CN103425973A - Method and apparatus for performing enhancement processing on text-containing image, and video display device - Google Patents
Method and apparatus for performing enhancement processing on text-containing image, and video display device Download PDFInfo
- Publication number
- CN103425973A CN103425973A CN2012101645527A CN201210164552A CN103425973A CN 103425973 A CN103425973 A CN 103425973A CN 2012101645527 A CN2012101645527 A CN 2012101645527A CN 201210164552 A CN201210164552 A CN 201210164552A CN 103425973 A CN103425973 A CN 103425973A
- Authority
- CN
- China
- Prior art keywords
- image
- text filed
- text
- pixel
- filed
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Landscapes
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a method and apparatus for performing enhancement processing on a text-containing image, and a video display device. The method comprises the follow steps: detecting the text area of the image, performing the enhancement processing on the image, and outputting the image after the enhancement processing, wherein the enhancement processing performed on the non-text area of the image is associated with the enhancement processing performed on the text area of the image. The provided apparatus is corresponding to the provided method. The video display device comprises the apparatus and is used for performing the enhancement processing on the image extracted from a video. When the method, the apparatus and the video display device provided by the invention are utilized for performing the enhancement processing on the text-containing image having a complex background or a complex natural background, the obtained image exhibits more coordinated visual effects.
Description
Technical field
The present invention relates to image processing techniques, more specifically, relate to for the image to containing text and strengthen method, device and the video display apparatus of processing.
Background technology
In image processing field, need to be processed the image that contains text (as captions).In order to realize the processing to this class image, the Chinese patent application No.200810119340.0 that is entitled as " a kind of video subtitle processing apparatus and method " proposes: when carrying out the captions processing, at first detect the caption area in image, then (the grey level by the background area beyond background removal unit caption area is set to 0, background is set to black), then the black background that comprises captions is strengthened to processing, finally with the caption area after strengthening, substitute the caption area in original video.
When background area is complex background or natural background, above-mentioned method for processing caption usually cause caption area and background area display effect difference huge, the whole display effect of video image is discord very much.
On the other hand, existing three kinds of main text positioning methods (text positioning method of analyzing based on connected domain (Connected component), text positioning method and the text positioning method based on rim detection based on texture analysis) are although each tool advantage all can't reach gratifying matching precision while in complex background or natural background, text being positioned.
Particularly, the text positioning method based on connected domain analysis is unsuitable for complex background or natural background, and the text positioning method precision based on texture analysis is not high, the easy mismatch of the text positioning method based on rim detection.
Thereby, while in background area, being complex background or natural background, the text filed positioning error that existing text positioning method causes also can make the display effect of video image worsen.
Summary of the invention
The object of the invention is to: a kind of method, device and video display apparatus of processing that strengthen for the image to containing text is provided, thoroughly eliminates or at least alleviate at least one in the problems referred to above.
For realizing above purpose, according to a first aspect of the invention, provide a kind of equipment of processing that strengthens for the image to containing text, comprising: text filed detecting unit, text filed for detection of image, and obtain the text locating information; Strengthen processing unit, for based on described text locating information, image is carried out to strengthen and process; And output unit, for exporting the image after strengthen processing, wherein strengthen processing unit the enhancing of the non-text filed execution of image is processed with the enhancing processing of text filed execution to image and is associated.
Alternatively, described enhancing processing unit can only strengthen to the non-text filed and text filed execution of image the enhancing processing that processing gain is different.
Alternatively, described enhancing processing unit can comprise: wave filter strengthens processing for image being carried out to filtering; Selector switch, for based on described text locating information, for the text filed and non-text filed pixel that is arranged in image, select different gains; Multiplier, apply for the pixel that filtering is strengthened to the text filed and non-text filed relevant position of the image after processing the gain of being selected based on described text locating information by described selector switch; And totalizer, for applying pixel after gain and the pixel addition of original image relevant position.
Alternatively, described enhancing processing unit can comprise: the first wave filter strengthens and processes for image text filed being carried out to the logical or high-pass filtering of the first band; The second wave filter, strengthen and process for image non-text filed being carried out to the logical or high-pass filtering of the second band; The first multiplier, apply the first gain for the text filed pixel of the image to after the first filter process; The second multiplier, apply the second gain for the non-text filed pixel of the image to after the second filter process; Selector switch, for based on described text locating information, for the text filed and non-text filed pixel that is arranged in image, select respectively the pixel of the first multiplier and the output of the second multiplier; And totalizer, for the pixel addition of the pixel by selecting and original image relevant position.
