Learn More
—Deep learning methods have recently achieved impressive performance in the area of visual recognition and speech recognition. In this paper, we propose a handwriting recognition method based on relaxation convolutional neural network (R-CNN) and alternately trained relaxation convolutional neural network (ATR-CNN). Previous methods regularize CNN at(More)
Text occlusion is among the most intractable obstacles for OCR engines. A typical example in document images is visible watermark characters, which are often occluded by foreground contents. This paper proposes a solution by restoring watermark characters before recognition. The text restoration process consists a core module as patch-based restoration(More)
—In this paper, a novel dual-band, dual-polarized, miniaturized and low-profile base station antenna operating in the frequency bands of 820–960 and 1710–2170 MHz is designed. Elements are arranged such that high-frequency elements are embedded in low frequency elements to reduce volume. A baffle is used to reflect the transmitted power density in the(More)
We describe a shape-based chamfer matching method for recovering 3D hand pose using a monocular camera. Although some variants of chamfer matching methods incorporated edge direction information, of which the direction term is set empirically, so they may fail in different application scenario. In this paper, a collaborated directional chamfer matching(More)