Granted Patent B2

US 8,135,217 · App. 12/963,651 · Granted Mar 13, 2012

Abstract

Claims (24)

1. A method for aligning a camera sensor to significant data which is text or barcode data to be recognized comprising the steps of:

a) capturing an image of the significant data by means of the camera sensor;

b) adapting contrast, compensating shade and processing an adaptive binarization of the image to obtain an artifact reduced image;

c) edge and line filtering of the artifact reduced image to obtain an edge and line enhanced image;

d) processing a transformation of the edge and line enhanced image by means of a robust algorithm for predominant alignment line angle detection of the significant data contained in the image in respect to a horizontal line of the camera sensor, such as to obtain a predominant alignment line, the predominant alignment line angle representing the inclination of the predominant alignment line in respect to the horizontal line;

e) determining image sections within the edge and line enhanced image which contain most likely significant data lines, comprising the following sub-steps:

detecting significant data lines which are substantially in alignment with the predominant alignment line;

determining distances between adjacent significant data lines; and

determining the image sections with substantially equally spaced apart adjacent significant data lines;

f) selecting a representative image section out of the determined image sections with the highest likelihood of containing significant data and being aligned with the predominant alignment line;

g) capturing a following image of the significant data by means of the camera sensor;

h) applying steps b) and c) again, taking the following image now as the image for said image processing within steps b) and c) and obtaining an edge and line enhanced image;

i) detecting and tracking the representative image section within the edge and line enhanced image of step h);

k) starting the process again at step d) if the representative image could not be detected and tracked again within step i);

l) determining the predominant alignment line angle from the representative image section in respect to the horizontal line of the camera sensor;

m) generating an user feedback signal dependent on the predominant alignment line angle and checking whether the predominant alignment line angle is equal or below a threshold;

n) repeating the process from step g) onwards if the predominant alignment line angle is above the threshold and the process of the alignment of the camera sensor to the significant data is not stopped by other means such as user action;

n) storing the last taken image or making immediately a high resolution image for a further processing if the predominant alignment line angle is below or equal to the threshold or if the process of the alignment of the camera sensor to the significant data is stopped by other means such as user action.

2. The method of claim 1 , wherein the robust algorithm for predominant alignment line angle detection is a Hough transformation algorithm or the like.

3. The method of claim 1 , wherein the feedback signal is an audio signal having a variable tone frequency in dependence on the detected predominant alignment line angle.

4. The method of claim 1 , wherein the feedback signal is a tactile signal having a variable frequency in dependence on the detected predominant alignment line angle.

5. The method of claim 1 , wherein the feedback signal is an LED signal or the like or a combination thereof with an audio and/or tactile signal.

6. The method of claim 1 , wherein the feedback signal is a combination of an audio signal and a tactile signal having a variable frequency in dependence on the detected predominant alignment line angle.

7. The method of claim 1 , wherein step e) also comprises after the determination of the image sections determining rectangle corner coordinates of the image sections; and storing the rectangle corner coordinates for later use.

Assignments (8)