Alternatively, the gain that described multiplier applies the pixel in image non-text filed can be less than the gain that the pixel in image text filed is applied.
Alternatively, described the first wave filter can be the bandpass filter that centre frequency is partial to high frequency side, and described the second wave filter can be Hi-pass filter.
Alternatively, described text filed detecting unit can convert the text filed of detected image by carrying out connected domain analysis and stroke width.
Alternatively, described text filed detecting unit detects text filed in the preset range of image.
Alternatively, described image can be the frame in video.
Alternatively, the text filed testing result that described text filed detecting unit can be based on previous frame, detect the text filed of present image.
Alternatively, described text filed text message can comprise following at least one: the credits present of the comment of image, the captions of video work or video work.
According to a second aspect of the invention, proposed a kind of method of processing that strengthens for the image to containing text, comprised the following steps: detected image text filed; Image is carried out to strengthen and process; And the image of output after strengthen processing, wherein the enhancing of the non-text filed execution of image is processed with the enhancing processing of text filed execution to image and is associated.
According to a third aspect of the invention we, proposed a kind of video display apparatus, having comprised: image acquiring apparatus, for from video, extracting image; According to the device of second aspect present invention, for the image to extracting from video, carry out image enhancement processing; Image combining apparatus is video for the image combining by after processing; And video output device, for exporting the video after combination.
Adopt technical scheme of the present invention to be processed the image that contains text, the whole display effect of the image after can making to process is more harmonious.In addition, adopt technical scheme of the present invention to be processed the image that contains text, can improve the precision of text location, thus and the display effect of the image after the improvement processing.In addition, adopt technical scheme of the present invention to be processed the video that contains text, can improve the precision of text location, thus and the display effect of the video after the improvement processing.It should be noted that, although technical scheme of the present invention be particularly suitable for thering is being processed containing text image of complex background or natural background, even also can obtain above advantage for what there is simple background containing text image.
The accompanying drawing explanation
By below in conjunction with accompanying drawing explanation the preferred embodiments of the present invention, will make of the present invention above-mentioned and other objects, features and advantages are clearer, wherein:
Fig. 1 shows the structured flowchart according to image enhancement processing device of the present invention;
Fig. 2 shows the figure according to the first example implementation of the enhancing processing unit of image enhancement processing device of the present invention;
Fig. 3 shows the figure according to the second example implementation of the enhancing processing unit of image enhancement processing device of the present invention;
Fig. 4 shows the process flow diagram according to image enhancement processing method of the present invention;
Fig. 5 shows the process flow diagram according to the text position fixing process of image enhancement processing method of the present invention;
Fig. 6 shows the block diagram according to video display apparatus of the present invention;
Fig. 7 shows the figure of the characteristic of the wave filter that can use in first of image enhancement processing device according to the present invention is realized; And
Fig. 8 shows the figure of the characteristic of the wave filter that can use in second of image enhancement processing device according to the present invention is realized.
Embodiment
To a preferred embodiment of the present invention will be described in detail, in the description process, having omitted is unnecessary details and function for the present invention with reference to the accompanying drawings, to prevent that the understanding of the present invention from causing, obscures.
At first, with reference to Fig. 1, the structure of image enhancement processing device 100 according to the present invention is described.As shown in Figure 1, image enhancement processing device 100 comprises text filed detecting unit 110, strengthens processing unit 120 and output unit 130.Text filed detecting unit 110 is text filed for detection of pending image, and obtains the relevant text locating information in the position in image with text.The text locating information that enhancing processing unit 120 utilizes text filed detecting unit 110 to obtain is come image is carried out to strengthen to process.Output unit 130 outputs have carried out strengthening the image after processing by strengthening processing unit 120.From text filedly remove that rear that text filed independent execution is strengthened to the mode of processing is different by non-in prior art,, the non-text filed execution of image is processed to the enhancing be associated with the enhancing of text filed execution to image and process based on the text locating information according to the enhancing processing unit 120 of technical scheme of the present invention.Image after the enhancing obtained by this mode is processed is text filed and non-text filed enhancing processing of having carried out being mutually related because of it, and whole display effect is more harmonious.
