Arbitrary direction text line detection method in natural image

Abstract

The invention discloses an arbitrary direction text line detection method in a natural image. The arbitrary direction text line detection method in the natural image comprises the following steps: (1) candidate text areas are detected through a maximum stable extreme area detection method with restriction, compound similarity among area pairs is obtained according to combination with size of the areas, absolute distance, relative distance, geometric similarity in a contextual information definition area and color similarity; (2) three areas are found, serve as seed areas of a candidate text line and are expanded to all areas in the line through a candidate text line identification method based on the similarity; and (3) non-text lines are removed through a filter based on morphologic framework characteristics, the filter conducts filtering through a sparse classifier and characteristic vectors required by the classifier are taken from the morphologic framework characteristics in all areas of the candidate text line. The arbitrary direction text line detection method in the natural image can detect text in arbitrary directions in the natural image. In addition, due to adoption of the area interior characteristic structured classifier, better identification accuracy can be achieved.

Description

technical field [0001] The invention relates to a method for detecting text lines in an arbitrary direction in a natural image. The method is used to detect scene text in an arbitrary direction in a natural image for OCR recognition, and belongs to the field of computer image processing. Background technique [0002] With the development of multimedia and electronic industries, more and more image information is produced. How to effectively organize and retrieve them becomes a difficult problem. Many image materials contain text information, such as book covers, street signs, buildings (with name information), etc. These text information are closely related to image content. If these text information can be effectively detected and recognized, they can be used to organize and retrieve image data, which has strong practical value. [0003] Word / text detection can be divided into three methods: gradient-based methods, color-clustering-based methods, and texture-based methods...

AI Technical Summary

Problems solved by technology

The method based on color clustering assumes that the text color in the video frame is uniform, but this assumption is not true in most cases, so its application is limited

Since the effect of subtitle detection using one feature is not ideal, many methods use the above features in combination

[0004] The above text detection methods have made some useful attempts, but due to the characteristics of natural scene texts that are not strong in discrimination from the background, arbitrary in direction, and not fixed in position, these methods are not effective in detecting text in any direction in natural images. good

Images