Image text location method and device based on connective component and support vector machine
A support vector machine and connected component technology, applied in the preprocessing field of optical character recognition, can solve problems such as low robustness, achieve high accuracy and recall rate, reduce calculation burden, and overcome the effect of requiring a large amount of calculation
Inactive Publication Date: 2008-09-17
INST OF AUTOMATION CHINESE ACAD OF SCI
View PDF0 Cites 36 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] The purpose of the present invention is mainly aimed at the fact that the robustness of existing text region positioning methods is not very high, some existing methods are based on too many artificial assumptions, and the present invention provides a robust The method and device for locating text areas in digital images with various complex backgrounds, realizes a robust text area locating method for digital images with high difficulty in text size, font, color, and background complexity, so as to facilitate subsequent text recognition prepare
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0036] The present invention will be described in detail below in conjunction with the accompanying drawings. It should be noted that the described embodiments are only intended to facilitate the understanding of the present invention, rather than limiting it in any way.
[0037]In the present invention, the input image can be an image obtained by various image acquisition units, for example: an image captured by a digital camera, a mobile phone with a shooting function, a PDA with a camera function, or a frame in a video image, etc. . If the input image is an analog signal, a digital-to-analog conversion tool is needed to convert the analog image into a digital image for processing. The image processed by the method of the present invention can be aimed at various image encoding formats, such as JPEG, BMP, etc., as long as the image in the format can be converted into a bitmap image. In this embodiment it is assumed that the input image is already a bitmap image. In the fol...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a text location method and a text location device in images based on connected components and support vector machine. The text location device comprises: an image segmentation unit; a connected region analysis unit; a unit for obtaining connected components characteristics and determining threshold value; a support vector machine classification unit; a unit for combining connected components into text region; and a unit for obtaining and determining text region statistical characteristics. The method comprises: dividing an input image to gain an image layered result; using connected components analysis to analyse prospect layer to gain a set of connected components; extracting the connected component characteristics, and using a structure of a cascade threshold classifier to exclude a plurality of non character connected components, and then using a support vector machine classification method to recognize if the rest candidate character connected components are character connected components; combining the rest connected components into candidate text regions according to principles that characteristics are consistent and distance is close, and extracting the characteristics of the candidate text regions, and using empirical threshold value to determine if the characteristics are the text regions.
Description
technical field [0001] The invention belongs to the preprocessing field of optical character recognition (OCR) of computer vision, and relates to a method and device for locating text in real scene images or video sequence images based on connected components and support vector machines, which are used for intelligent digital image analysis and understand. Background technique [0002] The text in digital images or video frames has a lot of semantic information, such as: road signs, advertisements, signage and so on. Therefore, a robust method for text localization in complex background images, combined with text recognition, will bring various practical applications, such as: content-based video indexing and image retrieval, car assisted driving, visual navigation of mobile robots, etc. application. Adding this approach to a machine translation system helps international tourists overcome language barriers. However, due to the difficulty in locating text in complex backg...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More IPC IPC(8): G06K9/72
Inventor 姚金良杨一平台宪青薛文芳
Owner INST OF AUTOMATION CHINESE ACAD OF SCI