One DAG to Rule Them All

Bolelli, Federico; Allegretti, Stefano; Grana, Costantino

doi:10.1109/tpami.2021.3055337

Cited by 19 publications

(17 citation statements)

References 72 publications

(96 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The 3D network outputs were further refined by the postprocessing technique described in [28]. We implement their method by applying a 3D connected components labeling (CCL) [36] algorithm on the output masks, preserving only the two largest objects that should represent the left and right branch of the inferior alveolar nerve canal. Unlike Jaskari et al, there is no need to verify at run-time how many connected components we have in our ground truth volumes since these are always two in the proposed dataset, namely the two branches of the canal.…”

Section: Post-processingmentioning

confidence: 99%

Deep Segmentation of the Mandibular Canal: A New 3D Annotated Dataset of CBCT Volumes

et al. 2022

Self Cite

View full text Add to dashboard Cite

Inferior Alveolar Nerve (IAN) canal detection has been the focus of multiple recent works in dentistry and maxillofacial imaging. Deep learning-based techniques have reached interesting results in this research field, although the small size of 3D maxillofacial datasets has strongly limited the performance of these algorithms. Researchers have been forced to build their own private datasets, thus precluding any opportunity for reproducing results and fairly comparing proposals. This work describes a novel, large, and publicly available mandibular Cone Beam Computed Tomography (CBCT) dataset, with 2D and 3D manual annotations, provided by expert clinicians. Leveraging this dataset and employing deep learning techniques, we are able to improve the state of the art on the 3D mandibular canal segmentation. The source code which allows to exactly reproduce all the reported experiments is released as an open-source project, along with this article.

show abstract

Section: Post-processingmentioning

confidence: 99%

Deep Segmentation of the Mandibular Canal: A New 3D Annotated Dataset of CBCT Volumes

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…A decision tree was proposed to access as few neighbors as possible. SAUF was later ported to 3D by Bolelli as SAUF 3D [4]. The decision tree was further optimized by He et al with the Label Equivalency Based (LEB ) algorithm for 2D [16] and 3D.…”

Section: Pixel-based Algorithmsmentioning

confidence: 99%

“…This method was generalized by Grana with the PRED algorithm [12], which was later extended to 3D volumes by Bolelli with PRED 3D. [4]. The introduction of Direct Rooted Acyclic Graphs (DRAG) by Bolelli [5] reduced the code footprint.…”

Section: Pixel-based Algorithmsmentioning

confidence: 99%

See 1 more Smart Citation

LSL3D: A Run-Based Connected Component Labeling Algorithm for 3D Volumes

Maurice

Lemaître

Julien

et al. 2022

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Connect Component Labeling (CCL) has been a fundamental operation in Computer Vision for decades. Most of the literature deals with 2D algorithms for applications like video surveillance or autonomous driving. Nonetheless, the need for 3D algorithms is rising, notably for medical imaging. While 2D CCL algorithms already generate large amounts of memory accesses and comparisons, 3D ones are even worse. This is the curse of dimensionality. Designing an efficient algorithm should address this problem. This paper introduces a segment-based algorithm for 3D labeling that uses a new strategy to accelerate label equivalence processing to mitigate the impact of higher dimensions. We claim that this new algorithm outperforms State-of-the-Art algorithms by a factor from ×1.5 up to ×3.1 for usual medical datasets and random images.

show abstract

“…Several image processing and computer vision applications employ connected components labeling as a pre-or post-processing step [1], [2], [3], [4], [5], [6]. Given the importance of the task, many works have been published in the last two decades that address its runtime optimization, both for sequential [7], [8], [9], [10], [11], [12] and parallel architectures [13], [14], [15], [16], [17], [18].…”

Section: Introductionmentioning

confidence: 99%

Fast Run-Based Connected Components Labeling for Bitonal Images

Lee

Allegretti

Bolelli

et al. 2021

2021 Joint 10th International Conference on Informatics, Electronics &Amp; Vision (ICIEV) and 2021 5th International Conference

Self Cite

View full text Add to dashboard Cite

Connected Components Labeling (CCL) is a fundamental task in binary image processing. Since its introduction in the sixties, several algorithmic strategies have been proposed to optimize its execution time. Most CCL algorithms in literature, including the current state-of-the-art, are designed to work on an input stored with 1-byte per pixel, even if the most memoryefficient format for a binary input only uses 1-bit per pixel. This paper deals with connected components labeling on 1bit per pixel images, also known as 1bpp or bitonal images. An existing run-based CCL strategy is adapted to this input format, and optimized with Find First Set hardware operations and a smart management of provisional labels, giving birth to an efficient solution called Bit-Run Two Scan (BRTS). Then, BRTS is further optimized by merging pairs of consecutive lines through bitwise OR, and finding runs on this reduced data. This modification is the basis for another new algorithm on bitonal images, Bit-Merge-Run Scan (BMRS). When evaluated on a public benchmark, the two proposals outperform all the fastest competitors in literature, and therefore represent the new stateof-the-art for connected components labeling on bitonal images.Contribution-This paper introduces two new Connected Components Labeling algorithms for bitonal images that significantly improve the state-of-the-art, using Find First Set instructions.

show abstract

One DAG to Rule Them All

Cited by 19 publications

References 72 publications

Deep Segmentation of the Mandibular Canal: A New 3D Annotated Dataset of CBCT Volumes

Deep Segmentation of the Mandibular Canal: A New 3D Annotated Dataset of CBCT Volumes

LSL3D: A Run-Based Connected Component Labeling Algorithm for 3D Volumes

Fast Run-Based Connected Components Labeling for Bitonal Images

Contact Info

Product

Resources

About