Learn More
In this paper, we develop a novel unified framework called DeepText for text region proposal generation and text detection in natural images via a fully convolutional neural network (CNN). First, we propose the inception region proposal network (InceptionRPN) and design a set of text characteristic prior bounding boxes to achieve high word recall with only(More)
BACKGROUND & AIMS The type III interferons (IFN-λs: interleukin [IL]-28a, IL-28b, and IL-29) have important roles in hepatitis C virus (HCV) infection, but little is understood about what cells produce these cytokines or how production is activated. We investigated whether human immune cells recognize HCV-infected cells and respond by producing IFN-λ. (More)
BACKGROUND & AIMS Interferon-γ (IFN-γ), a cytokine produced by activated natural killer cells (NK) and T lymphocytes, is an important regulator of innate and adaptive immunity during hepatitis C virus (HCV) infection. However, the cellular sources and mechanisms of IFN-γ induction in HCV-infection are not fully understood. METHODS We cultured normal human(More)
UNLABELLED Recognition of hepatitis C virus (HCV)-infected hepatocyes and interferon (IFN) induction are critical in antiviral immune response. We hypothesized that cell-cell contact between plasmacytoid dendritic cells (pDCs) and HCV-infected cells was required for IFN-α induction through the involvement of cell-surface molecules. Coculture of human(More)
BACKGROUND & AIMS Hepatitis C virus (HCV) is difficult to eradicate and type III interferons (IFN-λ, composed of IL-28A, IL-28B and IL-29) are novel therapeutic candidates. We hypothesized that IFN-λ have immunomodulatory effects in HCV- infected individuals. MATERIALS AND METHODS We analyzed the expression of IFN-λ and its receptor (composed of IL-10R2(More)
Maximally stable extremal regions (MSER), which is a popular method to generate character proposals/candidates, has shown superior performance in scene text detection. However, the pixel-level operation limits its capability for handling some challenging cases (e.g., multiple connected characters, separated parts of one character and non-uniform(More)
In this paper, we present an effective method to analyze the recognition confidence of handwritten Chinese character, based on the softmax regression score of a high performance convolutional neural networks (CNN). Through careful and thorough statistics of 827,685 testing samples that randomly selected from total 8836 different classes of Chinese(More)
This paper proposes an end-to-end framework, namely fully convolutional recurrent network (FCRN) for handwritten Chinese text recognition (HCTR). Unlike traditional methods that rely heavily on segmentation, our FCRN is trained with online text data directly and learns to associate the pentip trajectory with a sequence of characters. FCRN consists of four(More)
Patch-based Single-layer Unsupervised Feature Learning (SUFL) has been successfully applied in several tasks of computer vision. In the feature learning process, the key ingredient is how to learn a good feature mapping that connects patches to feature vectors. Among various feature mapping methods, the sparse filtering is easy to be implemented and(More)
With the rapid development of optical character recognition (OCR), font categorization becomes more and more important. This is because font information has very wide usage and researchers came to know this point recently. In this paper, we propose a new scheme for Chinese character font categorization (CCFC), which applies LBP descriptor based Chinese(More)