In order to make that the enhancing of the non-text filed execution of image is processed with the enhancing processing of text filed execution to image and is associated, as a kind of simple mode, can for example by strengthening processing unit 120, be embodied as: the non-text filed and text filed execution to image only strengthens the enhancing processing that processing gain is different.As another kind of mode, can be for example by strengthening processing unit 120, be embodied as: to the enhancing processing of the non-text filed and text filed execution same type of image.Without loss of generality, can also adopt neatly various other modes to realize strengthening processing unit 120, make the enhancing of the non-text filed execution of image is processed with the enhancing processing of text filed execution to image and is associated.
Below, with reference to Fig. 2 and Fig. 3, two kinds of example implementation that strengthen processing unit 120 are described.As shown in Figure 2, strengthen processing unit and comprise wave filter 210, selector switch 220, multiplier 230 and totalizer 240.210 pairs, wave filter comprises that text filed and non-text filed original image carries out filtering and strengthen to process, thereby makes the enhancing processing to the text filed and non-text filed execution of original image be associated.
The text locating information of selector switch 220 based on from outside, for the text filed and non-text filed pixel that is arranged in image, select different gain K
TAnd K
I.Particularly, when being arranged in image text filed, pixel selects K
T, select K when pixel is arranged in image text filed
T.If expect text filedly can obtain larger enhancing effect, can be by K
TBe set to be greater than K
I.
The pixel that 230 pairs of filtering of multiplier strengthen the text filed and non-text filed middle relevant position of the image after processing applies the selected gain of selector switch 220.Finally, totalizer 240 will apply the pixel addition of relevant position in pixel after gain and original image, the image be enhanced after processing.
Fig. 3 shows another example implementation that strengthens processing unit.As shown in Figure 3, this enhancing processing unit comprises the first wave filter 310, the second wave filter 320, selector switch 330, multiplier 340 and totalizer 350.310 pairs of images of the first wave filter text filed carries out the logical or high-pass filtering of the first band and strengthens and process, and 320 pairs of images of the second wave filter non-text filed carries out the logical or high-pass filtering of the second band and strengthen and process.Thus, the low frequency component in original image text filed and non-text filed is all by filtering, and the enhancing of the text filed and non-text filed execution of original image is processed and is associated.
Pixel in image after the first 340 pairs of multipliers filtering strengthen to be processed text filed applies selector switch 220 gain K
T.Pixel in image after the second 350 pairs of multipliers filtering strengthen to be processed non-text filed applies the second gain K
I.The text locating information of selector switch 330 based on from outside, for the text filed and non-text filed pixel that is arranged in image, select respectively the pixel of the first multiplier and the output of the second multiplier.If expect text filedly can obtain larger enhancing effect, can be by K
TBe set to be greater than K
I.Finally, totalizer 360 is by the pixel addition of relevant position in the pixel selected and original image.
As the non-limiting example of above-mentioned wave filter 210, Fig. 7 shows the normalized frequency characteristic of the single 7 tap FIR wave filters for entire image being carried out to sharpening.As the non-limiting example of above-mentioned the first wave filter 310 and the second wave filter 320, Fig. 8 shows for respectively for the text filed and non-text filed normalized frequency characteristic of carrying out two different wave filters of sharpening of image.As shown in Figure 8, the text filed wave filter that carries out sharpening is had to wider passband at lower frequency side, thereby can effectively strengthen large edge and profile (as, the stroke of character); Be Hi-pass filter to the non-text filed wave filter that carries out sharpening, thereby can be strengthened edge less in natural background or complex background and careful texture.
Should be understood that, except sharpening, process, the present invention also is suitable for other image enhancement techniques, includes but not limited to: picture contrast (contrast) is adjusted; Dynamic range of images (Dynamic Range) is adjusted, etc.
