Robust Text Detection in Natural Scene Images Yin, Xu-Cheng; Yin, Xuwang; Huang, Kaizhu ...
IEEE transactions on pattern analysis and machine intelligence,
05/2014, Letnik:
36, Številka:
5
Journal Article
Recenzirano
Odprti dostop
Text detection in natural scene images is an important prerequisite for many content-based image analysis tasks. In this paper, we propose an accurate and robust method for detecting texts in natural ...scene images. A fast and effective pruning algorithm is designed to extract Maximally Stable Extremal Regions (MSERs) as character candidates using the strategy of minimizing regularized variations. Character candidates are grouped into text candidates by the single-link clustering algorithm, where distance weights and clustering threshold are learned automatically by a novel self-training distance metric learning algorithm. The posterior probabilities of text candidates corresponding to non-text are estimated with a character classifier; text candidates with high non-text probabilities are eliminated and texts are identified with a text classifier. The proposed system is evaluated on the ICDAR 2011 Robust Reading Competition database; the f-measure is over 76%, much better than the state-of-the-art performance of 71%. Experiments on multilingual, street view, multi-orientation and even born-digital databases also demonstrate the effectiveness of the proposed method.
Targeting mitochondrial quality control with melatonin has been found promising for attenuating diabetic cardiomyopathy (DCM), although the underlying mechanisms remain largely undefined. Activation ...of SIRT6 and melatonin membrane receptors exerts cardioprotective effects while little is known about their roles during DCM. Using high‐fat diet‐streptozotocin‐induced diabetic rat model, we found that prolonged diabetes significantly decreased nocturnal circulatory melatonin and heart melatonin levels, reduced the expressions of cardiac melatonin membrane receptors, and decreased myocardial SIRT6 and AMPK‐PGC‐1α‐AKT signaling. 16 weeks of melatonin treatment inhibited the progression of DCM and the following myocardial ischemia‐reperfusion (MI/R) injury by reducing mitochondrial fission, enhancing mitochondrial biogenesis and mitophagy via re‐activating SIRT6 and AMPK‐PGC‐1α‐AKT signaling. After the induction of diabetes, adeno‐associated virus carrying SIRT6‐specific small hairpin RNA or luzindole was delivered to the animals. We showed that SIRT6 knockdown or antagonizing melatonin receptors abolished the protective effects of melatonin against mitochondrial dysfunction as evidenced by aggravated mitochondrial fission and reduced mitochondrial biogenesis and mitophagy. Additionally, SIRT6 shRNA or luzindole inhibited melatonin‐induced AMPK‐PGC‐1α‐AKT activation as well as its cardioprotective actions. Collectively, we demonstrated that long‐term melatonin treatment attenuated the progression of DCM and reduced myocardial vulnerability to MI/R injury through preserving mitochondrial quality control. Melatonin membrane receptor‐mediated SIRT6‐AMPK‐PGC‐1α‐AKT axis played a key role in this process. Targeting SIRT6 with melatonin treatment may be a promising strategy for attenuating DCM and reducing myocardial vulnerability to ischemia‐reperfusion injury in diabetic patients.
The intelligent analysis of video data is currently in wide demand because a video is a major source of sensory data in our lives. Text is a prominent and direct source of information in video, while ...the recent surveys of text detection and recognition in imagery focus mainly on text extraction from scene images. Here, this paper presents a comprehensive survey of text detection, tracking, and recognition in video with three major contributions. First, a generic framework is proposed for video text extraction that uniformly describes detection, tracking, recognition, and their relations and interactions. Second, within this framework, a variety of methods, systems, and evaluation protocols of video text extraction are summarized, compared, and analyzed. Existing text tracking techniques, tracking-based detection and recognition techniques are specifically highlighted. Third, related applications, prominent challenges, and future directions for video text extraction (especially from scene videos and web videos) are also thoroughly discussed.
