Scene Text Detection and Recognition: An Image Processing Approach

Images are captured by a variety of physical devices, including still and video cameras, scanners, X-ray devices, electron microscopes, radar, and ultrasound, and are used for a variety of purposes, including entertainment, medical, business, industrial, military, civil, security, and scientific. The interest in digital image processing is that researchers are thinking of designing a system as intelligent as the human brain. Although there are plenty of applications for image processing and pattern recognition, our focus in this book is on image which has text information, to understand the image with the help of Optical Character Recognizer (OCR), which in turn helps in indexing and retrieving semantic from the image database. This problem gains lots of researcher's interest because of the demand by real world applications, recognition and understanding text in the image plays a vital role. In the meantime, due to nature of scene text that can vary largely in fonts, font size, backgrounds, contrast, orientation and other distortions, the problem of text in scene image has become complex and challenging. Hence, scene text detection and recognition still remains an open problem.