Fig. 4 has provided the process flow diagram according to image enhancement processing method of the present invention.After starting, process advances to step S410.At step S410, detected image text filed, and obtain the text locating information.Then, process advances to step S420.At step S420, image is carried out to strengthen and process, make the enhancing of non-text filed execution is processed with the enhancing to text filed execution and processed and be associated.Then, execution step S430, output strengthens the image after processing.Finally, process finishes.
Below, with reference to Fig. 5, the process flow diagram according to the text position fixing process of image enhancement processing method of the present invention is described.It should be noted that, for the ease of narration, provided some optional steps with empty wire frame representation in Fig. 5, these steps are mainly used in when from video image, detection is text filed, optimization process speed and precision.One of ordinary skill in the art are appreciated that can suitably save these steps when the image to non-correlation is processed.
As shown in Figure 5, after process starts, advance to step S501, obtain present image from video.Then, process advances to step S502.At step S502, image is carried out to binary conversion treatment.That is the image that is, 0 or 1 by image transitions for each pixel value.In order to obtain better binary image, entire image can be divided into to a plurality of block of pixels (for example, size is the block of pixels of 60x60 pixel), and be provided for respectively carrying out the compare threshold of binaryzation in each piece.Then, execution step S503, extract connected domain according to binary image.
Then, at step S504, the statistical information based on previous frame (as, the size of connected domain and upright position), connected domain is filtered.In step S505, the stroke in a character is merged.In step S506, based on marginal density and other stroke features, again connected domain is filtered.In step S507, will merge into a sentence with all connected domains that there is reasonable distance in a line.
With above-mentioned steps concurrently or serially, in step S508, extract the edge of present image by edge extracting device (as, Canny edge extracting device).Then, at step S509, carry out stroke width conversion (SWT).Output meets stroke width normative text candidate.Then, at step S510, based on the stroke density feature preserving, only comprise the text filed of single character.
Subsequently, at step S511, text filed according to SWT feature expansion connected domain, text zone can be sentence or character.In addition, at step S512, if exist overlapping or cover, the connected domain after expansion is merged.Afterwards, at step S513, obtain the text positioning result of present image, and it is exported to and strengthens processing unit 120.Preferably, when obtaining the text positioning result of present image, can be with reference to the location empirical value of previous frame or consecutive frame.Simultaneously, at step S514, record the text positioning result of present image, and produce the statistical information that can use in step S504.If also have other images to wait to process in video, return to step S501.Otherwise process finishes.
Above-mentioned text position fixing process is combined with connected domain analysis and stroke width conversion (SWT) carrys out the text filed of detected image, can detect exactly the text under natural background, wherein, stroke width conversion (SWT) is the computing of a kind of topography, for each pixel, calculate the width of the most probable stroke that comprises this pixel.The output of SWT is the numerical matrix measure-alike with the picture element matrix of input picture, and the value of its each element is exactly the width of the stroke that is associated with respective pixel.Different from other features for text detection, SWT (stroke width depends on the information of the pixel away from very from current pixel sometimes) in global scope carries out density Estimation, thereby can reach higher precision.
Below, with reference to Fig. 6, describe according to video display apparatus 600 of the present invention.As shown in Figure 6, video display apparatus 600 comprises image acquiring apparatus 610, image intensifier device 620, image combining apparatus 630 and video output device 640.Image acquiring apparatus 610 extracts image from video.Image intensifier device 620 is image enhancement processing devices 100 as above.Image combining apparatus 630 is video by the image combining after processing.Video after video output device 640 output combinations.Video display apparatus 600 comprises any equipment that can display video such as TV, portable computer, desk-top computer, mobile phone, personal digital assistant.
As a further improvement on the present invention, in the situation that the general location in known text zone, can be defined in image preset range (as, captions for video work extract, can considering screen the scope of below 25%) in detect text filed, thereby improve detection efficiency saving resource consumption.Text message in text filed can be the comment of image, the captions of video work or the credits present of video work etc.
It should be noted in the discussion above that in above description, only in the mode of example, show technical scheme of the present invention, but be not intended that the invention be limited to above-mentioned steps and cellular construction.Under possible situation, can be adjusted and be accepted or rejected step and cellular construction as required.Therefore, the necessary element of overall invention thought of the present invention is not implemented in some step and unit.Therefore, technical characterictic essential to the invention only is limited to the minimum requirements that can realize overall invention thought of the present invention, and is not subject to the restriction of above instantiation.
