sends out features of the image for various applications. It can perform image processing at over 1,000 frames/s (fps). A prototype chip with 64 × 64 pixels resolution and 6-bit gray-scale image is fabricated in 0.18 μm Standard CMOS process. The area size of chip is 1.5 mm × 3.5 mm. Each pixel size is 9.5 μm × 9.5 μm and each processing element size is 23 μm × 29 μm. The experiment results demonstrate that the chip can perform low-level and mid-level image processing and it can be applied in the real-time vision applications, such as high speed target tracking.

show abstract

“…The program which computes this look-up table is very simple (see Annex). Notice that the same look-up table was used by Fontoura-Costa et al to compute an exact Euclidean dilation [17]. Once all decompositions are known, one must take into account the different symmetries of the space (their number is 8 for Z 2 , 48 for Z 3 ) and check those positions y which satisfy the second condition of prop.…”

Section: The Bisector Function: New Definition and Exact Algorithmmentioning

confidence: 99%

Discrete Bisector Function and Euclidean Skeleton

Couprie

Zrour

2005

Discrete Geometry for Computer Imagery

View full text Add to dashboard Cite

show abstract

Parallel implementation of exact dilations and multi-scale skeletonization

Cited by 4 publications

References 27 publications

A computational method to assist evaluation of root length of soybean based on digital image processing

A computational method to assist evaluation of root length of soybean based on digital image processing

A 1,000 Frames/s Programmable Vision Chip with Variable Resolution and Row-Pixel-Mixed Parallel Image Processors

Discrete Bisector Function and Euclidean Skeleton

Contact Info

Product

Resources

About