Efficient hydrogen evolution via electrocatalytic water splitting holds great promise in modern energy devices. Herein, we demonstrate that the localized surface plasmon resonance (LSPR) excitation ...of Au nanorods (NRs) dramatically improves the electrocatalytic hydrogen evolution activity of CoFe‐metal–organic framework nanosheets (CoFe‐MOFNs), leading to a more than 4‐fold increase of current density at −0.236 V (vs. RHE) for Au/CoFe‐MOFNs composite under light irradiation versus in dark. Mechanistic investigations reveal that the hydrogen evolution enhancement can be largely attributed to the injection of hot electrons from AuNRs to CoFe‐MOFNs, raising the Fermi level of CoFe‐MOFNs, facilitating the reduction of H2O and affording decreased activation energy for HER. This study highlights the superiority of plasmonic excitation on improving electrocatalytic efficiency of MOFs and provides a novel avenue towards the design of highly efficient water‐splitting systems under light irradiation.
Some like it hot: A composite of Au nanorods/CoFe‐MOF nanosheets (Au/CoFe‐MOFNs) was used as an electrocatalyst for the hydrogen evolution reaction (HER). Au/CoFe‐MOFNs give a four‐fold increase of current density and a much reduced activation energy upon light irradiation as a result of hot‐electron injection from plasmonic Au to CoFe‐MOFNs.
The autophagy–lysosomal pathway (ALP) is involved in the degradation of long-lived proteins. Deficits in the ALP result in protein aggregation, the generation of toxic protein species, and ...accumulation of dysfunctional organelles, which are hallmarks of Alzheimer's disease (AD), Parkinson's disease (PD), Huntington's disease (HD), and prion disease. Decades of research have therefore focused on enhancing the ALP in neurodegenerative diseases. More recently, transcription factor EB (TFEB), a major regulator of autophagy and lysosomal biogenesis, has emerged as a leading factor in addressing disease pathology. We review the regulation of the ALP and TFEB and their impact on neurodegenerative diseases. We also offer our perspective on the complex role of autophagy and TFEB in disease pathogenesis and its therapeutic implications through the examination of prion disease.
Distributed quantum metrology can enhance the sensitivity for sensing spatially distributed parameters beyond the classical limits. Here we demonstrate distributed quantum phase estimation with ...discrete variables to achieve Heisenberg limit phase measurements. Based on parallel entanglement in modes and particles, we demonstrate distributed quantum sensing for both individual phase shifts and an averaged phase shift, with an error reduction up to 1.4 dB and 2.7 dB below the shot-noise limit. Furthermore, we demonstrate a combined strategy with parallel mode entanglement and multiple passes of the phase shifter in each mode. In particular, our experiment uses six entangled photons with each photon passing the phase shifter up to six times, and achieves a total number of photon passes N = 21 at an error reduction up to 4.7 dB below the shot-noise limit. Our research provides a faithful verification of the benefit of entanglement and coherence for distributed quantum sensing in general quantum networks.Distributed quantum metrology is demonstrated for both individual and averaged phase shifts by using discrete-variable entangled photons. An error reduction of 4.7 dB below the shot-noise limit is achieved when a total number of photon passes is 21.
Ultrathin 2D molybdenum disulfide (MoS2), which is the flagship of 2D transition‐metal dichalcogenide nanomaterials, has drawn much attention in the last few years. 2D MoS2 has been banked as an ...alternative to platinum for highly active hydrogen evolution reaction because of its low cost, high surface‐to‐volume ratio, and abundant active sites. However, when MoS2 is used directly as a photocatalyst, contrary to public expectation, it still performs poorly due to lateral size, high recombination ratio of excitons, and low optical cross section. Besides, simply compositing MoS2 as a cocatalyst with other semiconductors cannot satisfy the practical application, which stimulates the pursual of a comprehensive insight into recent advances in synthesis, properties, and enhanced hydrogen production of MoS2. Therefore, in this Review, emphasis is given to synthetic methods, phase transitions, tunable optical properties, and interfacial engineering of 2D MoS2. Abundant ways of band edge tuning, structural modification, and phase transition are addressed, which can generate the neoteric photocatalytic systems. Finally, the main challenges and opportunities with respect to MoS2 being a cocatalyst and coherent light–matter interaction of MoS2 in photocatalytic systems are proposed.
A potential insight into synthesis methods, phase transitions, and tunable optical properties is reviewed for the rational design of MoS2 photocatalytic systems. Moreover, photocatalytic enhancements of plasmon‐assisted MoS2 are also reviewed to further explore the prospects for MoS2 as a cocatalyst and a photocatalyst.
Microgrids can act as emergency sources to serve critical loads when utility power is unavailable. This paper proposes a resiliency-based methodology that uses microgrids to restore critical loads on ...distribution feeders after a major disaster. Due to limited capacity of distributed generators (DGs) within microgrids, dynamic performance of the DGs during the restoration process becomes essential. In this paper, the stability of microgrids, limits on frequency deviation, and limits on transient voltage and current of DGs are incorporated as constraints of the critical load restoration problem. The limits on the amount of generation resources within microgrids are also considered. By introducing the concepts of restoration tree and load group, restoration of critical loads is transformed into a maximum coverage problem, which is a linear integer program (LIP). The restoration paths and actions are determined for critical loads by solving the LIP. A 4-feeder, 1069-bus unbalanced test system with four microgrids is utilized to demonstrate the effectiveness of the proposed method. The method is applied to the distribution system in Pullman, WA, resulting in a strategy that uses generators on the Washington State University campus to restore service to the Hospital and City Hall in Pullman.
Multi-Orientation Scene Text Detection with Adaptive Clustering Yin, Xu-Cheng; Pei, Wei-Yi; Zhang, Jun ...
IEEE transactions on pattern analysis and machine intelligence,
2015-Sept.-1, 2015-Sep, 2015-9-1, 20150901, Letnik:
37, Številka:
9
Journal Article
Recenzirano
Text detection in natural scene images is an important prerequisite for many content-based image analysis tasks, while most current research efforts only focus on horizontal or near horizontal scene ...text. In this paper, first we present a unified distance metric learning framework for adaptive hierarchical clustering, which can simultaneously learn similarity weights (to adaptively combine different feature similarities) and the clustering threshold (to automatically determine the number of clusters). Then, we propose an effective multi-orientation scene text detection system, which constructs text candidates by grouping characters based on this adaptive clustering. Our text candidates construction method consists of several sequential coarse-to-fine grouping steps: morphology-based grouping via single-link clustering, orientation-based grouping via divisive hierarchical clustering, and projection-based grouping also via divisive clustering. The effectiveness of our proposed system is evaluated on several public scene text databases, e.g., ICDAR Robust Reading Competition data sets (2011 and 2013), MSRA-TD500 and NEOCR. Specifically, on the multi-orientation text data set MSRA-TD500, the <inline-formula><tex-math>f</tex-math> <inline-graphic xlink:type="simple" xlink:href="yin-ieq1-2388210.gif"/> </inline-formula> measure of our system is <inline-formula><tex-math>71</tex-math> <inline-graphic xlink:type="simple" xlink:href="yin-ieq2-2388210.gif"/> </inline-formula> percent, much better than the state-of-the-art performance. We also construct and release a practical challenging multi-orientation scene text data set (USTB-SV1K), which is available at http://prir.ustb.edu.cn/TexStar/MOMV-text-detection/.
Video text extraction plays an important role for multimedia understanding and retrieval. Most previous research efforts are conducted within individual frames. A few of recent methods, which pay ...attention to text tracking using multiple frames, however, do not effectively mine the relations among text detection, tracking and recognition. In this paper, we propose a generic Bayesian-based framework of Tracking based Text Detection And Recognition (T2DAR) from web videos for embedded captions, which is composed of three major components, i.e., text tracking, tracking based text detection, and tracking based text recognition. In this unified framework, text tracking is first conducted by tracking-by-detection. Tracking trajectories are then revised and refined with detection or recognition results. Text detection or recognition is finally improved with multi-frame integration. Moreover, a challenging video text (embedded caption text) database (USTB-VidTEXT) is constructed and publicly available. A variety of experiments on this dataset verify that our proposed approach largely improves the performance of text detection and recognition from web videos.