Chuang Yang

Prof. Dr. Chuang Yang

orcid

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
29 March 2022 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
Chuang YangChuang Yang
Chuang Yang
MCMulin Chen
Mulin Chen
ZXZhitong Xiong
Zhitong Xiong
YYYuan Yuan
Yuan Yuan
Qi WangQi Wang
Qi Wang
Recently fast arbitrary-shaped text detection has become an attractive research topic. However, most existing methods are non-real-time, which may fall short in intelligent systems. Although a few real-time text methods are proposed, the detection accuracy is far behind non-real-time methods. To improve the detection accuracy and speed simultaneously, we propose a novel fast and accurate text detection framework, namely CM-Net, which is constructed based on a new text representation method and a multi-perspective feature (MPF) module. The former can fit arbitrary-shaped text contours by concentric mask (CM) in an efficient and robust way. The latter encourages the network to learn more CM-related discriminative features from multiple perspectives and brings no extra computational cost. Benefiting the advantages of CM and MPF, the proposed CM-Net only needs to predict one CM of the text instance to rebuild the text contour and achieves the best balance between detection accuracy and speed compared with previous works. Moreover, to ensure that multi-perspective features are effectively learned, the multi-factor constraints loss is proposed. Extensive experiments demonstrate the proposed CM is efficient and robust to fit arbitrary-shaped text instances, and also validate the effectiveness of MPF and constraints loss for discriminative text features recognition. Furthermore, experimental results show that the proposed CM-Net is superior to existing state-of-the-art (SOTA) real-time text detection methods in both detection speed and accuracy on MSRA-TD500, CTW1500, Total-Text, and ICDAR2015 datasets.

13 February 2023 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
Chuang YangChuang Yang
Chuang Yang
MCMulin Chen
Mulin Chen
YYYuan Yuan
Yuan Yuan
Qi WangQi Wang
Qi Wang
Irregular-shaped texts bring challenges to Scene Text Detection (STD). Although existing regression-based approaches achieve comparable performances, they fail to cover some highly curved ribbon-like text lines. Inspired by morphology, we found that the leaf vein can easily cover various geometries. Specifically, lateral and thin veins are emitted to margin along main vein gradually with the leaf growth. This process can decompose a concave object into consecutive convex regions, which are easier to fit. Hence, the leaf vein is suitable for representing highly curved texts. Considering the aforementioned advantage, we design a leaf vein-based text representation method (LVT), where text contour is treated as leaf margin and represented through main, lateral, and thin veins. We further construct a detection framework based on LVT, namely LeafText. In the text reconstruction stage, LeafText simulates the leaf growth process to rebuild text contours. It grows main veins in Cartesian coordinates to locate texts roughly at first. Then, lateral and thin veins are generated along the main vein growth direction in polar coordinates. They are responsible for generating the coarse contour and refining it, respectively. Meanwhile, Multi-Oriented Smoother (MOS) is designed to smooth the main vein for ensuring reliable growth directions of lateral and thin veins. Additionally, a global incentive loss is proposed to enhance the predictions of lateral and thin veins. Ablation experiments demonstrate LVT can fit irregular-shaped texts precisely and verify the effectiveness of MOS and global incentive loss. Comparisons show that LeafText is superior to existing state-of-the-art (SOTA) methods on MSRA-TD500, CTW1500, Total-Text, and ICDAR2015 datasets.

4 July 2023 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
Chuang YangChuang Yang
Chuang Yang
MCMulin Chen
Mulin Chen
YYYuan Yuan
Yuan Yuan
Qi WangQi Wang
Qi Wang
To pursue comprehensive performance, recent text detectors improve detection speed at the expense of accuracy. They adopt shrink-mask-based text representation strategies, which leads to a high dependence of detection accuracy on shrink-masks. Unfortunately, three disadvantages cause unreliable shrink-masks. Specifically, these methods try to strengthen the discrimination of shrink-masks from the background by semantic information. However, the feature defocusing phenomenon that coarse layers are optimized by fine-grained objectives limits the extraction of semantic features. Meanwhile, since both shrink-masks and the margins belong to texts, the detail loss phenomenon that the margins are ignored hinders the distinguishment of shrink-masks from the margins, which causes ambiguous shrink-mask edges. Moreover, false-positive samples enjoy similar visual features with shrink-masks. They aggravate the decline of shrink-masks recognition. To avoid the above problems, we propose a zoom text detector (ZTD) inspired by the zoom process of the camera. Specifically, zoomed-out view module (ZOM) is introduced to provide coarse-grained optimization objectives for coarse layers to avoid feature defocusing. Meanwhile, zoomed-in view module (ZIM) is presented to enhance the margins recognition to prevent detail loss. Furthermore, sequential-visual discriminator (SVD) is designed to suppress false-positive samples by sequential and visual features. Experiments verify the superior comprehensive performance of ZTD.