So far invention has been described in conjunction with the preferred embodiments.Should be appreciated that, those skilled in the art without departing from the spirit and scope of the present invention, can carry out various other change, replacement and interpolations.Therefore, scope of the present invention is not limited to above-mentioned specific embodiment, and should be limited by claims.
Claims (23)
1. a device that strengthens to process for the image to containing text comprises:
Text filed detecting unit, text filed for detection of image, and obtain the text locating information;
Strengthen processing unit, for based on described text locating information, image is carried out to strengthen and process; And
Output unit, for exporting the image strengthened after processing, wherein
Described enhancing processing unit is processed with the enhancing processing of text filed execution to image and is associated the enhancing of the non-text filed execution of image.
2. device according to claim 1, wherein, described enhancing processing unit only strengthens to the non-text filed and text filed execution of image the enhancing that processing gain is different to be processed.
3. device according to claim 2, wherein, described enhancing processing unit comprises:
Wave filter, strengthen processing for image being carried out to filtering;
Selector switch, for based on described text locating information, for the text filed and non-text filed pixel that is arranged in image, select different gains;
Multiplier, apply for the pixel that filtering is strengthened to the text filed and non-text filed relevant position of the image after processing the gain of being selected based on described text locating information by described selector switch; And
Totalizer, for applying pixel after gain and the pixel addition of original image relevant position.
4. device according to claim 1, wherein, described enhancing processing unit comprises:
The first wave filter, strengthen and process for image text filed being carried out to the logical or high-pass filtering of the first band;
The second wave filter, strengthen and process for image non-text filed being carried out to the logical or high-pass filtering of the second band;
The first multiplier, apply the first gain for the text filed pixel of the image to after the first filter process;
The second multiplier, apply the second gain for the non-text filed pixel of the image to after the second filter process;
Selector switch, for based on described text locating information, for the text filed and non-text filed pixel that is arranged in image, select respectively the pixel of the first multiplier and the output of the second multiplier; And
Totalizer, for the pixel addition of the pixel by selecting and original image relevant position.
5. according to the described device of any one in claim 2 to 4, wherein, the gain that described multiplier applies the pixel in image non-text filed is less than the gain that the pixel in image text filed is applied.
6. device according to claim 4, wherein, described the first wave filter is the bandpass filter that centre frequency is partial to high frequency side, described the second wave filter is Hi-pass filter.
7. according to the described device of any one in claim 1～6, wherein, described text filed detecting unit is combined with connected domain analysis and stroke width converts the text filed of detected image.
8. according to the described device of any one in claim 1～7, wherein, described text filed detecting unit detects text filed in the preset range of image.
9. according to the described device of claim 1～8, wherein, described image is the frame in video.
10. device according to claim 9, wherein, the text filed detection statistics of described text filed detecting unit based on previous frame, detect the text filed of present image.
11., according to the described device of any one in claim 1～10, wherein, described text filed text message comprises following at least one: the credits present of the comment of image, the captions of video work or video work.
12. a video display apparatus comprises:
Image acquiring apparatus, for extracting image from video;
According to the described device of claim 1 to 11, for the image to extracting from video, carry out image enhancement processing;
Image combining apparatus is video for the image combining by after processing; And
Video output device, for exporting the video after combination.
13. a method that strengthens to process for the image to containing text comprises the following steps:
Detected image text filed, and obtain the text locating information;
Based on described text locating information, image is carried out to strengthen and process; And
Output strengthens the image after processing, wherein
The enhancing of the non-text filed execution of image is processed with the enhancing processing of text filed execution to image and is associated.
14. method according to claim 13, wherein, only strengthen to the non-text filed and text filed execution of image the enhancing that processing gain is different and process.
15. method according to claim 14, the described step that image execution enhancing is processed comprises:
Image is carried out to filtering and strengthen processing;
Based on described text locating information, for the text filed and non-text filed pixel that is arranged in image, select different gains;
The pixel that filtering is strengthened to the text filed and non-text filed middle relevant position of the image after processing applies the gain of selecting based on described text locating information; And
The pixel addition of relevant position in pixel after gain and original image will be applied.
