System and method for fitting images in an electronic device

• US 8,300,053 B2
• Filed: 12/23/2009
• Issued: 10/30/2012
• Est. Priority Date: 06/29/2009
• Status: Expired due to Fees

• Current Assignee: Hong Fu Jin Precision Industry (Shenzhen) Co., Ltd. (Hon Hai Precision Industry Co., Ltd.), Hon Hai Precision Industry Co., Ltd.
• Original Assignee: Hong Fu Jin Precision Industry (Shenzhen) Co., Ltd. (Hon Hai Precision Industry Co., Ltd.), Hon Hai Precision Industry Co., Ltd.
• Inventors: Chang, Chih-Kuang, Wu, Xin-Yuan, Wang, Min
• Primary Examiner(s): Wu, Xiao M.
• Assistant Examiner(s): Hoang, Phi
• Application Number:
  US12/646,878
• Publication Number:
  US 20100328349A1
• Time in Patent Office: 1,042 Days
• Field of Search: 382/182, 382/190, 382/139
• US Class Current: 345/468
• CPC Class Codes: G06F 18/28 Determining representative reference patterns, e.g. by averaging or distorting; Generating dictionaries
• CPC Class Codes: G06V 30/10 Character recognition

Abstract

An electronic device includes an image fitting system to fit an image to identify characters of the image and graphics of the image in the electronic device. Operations of fitting the image by the image fitting system includes generation of a standard character database to fit characters of the image, generation of character fitting results by fitting each character of the image according to the standard character database, and generation of graphic fitting results by fitting each graphic of the image according to a standard graphic that is defined by a graphic equation.

Claims

1. An electronic device, comprising:

at least one storage system and at least one processor; and

an image fitting system stored in the at least one storage system, and being executable by the at least one processor to perform steps of;

(i1) obtaining an image from the at least one storage system;

(i2) obtaining standard character data from the at least one storage system;

(i3) generating a standard character database according to the standard character data;

(i4) obtaining all characters and graphics of the image;

(i5) generating image fitting results of the image by fitting each of the obtained characters according to the standard character database, and by fitting each of the obtained graphics according to a standard graphic, each of the graphics corresponding to a standard graphic that is defined by a graphic equation;

(i6) displaying the image fitting results on a display unit of the electronic device; and

(i7) filtering the image fitting results, comprising;

searching out unacceptable characters and unacceptable graphics, each of the unacceptable characters matching with none of standard characters or matches with a plurality of standard characters, and each of the unacceptable graphics matching with none of standard graphics or matches with a plurality of standard graphics;

generating a fault result list that lists searched unacceptable characters and unacceptable graphics; and

displaying the fault result list on the display unit.

2. The electronic device as described in claim 1, wherein the step (i3) further comprises:

dividing each standard character into a plurality of available pixels, by utilizing a plurality of square grids that each has a predetermined side length;

obtaining a coordinate value for each of the plurality of available pixels; and

generating a standard character database according to obtained coordinate values of the plurality of available pixels, and mapping relationships between the plurality of available pixels and standard characters.

3. The electronic device as described in claim 1, wherein the step (i4) further comprises:

dividing the image into a plurality of line segments;

searching out all intersecting line segments according to intersecting relationships among the plurality of line segments, wherein each of searched intersecting line segments refers to a line segment that is intersecting with at least one another line segment;

grouping the searched intersecting line segments according to intersecting relationships among the searched intersecting line segments, to obtain at least one line segment group, wherein each of the at least one line segment group indicates a character or a graphic; and

outputting the at least one line segment group.

4. The electronic device as described in claim 1, wherein the step (i5) further comprises:

(i51) presetting a function standard value of an iteration function, a similarity tolerance standard value, and an iteration step-length;

(i52) selecting a character or a graphic from obtained characters and graphics, selecting available pixels of selected character or selected graphic, and calculating a function value of the iteration function that selected available pixels relative to each standard character or each standard graphic, wherein each calculated function value corresponds to a standard character or a standard graphic;

(i53) analyzing whether a calculated function value is larger than the function standard value, and going to step (i59) if the calculated function value is smaller than or equal to the function standard value, or going to step (i55) if the calculated function value is larger than the function standard value;

(i55) iterating the iteration function by utilizing a least-squares Newton iteration method, to generate an iterated iteration function;

(i56) analyzing whether the iterated iteration function has a smallest function value, and going to step (i57) if the iterated iteration function has the smallest function value, or going to step (i59) if the iterated iteration function has not the smallest function value;

(i57) shifting the selected available pixels according to the iteration step-length, and calculating a shifted function value of the iterated iteration function that shifted available pixels relative to a standard character or a standard graphic, wherein the standard character or the standard graphic corresponds to the calculated function value;

(i58) analyzing whether the shifted function value is smaller than the calculated function value, and going to step (i55) if the shifted function value is smaller than the calculated function value, or going to step (i57) if the shifted function value is larger than or equal to the calculated function value;

(i59) outputting the calculated function value or the shifted function value, and analyzing the similarity tolerance between the selected character and the standard character, or the selected graphic and the standard graphic according to the similarity tolerance standard value, to obtain an acceptable character or an acceptable graphic;

(i60) repeatedly performing the steps (i52)-(i59) until all obtained characters of the image and all obtained graphics of the image are fitted; and

(i61) outputting all acceptable characters and all acceptable graphics to the display unit for display.

5. A computer-implemented method for fitting an image in an electronic device, the method comprising:

(i1) obtaining an image from the at least one storage system;

(i2) obtaining standard character data from the at least one storage system;

(i3) generating a standard character database according to the standard character data;

(i4) obtaining all characters and graphics of the image;

(i5) generating image fitting results of the image by fitting each of the obtained characters according to the standard character database, and by fitting each of the obtained graphics according to a standard graphic, each of the graphics corresponding to a standard graphic that is defined by a graphic equation;

(i6) displaying the image fitting results on a display unit of the electronic device; and

(i7) filtering the image fitting results, comprising;

searching out unacceptable characters and unacceptable graphics, each of the unacceptable characters matching with none of standard characters or matches with a plurality of standard characters, and each of the unacceptable graphics matching with none of standard graphics or matches with a plurality of standard graphics;

generating a fault result list that lists searched unacceptable characters and unacceptable graphics; and

displaying the fault result list on the display unit.

6. The method as described in claim 5, wherein the step (i3) further comprises:

dividing each standard character into a plurality of available pixels, by utilizing a plurality of square grids that each has a predetermined side length;

obtaining a coordinate value for each of the plurality of available pixels; and

generating a standard character database according to obtained coordinate values of the plurality of available pixels, and mapping relationships between the plurality of available pixels and standard characters.

7. The method as described in claim 5, wherein the step (i4) further comprises:

dividing the image into a plurality of line segments;

searching out all intersecting line segments according to intersecting relationships among the plurality of line segments, wherein each of searched intersecting line segments refers to a line segment that is intersecting with at least one another line segment;

grouping the searched intersecting line segments according to intersecting relationships among the searched intersecting line segments, to obtain at least one line segment group, wherein each of the at least one line segment group indicates a character or a graphic; and

outputting the at least one line segment group.

8. The method as described in claim 5, wherein the step (i5) further comprises:

(i51) presetting a function standard value of an iteration function, a similarity tolerance standard value, and an iteration step-length;

(i52) selecting a character or a graphic from obtained characters and graphics, selecting available pixels of selected character or selected graphic, and calculating a function value of the iteration function that selected available pixels relative to each standard character or each standard graphic, wherein each calculated function value corresponds to a standard character or a standard graphic;

(i53) analyzing whether a calculated function value is larger than the function standard value, and going to step (i59) if the calculated function value is smaller than or equal to the function standard value, or going to step (i55) if the calculated function value is larger than the function standard value;

(i55) iterating the iteration function by utilizing a least-squares Newton iteration method, to generate an iterated iteration function;

(i56) analyzing whether the iterated iteration function has a smallest function value, and going to step (i57) if the iterated iteration function has the smallest function value, or going to step (i59) if the iterated iteration function has not the smallest function value;

(i57) shifting the selected available pixels according to the iteration step-length, and calculating a shifted function value of the iterated iteration function that shifted available pixels relative to a standard character or a standard graphic, wherein the standard character or the standard graphic corresponds to the calculated function value;

(i58) analyzing whether the shifted function value is smaller than the calculated function value, and going to step (i55) if the shifted function value is smaller than the calculated function value, or going to step (i57) if the shifted function value is larger than or equal to the calculated function value;

(i59) outputting the calculated function value or the shifted function value, and analyzing the similarity tolerance between the selected character and the standard character, or the selected graphic and the standard graphic according to the similarity tolerance standard value, to obtain an acceptable character or an acceptable graphic;

(i60) repeatedly performing the steps (i52)-(i59) until all obtained characters of the image and all obtained graphics of the image are fitted; and

(i61) outputting all acceptable characters and all acceptable graphics to the display unit for display.

9. A non-transitory storage medium having stored thereon instructions that, when executed by a processor of an electronic device, causing the electronic device to perform a method for fitting an image, wherein the method comprises:

(i1) obtaining an image from the at least one storage system;

(i2) obtaining standard character data from the at least one storage system;

(i3) generating a standard character database according to the standard character data;

(i4) obtaining all characters and graphics of the image;

(i5) generating image fitting results of the image by fitting each of the obtained characters according to the standard character database, and by fitting each of the obtained graphics according to a standard graphic, each of the graphics corresponding to a standard graphic that is defined by a graphic equation;

(i6) displaying the image fitting results on a display unit of the electronic device; and

(i7) filtering the image fitting results comprising;

searching out unacceptable characters and unacceptable graphics, each of the unacceptable characters matching with none of standard characters or matches with a plurality of standard characters, and each of the unacceptable graphics matching with none of standard graphics or matches with a plurality of standard graphics;

generating a fault result list that lists searched unacceptable characters and unacceptable graphics; and

displaying the fault result list on the display unit.

10. The non-transitory storage medium as described in claim 9, wherein the step (i3) further comprises:

dividing each standard character into a plurality of available pixels, by utilizing a plurality of square grids that each has a predetermined side length;

obtaining a coordinate value for each of the plurality of available pixels; and

generating a standard character database according to obtained coordinate values of the plurality of available pixels, and mapping relationships between the plurality of available pixels and standard characters.

11. The non-transitory storage medium as described in claim 9, wherein the step (i4) further comprises:

dividing the image into a plurality of line segments;

searching out all intersecting line segments according to intersecting relationships among the plurality of line segments, wherein each of searched intersecting line segments refers to a line segment that is intersecting with at least one another line segment;

grouping the searched intersecting line segments according to intersecting relationships among the searched intersecting line segments, to obtain at least one line segment group, wherein each of the at least one line segment group indicates a character or a graphic; and

outputting the at least one line segment group.

12. The non-transitory storage medium as described in claim 9, wherein the step (i5) further comprises:

(i51) presetting a function standard value of an iteration function, a similarity tolerance standard value, and an iteration step-length;

(i52) selecting a character or a graphic from obtained characters and graphics, selecting available pixels of selected character or selected graphic, and calculating a function value of the iteration function that selected available pixels relative to each standard character or each standard graphic, wherein each calculated function value corresponds to a standard character or a standard graphic;

(i53) analyzing whether a calculated function value is larger than the function standard value, and going to step (i59) if the calculated function value is smaller than or equal to the function standard value, or going to step (i55) if the calculated function value is larger than the function standard value;

(i55) iterating the iteration function by utilizing a least-squares Newton iteration method, to generate an iterated iteration function;

(i56) analyzing whether the iterated iteration function has a smallest function value, and going to step (i57) if the iterated iteration function has the smallest function value, or going to step (i59) if the iterated iteration function has not the smallest function value;

(i57) shifting the selected available pixels according to the iteration step-length, and calculating a shifted function value of the iterated iteration function that shifted available pixels relative to a standard character or a standard graphic, wherein the standard character or the standard graphic corresponds to the calculated function value;

(i58) analyzing whether the shifted function value is smaller than the calculated function value, and going to step (i55) if the shifted function value is smaller than the calculated function value, or going to step (i57) if the shifted function value is larger than or equal to the calculated function value;

(i59) outputting the calculated function value or the shifted function value, and analyzing the similarity tolerance between the selected character and the standard character, or the selected graphic and the standard graphic according to the similarity tolerance standard value, to obtain an acceptable character or an acceptable graphic;

(i60) repeatedly performing the steps (i52)-(i59) until all obtained characters of the image and all obtained graphics of the image are fitted; and

(i61) outputting all acceptable characters and all acceptable graphics to the display unit for display.