25 July 2024 in IEEE Transactions on Intelligent Transportation Systems
Verified
Journal Article
Closed access
Chuang YangChuang Yang
Chuang Yang
KZKai Zhuang
Kai Zhuang
MCMulin Chen
Mulin Chen
HMHaozhao Ma
Haozhao Ma
XHXu Han
Xu Han
Qi WangQi Wang
Qi Wang
Most existing traffic sign-related works are dedicated to detecting and recognizing part of traffic signs separately, which fails to analyze the global semantic logic among signs and may convey inaccurate traffic instruction information. Following the above issues, we propose a traffic sign interpretation (TSI) task, which aims to interpret global semantic interrelated traffic signs (e.g., driving instruction-related texts, symbols, and guide panels) into a natural language for providing complete traffic instruction support to autonomous or assistant driving. Meanwhile, considering the lack of an effective framework for the proposed TSI task in existing works, we design a multi-task learning architecture (TSI-arch) to detect and recognize various traffic signs with drastic changes in sizes and aspect ratios. Meanwhile interpreting these signs into a natural language like a human according to Chinese design criteria of road traffic signs. Furthermore, the absence of a public TSI available dataset prompts us to build a traffic sign interpretation dataset, namely TSI-CN. The dataset consists of real road scene images, which are captured from the highway and the urban way in China from a driver’s perspective. It contains rich location labels of texts, symbols, and guide panels, and the corresponding natural language description labels. Experiments on our TSI-CN dataset demonstrate that the TSI task is achievable and the TSI architecture can interpret traffic signs from scenes successfully even if there is a complicated semantic logic among signs.

23 November 2023 in Science Bulletin
Verified
Journal Article
Open access
Chuang YangChuang Yang
Chuang Yang
ALAnni Luo
Anni Luo
HLHai-Ping Lu
Hai-Ping Lu
SDSeth Jon Davis
Seth Jon Davis
JLJian-Xiang Liu
Jian-Xiang Liu
Rice (Oryza sativa L.) production is threatened by global warming associated with extreme high temperatures, and rice heat sensitivity is differed when stress occurs between daytime and nighttime. However, the underlying molecular mechanism are largely unknown. We show here that two glycine-rich RNA binding proteins, OsGRP3 and OsGRP162, are required for thermotolerance in rice, especially at nighttime. The rhythmic expression of OsGRP3/OsGRP162 peaks at midnight, and at these coincident times, is increased by heat stress. This is largely dependent on the evening complex component OsELF3-2. We next found that the double mutant of OsGRP3/OsGRP162 is strikingly more sensitive to heat stress in terms of survival rate and seed setting rate when comparing to the wild-type plants. Interestingly, the defect in thermotolerance is more evident when heat stress occurred in nighttime than that in daytime. Upon heat stress, the double mutant of OsGRP3/OsGRP162 displays globally reduced expression of heat-stress responsive genes, and increases of mRNA alternative splicing dominated by exon-skipping. This study thus reveals the important role of OsGRP3/OsGRP162 in thermotolerance in rice, and unravels the mechanism on how OsGRP3/OsGRP162 regulate thermotolerance in a diurnal manner.

23 September 2022 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
Chuang YangChuang Yang
Chuang Yang
MCMulin Chen
Mulin Chen
YYYuan Yuan
Yuan Yuan
Qi WangQi Wang
Qi Wang
Existing real-time text detectors reconstruct text contours by shrink-masks only. Though they simplify the framework and can make the model run fast, the strong dependence on shrink-masks leads to unreliable detection results (e.g., miss detection and overdetection). Moreover, these methods ignore the information from surrounding pixels, which causes sensitive shrink-masks and accelerates the reliability decline of detection results. Considering the above problems, we construct an effective and efficient text detection network, termed as Reinforcement Shrink-Mask for Text Detection (RSMTD), which strengthens the model's ability to recognize texts while enjoying a high detection speed. Specifically, an effective text representation strategy (Reinforcement Shrink-Mask, RSM) is designed to decouple texts and shrink-masks. RSM builds texts through shrink-masks and reinforcement offsets to ensure stable detection results encountering shrink-masks that deviate from the ground-truth. It is worth noting that reinforcement offsets can force our method to focus on the foreground shapes to bring precise shrink-mask edges. For the robustness improvement of shrink-masks, Super-pixel Window (SPW) is proposed to encourage RSMTD to utilize the surroundings of each pixel to predict shrink-masks. Particularly, SPW treats the interval regions between texts and shrink-masks as background, which helps to suppress interval regions and to avoid text adhesion. Moreover, a lightweight feature merging branch is constructed to further accelerate the inference process. As demonstrated in the experiments, our method is superior to existing state-of-the-art (SOTA) methods in both detection accuracy and speed on multiple benchmarks.