16. method according to claim 13, wherein, the described step that image execution enhancing is processed comprises:
Image text filed carried out to the logical or high-pass filtering of the first band to strengthen and processes;
Image non-text filed carried out to the logical or high-pass filtering of the second band to strengthen and processes;
Pixel in image after the first filtering strengthen is processed text filed applies the first gain;
Pixel in image after the second filtering strengthen is processed non-text filed applies the second gain;
Based on described text locating information, for the text filed and non-text filed pixel that is arranged in image, the pixel after having selected respectively to apply the first gain and having applied the first gain; And
Pixel addition by relevant position in the pixel selected and original image.
17., according to claim 14 to the described method of any one in 16, wherein, the gain that the pixel in image non-text filed is applied is less than the gain that the pixel in image text filed is applied.
18. method according to claim 16, wherein, described the first band leads to or high-pass filtering is the bandpass filtering that centre frequency is partial to high frequency side, and described the second band leads to or high-pass filtering is high-pass filtering.
19., according to the described method of any one in claim 13～18, wherein, be combined with connected domain analysis and stroke width and convert the text filed of detected image.
20., according to the described method of any one in claim 13～19, wherein, detect text filed in the preset range of image.
21., according to the described method of claim 13～20, wherein, described image is the frame in video.
22. method according to claim 21, wherein, the text filed detection statistics based on previous frame, detect the text filed of present image.
23., according to the described method of any one in claim 13～22, wherein, described text filed text message comprises following at least one: the credits present of the comment of image, the captions of video work or video work.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210164552.7A CN103425973B (en) | 2012-05-25 | 2012-05-25 | The method, apparatus and video display apparatus of enhancing processing are carried out to the image containing text |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210164552.7A CN103425973B (en) | 2012-05-25 | 2012-05-25 | The method, apparatus and video display apparatus of enhancing processing are carried out to the image containing text |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103425973A true CN103425973A (en) | 2013-12-04 |
| CN103425973B CN103425973B (en) | 2019-05-31 |
Family
ID=49650685
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210164552.7A Expired - Fee Related CN103425973B (en) | 2012-05-25 | 2012-05-25 | The method, apparatus and video display apparatus of enhancing processing are carried out to the image containing text |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103425973B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105303156A (en) * | 2014-06-19 | 2016-02-03 | 株式会社东芝 | Character Detection Apparatus, Method and program |
| CN106204425A (en) * | 2016-06-28 | 2016-12-07 | 广东欧珀移动通信有限公司 | A kind of present the method for augmented reality content, device and mobile terminal |
| CN107424137A (en) * | 2017-08-01 | 2017-12-01 | 深信服科技股份有限公司 | A kind of Text enhancement method and device, computer installation, readable storage medium storing program for executing |
| CN112488107A (en) * | 2020-12-04 | 2021-03-12 | 北京华录新媒信息技术有限公司 | Video subtitle processing method and processing device |
| CN112749599A (en) * | 2019-10-31 | 2021-05-04 | 北京金山云网络技术有限公司 | Image enhancement method and device and server |
| CN114758332A (en) * | 2022-06-13 | 2022-07-15 | 北京万里红科技有限公司 | Text detection method and device, computing equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1677440A (en) * | 2004-03-31 | 2005-10-05 | 富士通株式会社 | Image magnification device and image magnification method |
| CN102081731A (en) * | 2009-11-26 | 2011-06-01 | 中国移动通信集团广东有限公司 | Method and device for extracting text from image |
| CN102214357A (en) * | 2011-06-22 | 2011-10-12 | 王洪剑 | Image enhancement method and system |
| CN102270340A (en) * | 2011-09-05 | 2011-12-07 | 上海果壳电子有限公司 | Method and system for enhancing text image based on stroke operator |
| CN102292741A (en) * | 2009-01-20 | 2011-12-21 | 皇家飞利浦电子股份有限公司 | Method and apparatus for generating enhanced images |
-
2012
- 2012-05-25 CN CN201210164552.7A patent/CN103425973B/en not_active Expired - Fee Related
