Papers › PixelLink: Detecting Scene Text via Instance Segmentation

PixelLink: Detecting Scene Text via Instance Segmentation

4 Jan 2018arXiv:1801.01315archive 2025-07-28

Dan Deng, Haifeng Liu, Xuelong. Li, Deng Cai

Most state-of-the-art scene text detection algorithms are deep learning based methods that depend on bounding box regression and perform at least two kinds of predictions: text/non-text classification and location regression. Regression plays a key role in the acquisition of bounding boxes in these methods, but it is not indispensable because text/non-text prediction can also be considered as a kind of semantic segmentation that contains full location information in itself. However, text instances in scene images often lie very close to each other, making them very difficult to separate via semantic segmentation. Therefore, instance segmentation is needed to address this problem. In this paper, PixelLink, a novel scene text detection algorithm based on instance segmentation, is proposed. Text instances are first segmented out by linking pixels within the same instance together. Text bounding boxes are then extracted directly from the segmentation result without location regression. Experiments show that, compared with regression-based methods, PixelLink can achieve better or comparable performance on several benchmarks, while requiring many fewer training iterations and less training data.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

Autonise-AI/Text-Recognition mentioned on GitHubpytorch report
ZJULearning/pixel_link mentioned on GitHubtf report
dengdan/seglink mentioned on GitHubtf report
mayank-git-hub/Text-Recognition mentioned on GitHubpytorch report
opconty/pixellink_keras mentioned on GitHubtf report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Instance SegmentationScene Text DetectionSegmentationSemantic SegmentationText ClassificationText Detectionregression

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Scene Text Detection ICDAR 2013 PixelLink+VGG16 2s MS F-Measure 88.1% #6 of 16 Archive leaderboard report
Scene Text Detection ICDAR 2013 PixelLink+VGG16 2s MS Precision 88.6 #6 of 16 Archive leaderboard report
Scene Text Detection ICDAR 2013 PixelLink+VGG16 2s MS Recall 87.5 #6 of 16 Archive leaderboard report
Scene Text Detection ICDAR 2015 SLPR F-Measure 84.5 #26 of 43 Archive leaderboard report
Scene Text Detection ICDAR 2015 SLPR Precision 85.5 #26 of 43 Archive leaderboard report
Scene Text Detection ICDAR 2015 SLPR Recall 83.6 #26 of 43 Archive leaderboard report
Scene Text Detection MSRA-TD500 PixelLink + VGG16 2s F-Measure 77.8 #16 of 18 Archive leaderboard report
Scene Text Detection MSRA-TD500 PixelLink + VGG16 2s Precision 83 #16 of 18 Archive leaderboard report
Scene Text Detection MSRA-TD500 PixelLink + VGG16 2s Recall 73.2 #16 of 18 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections