Weilin Huang

Learn More
Maximally Stable Extremal Regions (MSERs) have achieved great success in scene text detection. However, this low-level pixel operation inherently limits its capability for handling complex text information efficiently (e. g. connections between text or background components), leading to the difficulty in distinguishing texts from background components. In(More)
We propose a novel Connectionist Text Proposal Network (CTPN) that accurately localizes text lines in natural image. The CTPN detects a text line in a sequence of fine-scale text proposals directly in convolutional feature maps. We develop a vertical anchor mechanism that jointly predicts location and text/non-text score of each fixed-width proposal,(More)
In this paper, we present a new approach for text localization in natural images, by discriminating text and non-text regions at three levels: pixel, component and text line levels. Firstly, a powerful low-level filter called the Stroke Feature Transform (SFT) is proposed, which extends the widely-used Stroke Width Transform (SWT) by incorporating color(More)
Recent deep learning models have demonstrated strong capabilities for classifying text and non-text components in natural images. They extract a high-level feature globally computed from a whole image component (patch), where the cluttered background information may dominate true text features in the deep representation. This leads to less discriminative(More)
A comprehensive wet chemical procedure was developed by combining acid demineralization, base extraction, and dichromate oxidation for fractionation and quantitative isolation of soil/sediment organic matter (SOM) into four fractions: (1) humic acids + kerogen + BC (HKB); (2) kerogen + BC (KB); (3) humic acid (HA); and (4) BC. The soil/sediment samples(More)
The Xijiang River is the major tributary of the Pearl River, South China, and is the major source water system for more than 4.5 million of urban population and 28.7 million of rural population. We initiated a systematic study on detection and quantification of organic pollutants in both water and suspended particulate matter (SPM) for samples collected in(More)
Steroid hormones such as 17alpha-ethinyl estradiol (EE2) have been frequently detected at various levels in surface waters downstream of many municipal wastewater treatment facilities. Their fate, transport, and environmental risk are currently not well characterized. This study examined the competitive sorption between EE2 and two aromatic hydrocarbon(More)
Steroid estrogens at sub-micrograms per liter levels are frequently detected in surface water, and increasingly cause public concern of their potential impacts on ecosystems and human health. Assessing the environmental fate and risks of steroid estrogens requires accurate characterization of various physicochemical and biological processes involving these(More)
We develop a Deep-Text Recurrent Network (DTRN) that regards scene text reading as a sequence labelling problem. We leverage recent advances of deep convolutional neural networks to generate an ordered highlevel sequence from a whole word image, avoiding the difficult character segmentation problem. Then a deep recurrent model, building on long short-term(More)