Stripe-based connected components labelling

Zhao, Hualong; Fan, Yebin; Zhang, T.X.; Sang, Hongshi

doi:10.1049/el.2010.2016

Cited by 15 publications

(11 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…1 Differ with the conventional union-find-like algorithms which used in many proposed algorithms [8] [12] [13], the root combination direction of reversed hookup algorithm is pointing to the newest equivalence connected component instead of pointing to the smallest or oldest one. Fig.4 describes the key difference between two approaches.…”

Section: Line Hookupmentioning

confidence: 99%

See 1 more Smart Citation

A novel algorithm and its VLSI architecture for connected component labeling

Zhao

Sang

2011

SPIE Proceedings

View full text Add to dashboard Cite

A novel line-based streaming labeling algorithm with its VLSI architecture is proposed in this paper. Line-based neighborhood examination scheme is used for efficient local connected components extraction. A novel reversed rooted tree hook-up strategy, which is very suitable for hardware implementation, is applied on the mergence stage of equivalent connected components. The reversed rooted tree hook-up strategy significant reduces the requirement of onchip memory, which makes the chip area smaller. Clock domains crossing FIFOs are also applied for connecting the label core and external memory interface, which makes the label engine working in a higher frequency and raises the throughput of the label engine. Several performance tests have been performed for our proposed hardware implementation. The processing bandwidth of our hardware architecture can reach the I/O transfer boundary according to the external interface clock in all the real image tests. Beside the advantage of reducing the processing time, our hardware implementation can support the image size as large as 4096*4096, which will be very appealing in remote sensing or any other high-resolution image applications. The implementation of proposed architecture is synthesized with SMIC 180nm standard cell library. The work frequency of the label engine reaches 200MHz.

show abstract

Section: Line Hookupmentioning

confidence: 99%

“…Therefore, Yang's result is not convincing. Zhao et al [8] proposed a fast labeling algorithm based on two rows' raster scan called SBLA which can also be categories into parallel algorithm from the hardware point of view. However, authors didn't mention any information for its hardware implementation.…”

Section: Introductionmentioning

confidence: 99%

A novel algorithm and its VLSI architecture for connected component labeling

Zhao

Sang

2011

SPIE Proceedings

View full text Add to dashboard Cite

show abstract

“…We divide them into four classes depending on the way they check the neighborhood in the first scan in order to assign a provisional label and to determine label equivalences: pixel-based [3,7,9,10,22,23,24], run-based [8,11,14], block-based [5,6,12,13,19,21] and stripe-based [25]. According to the number of times of scanning an image for labeling, there are multi-scan [7,22], two-scan [5,6,8,9,10,12,13,19,21,23,24,25], one-and-a-half-scan [11,19] and one-scan [3,14] algorithms.…”

Section: Introductionmentioning

confidence: 99%

“…However, for these algorithms, it is not possible to perform oneand-a-half-scan using run data without extra comparisons, analogously to He et al [11] and Santiago et al [19]. Hence, we design a new image representation based on the stripe definition of Zhao et al [25]. A stripe is a part of a connected component, which is in the even row and the following odd row of the image.…”

Section: Introductionmentioning

confidence: 99%

Efficient 2×2 block-based connected components labeling algorithms

Santiago

Ren

Cavalcanti

et al. 2015

2015 IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

This paper presents three new efficient 2×2 block-based algorithms for connected components labeling: a two-scan which assigns provisional labels to blocks, a two-scan which assigns provisional labels to pixels and a one-and-a-half-scan which assigns provisional labels to blocks. A new stripe image representation is designed in order to perform the second pass only through the blocks containing some foreground pixel. We also improved the existing 2×2 block-based algorithms by utilizing information of a pixel during a transition in the mask, which allows checking of four neighbor pixels in the mask at most. Thus, the average number of checking operations needed to inspect the neighbor pixels in the first scan is reduced from 1.459 to 1.156, an improvement of 21%. We conducted experiments using synthetic and real images to evaluate the performance of the proposed methods compared to the existing methods. The proposed block-based one-and-a-half-scan algorithm presents the best performance in the real images dataset, which is composed of 1290 documents. Our block-based two-scan algorithm which assigns provisional labels to pixels showed to be the fastest in the synthetic dataset, especially in high density images.

show abstract

“…Comparison and test results: Comparison is performed on two state-ofthe-art CPU algorithms: the SBLA [7] and BBDT [4] as well as the fastest GPU CCL algorithm [1] already published. The test hardware platform is a 2.0 GHz Intel P6100 processor with 4GB dual channel DDR3, a NVIDIA GT425M GPU with 96 CUDA cores and 1GB 128bit DDR3.…”

mentioning

confidence: 99%

Block-run-based connected component labelling algorithm for GPGPU using shared memory

et al. 2011

Self Cite

View full text Add to dashboard Cite

An efficient two-scan connected component labelling (CCL) algorithm is proposed for a general purpose graphics processing unit (GPGPU). Compared to other GPU CCL algorithm, this algorithm has three distinct features. First, block-based and run-based strategies are combined in the first scan to simplify the equivalence label resolving process. Secondly, a novel labelling method for the GPU is introduced by constructing a forest of rooted trees using only 16-bit value for each node. Thirdly, the whole algorithm can be implemented in the GPU shared memory and minimise global memory bandwidth consumption. Experiments show that the algorithm achieves a speedup of between two and five times compared to other state-of-the-art GPU and CPU CCL algorithms.

show abstract

Stripe-based connected components labelling

Cited by 15 publications

References 4 publications

A novel algorithm and its VLSI architecture for connected component labeling

A novel algorithm and its VLSI architecture for connected component labeling

Efficient 2×2 block-based connected components labeling algorithms

Block-run-based connected component labelling algorithm for GPGPU using shared memory

Contact Info

Product

Resources

About