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1677440A (en) * | 2004-03-31 | 2005-10-05 | 富士通株式会社 | Image magnification device and image magnification method |
| CN102292741A (en) * | 2009-01-20 | 2011-12-21 | 皇家飞利浦电子股份有限公司 | Method and apparatus for generating enhanced images |
| CN102081731A (en) * | 2009-11-26 | 2011-06-01 | 中国移动通信集团广东有限公司 | Method and device for extracting text from image |
| CN102214357A (en) * | 2011-06-22 | 2011-10-12 | 王洪剑 | Image enhancement method and system |
| CN102270340A (en) * | 2011-09-05 | 2011-12-07 | 上海果壳电子有限公司 | Method and system for enhancing text image based on stroke operator |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105303156A (en) * | 2014-06-19 | 2016-02-03 | 株式会社东芝 | Character Detection Apparatus, Method and program |
| US10339657B2 (en) | 2014-06-19 | 2019-07-02 | Kabushiki Kaisha Toshiba | Character detection apparatus and method |
| CN105303156B (en) * | 2014-06-19 | 2020-04-21 | 株式会社东芝 | Character detection device, method, and program |
| CN106204425A (en) * | 2016-06-28 | 2016-12-07 | 广东欧珀移动通信有限公司 | A kind of present the method for augmented reality content, device and mobile terminal |
| CN106204425B (en) * | 2016-06-28 | 2020-02-14 | Oppo广东移动通信有限公司 | Method and device for presenting augmented reality content and mobile terminal |
| CN107424137A (en) * | 2017-08-01 | 2017-12-01 | 深信服科技股份有限公司 | A kind of Text enhancement method and device, computer installation, readable storage medium storing program for executing |
| CN112749599A (en) * | 2019-10-31 | 2021-05-04 | 北京金山云网络技术有限公司 | Image enhancement method and device and server |
| CN112488107A (en) * | 2020-12-04 | 2021-03-12 | 北京华录新媒信息技术有限公司 | Video subtitle processing method and processing device |
| CN114758332A (en) * | 2022-06-13 | 2022-07-15 | 北京万里红科技有限公司 | Text detection method and device, computing equipment and storage medium |
| CN114758332B (en) * | 2022-06-13 | 2022-09-02 | 北京万里红科技有限公司 | Text detection method and device, computing equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103425973B (en) | 2019-05-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Lu et al. | Real-time contrast preserving decolorization | |
| CN103425973A (en) | Method and apparatus for performing enhancement processing on text-containing image, and video display device | |
| RU2637989C2 (en) | Method and device for identifying target object in image | |
| RU2721188C2 (en) | Improved contrast and noise reduction on images obtained from cameras | |
| CN102332001B (en) | Video thumbnail generation method and device | |
| CN109587560A (en) | Method for processing video frequency, device, electronic equipment and storage medium | |
| EP3819820B1 (en) | Method and apparatus for recognizing key identifier in video, device and storage medium | |
| Singh et al. | Contrast enhancement and brightness preservation using global-local image enhancement techniques | |
| CN107622504B (en) | Method and device for processing pictures | |
| CN104766076A (en) | Detection method and device for video images and texts | |
| WO2020108010A1 (en) | Video processing method and apparatus, electronic device and storage medium | |
| KR20130000827A (en) | A method for edge enhancement of image | |
| CN110555863A (en) | moving object detection method and device and computer readable storage medium | |
| US7961977B2 (en) | Image processing apparatus, display device, and image processing method for edge-preserving smoothing | |
| JP5939023B2 (en) | Computer program and image extraction apparatus | |
| US7949200B2 (en) | Image processing apparatus, display device, and image processing method | |
| CN114529909A (en) | Sample data set generation method and device and electronic equipment | |
| CN113870100A (en) | Image processing method and electronic device | |
| Taha et al. | Partial Differential Equations and Digital Image Processing: A Review | |
| CN105516735A (en) | Representation frame acquisition method and representation frame acquisition apparatus | |
| US9773472B2 (en) | Text extraction from graphical user interface content | |
| Lim et al. | Edge detection control of color images using FPGA | |
| CN114387315A (en) | Image processing model training method, image processing device, image processing equipment and image processing medium | |
| US20110069883A1 (en) | Image processing apparatus, display device, and image processing method | |
| Datta et al. | Minimizing aliasing effects using faster super resolution technique on text images |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20190531 Termination date: 20210525 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |