Achieving good text detection and recognition results for multi-script-oriented images is a
challenging task. First, we explore bit plane slicing in order to utilize the advantage of the …

摘要本文对自然场景文本检测问题及其方法的研究进展进行了综述. 首先,
论述了自然场景文本的特点, 自然场景文本检测技术的研究背景, 现状以及主要技术路线. 其次 …

Scene image or video understanding is a challenging task especially when number of video
types increases drastically with high variations in background and foreground. This paper …

The principal goal of optical character recognition system (OCR) is to recognize the classes
of unknown handwritten characters using a previously stored dataset of characters' classes …

Captions in videos play an important role for video indexing and retrieval. In this paper, we
propose a novel algorithm to extract multilingual captions from video. Our approach is based …

Deep CNNs have achieved great success in text detection. Most of existing methods attempt
to improve accuracy with sophisticated network design, while paying less attention on …

In this paper, a virtual assistant for the visually impaired is built using various technologies
such as computer vision, object recognition, emotion detection, and text-to-speech using a …

Scene text detection has been attracting increasing interests in recent years and a rich body
of approaches has been proposed. These previous works of detecting scene text have been …

A method for extraction of descriptors from video content, includes the following steps: a Key
Frame Extracting step, applying a local descriptors-based approach to select pictures of the …

Text recognition is a field to detect text from digital images and produces meaningful
information for various applications such as navigation, object recognition, hoardings, image …