Unlock instant, AI-driven research and patent intelligence for your innovation.

Character locating method and device in picture of digital camera

A digital image and digital technology, applied in the field of scene character positioning algorithm, can solve the problems of different character fonts, sizes and formats, low battery capacity, uneven lighting, etc.

Inactive Publication Date: 2003-02-05
NOKIA TECH OY
View PDF0 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Second, the characters may be colored or printed in any color, and the background color may differ only slightly from the character color
[0005] Third, characters may vary in font, size, and format; finally, lighting may be uneven
Therefore, these methods are not suitable for mobile devices such as mobile terminal devices, mobile cameras, mobile phones or laptop computers due to low computing power or low battery capacity

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Character locating method and device in picture of digital camera
  • Character locating method and device in picture of digital camera
  • Character locating method and device in picture of digital camera

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] figure 1 A TAD method illustrating smoothness inference in digital color images. Any image of a scene from a digital camera is polluted by noise. There are two kinds of noise: one is random noise, which is mainly caused by the camera itself; the other is "pepper-salt" noise, which is caused by smudges in natural scenes. Before the color layering of the image, it should be removed as much as possible, otherwise, good color layering results cannot be obtained. One way to reduce this "pepper-salt" noise is to use anisotropic diffusion on the scene image. The 4-connected discrete approximation of traditional anisotropic diffusion (TAD) is realized by the following formula. I ( t + 1 ) = I ( t ) + λ Σ D C D ▿ ...

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

No PUM Login to View More

Abstract

Disclosed is a method for locating characters in digital images, using an image layering process, characterized by the steps of: transforming the digital data of said digital image into normalized digital color image data and into digital grayscale image data; discarding redundant components of said normalized digital color image data and / or said digital grayscale image data; generating binary image layers from said un-discarded grayscale and normalized color image data according to a layering process using a recognition algorithm on said binary image layers to recognize connected components that can represent characters or part of characters contained in said digital image. Further, there are provided a computer program, computer program product and a device for executing the method as above.

Description

technical field [0001] The invention relates to a character positioning method. It also involves localization of characters in digital camera images with minimal use of computing power. More specifically, the present invention relates to a scene character localization algorithm for digital images based on simple robust connected components. Background technique [0002] In fields like image or video databases, characters as descriptors are key objects. It is ubiquitous in signs, directions, bulletin boards, video sequences, text documents, etc. Therefore, character extraction and recognition are very important and are widely used. For example, with the help of optical character recognition (OCR) technology, the usability of information devices like mobile phones will be enhanced. Video sequences can be automatically tagged or indexed based on recognized characters provided in a frame or frames. However, it is quite difficult to locate and extract characters from images,...

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
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06T5/00G06V30/10
CPCG06K9/342G06T2207/30176G06T7/004G06K2209/01G06K9/325G06T7/0093G06T7/70G06T7/162G06V20/62G06V30/10G06V30/15
Inventor 汪孔桥J·坎加斯
Owner NOKIA TECH OY