CN102547147A - Method for realizing enhancement processing for subtitle texts in video images and device - Google Patents
Method for realizing enhancement processing for subtitle texts in video images and device Download PDFInfo
- Publication number
- CN102547147A CN102547147A CN2011104487145A CN201110448714A CN102547147A CN 102547147 A CN102547147 A CN 102547147A CN 2011104487145 A CN2011104487145 A CN 2011104487145A CN 201110448714 A CN201110448714 A CN 201110448714A CN 102547147 A CN102547147 A CN 102547147A
- Authority
- CN
- China
- Prior art keywords
- captioned test
- caption area
- captions
- video image
- video
- 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.)
- Pending
Links
Images
Landscapes
- Television Systems (AREA)
Abstract
The invention aims to provide a method for realizing enhancement processing for subtitle texts in video images and a device. The subtitle enhancement device identifies a subtitle text in a subtitle area according to the subtitle area in a video image when preset subtitle enhancement triggering conditions are met, and the subtitle text is in enhancement processing, so that the subtitle text is clearly displayed in the video image. Compared with the prior art, the method for realizing enhancement processing for subtitle texts in video images and the subtitle enhancement device have the advantages that the subtitle text in the video image can be clearly displayed by means of enhancement processing for the subtitle text contained in the video image, better playing experiences are realized for users when a video is played, the subtitle enhancement device does not always work by means of setting the triggering conditions for enhancement processing for the subtitle text, or subtitle enhancement processing for an integral video file can be omitted, and accordingly load pressure and/or computation load of equipment with the subtitle enhancement device are reduced.
Description
Technical field
The present invention relates to the video playback technical field, relate in particular to a kind of technology that is used for the captioned test of video image is carried out enhancement process.
Background technology
In the existing video file, mainly comprise two types captions: a kind of captions are independent of video data as additional information, only when playing video file, according to time shaft with subtitle superposition on video image; Another kind of captions generate video image as the part of video data with the video content coding, and when playing video file, it is embedded in the video image.
Yet for the captions that are embedded in the video image, owing to reasons such as video code rate, resolution, these captions are as the video supplementary, and often definition is relatively poor, and the video playback that has had a strong impact on the user is experienced.
Therefore, how the captioned test in the video image is carried out enhancement process, make the captioned test that is embedded in the video image clearly to appear, become one of present urgent problem.
Summary of the invention
The purpose of this invention is to provide a kind of being used for carries out enhancement processing method and device to the captioned test of video image.
According to an aspect of the present invention, provide a kind of being used for that the captioned test of video image is carried out enhancement processing method, wherein, this method may further comprise the steps:
A according to the caption area in the video image, discerns the captioned test in the said caption area when satisfying predetermined captions enhancing trigger condition;
B carries out enhancement process to said captioned test, so that said captioned test clear appearing in said video image.
According to another aspect of the present invention, a kind of device that is used for the captioned test of video image is carried out enhancement process is provided also, wherein, this device comprises:
The captioned test recognition device is used for when satisfying predetermined captions enhancing trigger condition, according to the caption area in the video image, discerning the captioned test in the said caption area;
The captioned test processing unit is used for said captioned test is carried out enhancement process, so that said captioned test clear appearing in said video image.
According to a further aspect of the invention; A kind of player plug-in unit that is used for the captioned test of video image is carried out enhancement process also is provided; Wherein, this player plug-in unit comprises like the aforementioned device that is used for the captioned test of video image is carried out enhancement process according to another aspect of the present invention.
Compared with prior art, among the present invention,, make that the captioned test in video image can clearly appear, make that the user obtains better to play to experience when video playback through the captioned test that comprises in the video image is carried out enhancement process.And; Through setting the trigger condition of captioned test being carried out enhancement process; The captions intensifier needn't be in running order all the time, maybe needn't carry out the captions enhancement process to the whole video file, thereby alleviated the load pressure and/or the calculated load of captions intensifier corresponding device.
Description of drawings
Through reading the detailed description of doing with reference to following accompanying drawing that non-limiting example is done, it is more obvious that other features, objects and advantages of the present invention will become:
Fig. 1 illustrates the device sketch map that is used for the captioned test of video image is carried out the device of enhancement process according to one aspect of the invention;
Fig. 2 illustrates the device sketch map that is used for the captioned test of video image is carried out the device of enhancement process in accordance with a preferred embodiment of the present invention;
Fig. 3 illustrate according to a further aspect of the present invention be used for the captioned test of video image is carried out the enhancement processing method flow chart;
Fig. 4 illustrate in accordance with a preferred embodiment of the present invention be used for the captioned test of video image is carried out the enhancement processing method flow chart.
Same or analogous Reference numeral is represented same or analogous parts in the accompanying drawing.
Embodiment
Below in conjunction with accompanying drawing the present invention is described in further detail.
Fig. 1 is the device sketch map according to one aspect of the invention, and a kind of captions intensifier that is used for the captioned test of video image is carried out enhancement process is shown.At this, the subscriber equipment or the network equipment can installed and run on to captions intensifier 1; Subscriber equipment includes but not limited to anyly can carry out mutual electronic product with the user through mouse, keyboard, touch-screen etc. applicable to of the present invention, such as personal computer, notebook computer, panel computer, mobile phone, PDA, palmtop PC (PPC), game machine (PSP) etc.; The network equipment includes but not limited to network host, single network server, a plurality of webserver collection or based on the set of computers of cloud computing; Wherein, Cloud computing is a kind of of Distributed Calculation, a super virtual machine of being made up of the loosely-coupled computer collection of a group.
Particularly, among the present invention, the operating system of subscriber equipment, subscriber equipment or the media player of subscriber equipment can installed and run on to captions intensifier 1; Perhaps; The operating system of the network equipment, the network equipment can installed and run on to captions intensifier 1; And when the network equipment comprised the set of being made up of a plurality of servers or computer, wherein a station server or computer can installed and run on to captions intensifier 1.
Those skilled in the art will be understood that the above-mentioned subscriber equipment and the network equipment are merely for example; Other subscriber equipmenies existing or that possibly occur from now on or the network equipment are as applicable to the present invention; Also should be included in the protection range of the present invention, and be contained in this with way of reference.
As shown in Figure 1, captions intensifier 1 comprises captioned test recognition device 11 and captioned test processing unit 12.Particularly, captioned test recognition device 11 according to the caption area in the video image, is discerned the captioned test in the said caption area when satisfying predetermined captions enhancing trigger condition; 12 pairs of said captioned tests of captioned test processing unit carry out enhancement process, so that said captioned test clear appearing in said video image.
Captioned test recognition device 11 according to the caption area in the video image, is discerned the captioned test in the said caption area when satisfying predetermined captions enhancing trigger condition.
At this, said predetermined captions strengthen trigger condition and include but not limited to, below at least each:
1) the corresponding threshold value with it of the attribute information of said video image is not inconsistent;
2) color of the background colour of said caption area and said captioned test is approximate;
3) from the captions enhancement process request to video file of other equipment.
Particularly; 1) said attribute information includes but not limited to any applicable to of the present invention; Influence the definition of video image, the image association attributes of the definition of captions in the video image especially, the multiplication factor during such as the resolution of video image, video playback, code check of video etc.; For example, when user's displaying video, the multiplication factor of this video is 2, surpasses its corresponding threshold value 1.5, thinks that then satisfying captions strengthens trigger condition.
2) when the color of the background colour of caption area and captioned test is approximate, as is dark color or is light color, think that then satisfying captions strengthens trigger condition; For example; Based on gray value caption area is carried out binary conversion treatment; As to handle back caption area intermediate value be that 1 pixel quantity is 0 pixel quantity greater than value; Think that then the background colour of caption area and the color of captioned test are similar to, and be dark color, and judge that satisfying captions this moment strengthens trigger condition.
3) captions intensifier 1 can be used as video equipment is provided; Such as service node that resource is provided for other nodes in video server, the P2P network etc.; When this captions intensifier 1 receive from other equipment to the captions enhancement process request of video file the time, think that then satisfying captions strengthens trigger condition.
Those skilled in the art will be understood that above-mentioned captions strengthen trigger condition and are merely for example; Other captions existing or that possibly occur from now on strengthen trigger conditions as applicable to the present invention; Also should be included in the protection range of the present invention, and be contained in this with way of reference.
At this, the RM of said caption area includes but not limited to any applicable to caption area recognition methods of the present invention, comprises based on the caption area recognition methods of single frames video image with based on the caption area recognition methods of multi-frame video image.
Wherein, Caption area recognition methods based on the single frames video image comprises: 1) based on the recognition methods of connected domain; This method utilizes same caption area to have information such as close color and size, and video image is divided into a plurality of little connected domains, remerges these little connected domains; Forming big connected domain, thereby obtain the caption area in this video image; 2) based on the recognition methods at edge; This method is utilized the edge rich of caption area; And other the regional edges in the video image are simple relatively; Utilize the edge strength that detects each pixel in the video image like the sobel edge detection operator,, obtain the caption area of this video image through filtering and denoising; 3) based on the recognition methods of texture; Obtain the texture maps of video image according to wavelet transformation, Gabor conversion, Fourier transform etc.; Through methods such as svm classifier device, K-means clusters wherein textural characteristics is carried out classification processing, to confirm the caption area and other zones in this video image.
Caption area recognition methods based on the multi-frame video image mainly utilizes caption area redundancy feature in time, and identical caption area is contained in the continuous multi-frame video image; For example, have the multi-frame video image of identical caption area, these video images are asked average and image, eliminating the background information in these video images, thereby obtain the caption area in these video images through dichotomy inquiry.
Those skilled in the art will be understood that above-mentioned caption area recognition methods is merely for example; Other caption area recognition methodss existing or that possibly occur from now on are as applicable to the present invention; Also should be included in the protection range of the present invention, and be contained in this with way of reference.
At this, the RM of said captioned test includes but not limited to following mode:
1) through optical character identification (OCR) technology, the text in the caption area is discerned, to obtain corresponding captioned test;
2) obtain the multi-frame video image that comprises identical caption area; These caption areas are asked average and image, the average and image that is obtained is carried out OTSU cut apart, to generate the caption area image that only comprises the black-and-white two color connected domain; Confirm that which kind of color is a character area, thereby obtain captioned test.
Those skilled in the art will be understood that the RM of above-mentioned captioned test is merely for example; The RM of other captioned tests existing or that possibly occur from now on is as applicable to the present invention; Also should be included in the protection range of the present invention, and be contained in this with way of reference.
12 pairs of said captioned tests of captioned test processing unit carry out enhancement process, so that said captioned test clear appearing in said video image.
At this, the mode that 12 pairs of said captioned tests of captioned test processing unit carry out enhancement process includes but not limited to, below each mode at least:
1) the edge pixel point to each literal in the said captioned test carries out the sharpening processing; For example, the edge pixel point of each literal in the captioned test is carried out sharpening handle, increasing the contrast of these edge pixel points and its neighborhood pixels point, thereby make captioned test clear appearing in video image.
2) gray value of each literal in the said captioned test of increase; For example,, increase these gray values of pixel points, so that captioned test clear appearing in video image according to the pairing pixel of each literal in the captioned test.
3) when the color of the background colour of said caption area and said captioned test is close, according to the color value of the background colour of said caption area, inverse ratio is adjusted the color value of said captioned test; For example, the background colour of caption area and the color of captioned test are dark color, and according to the color value of the background colour of caption area, as 90%, the color value of this captioned test of inverse ratio adjustment is as being adjusted to 45% from 90%.
4) when the color of the background colour of said caption area and said captioned test is close, said caption area is filled the background color opposite with said background colour; For example, the background colour of caption area and the color of captioned test are dark color, with filling light color in this caption area, so that captioned test clear appearing in video image.
5) the pairing literal of said captioned test is superimposed to said captioned test; For example, the captioned test that identifies word for word is superimposed in the caption area corresponding literal, covering the former captioned test in the caption area, thereby makes captioned test clear appearing in video image.
Among the present invention,, make that the captioned test in video image can clearly appear, make that the user obtains better to play to experience when video playback through the captioned test that comprises in the video image is carried out enhancement process.And through setting the trigger condition of captioned test being carried out enhancement process, captions intensifier 1 needn't be in running order all the time, as can only responding the captions enhancement process request from other equipment, to start the operation of captions enhancement process; Maybe needn't carry out the captions enhancement process to the whole video file, unintelligible as the captions that cause being play in the video amplification for the user, only need carry out the captions enhancement process to pairing video image after amplifying broadcast.The present invention has alleviated the load pressure and/or the calculated load of captions intensifier 1 corresponding device; For example; The network equipment is installed and run on to captions intensifier 1; This network equipment and a plurality of subscriber equipment carry out alternately, can be merely the video of submitting to after captions enhancement process requesting users equipment provides the captions enhancement process, thereby have alleviated the load pressure and the calculated load of this network equipment; And for example, captions intensifier 1 is installed and is run on subscriber equipment, and this subscriber equipment can only carry out the captions enhancement process to the unclear video image of part captions in the video file of current broadcast, to reduce the calculated load of this subscriber equipment.
In a preferred exemplary of the present invention, captioned test recognition device 11 obtains the caption area in the said video image, thereby obtains the captioned test in the said caption area when satisfying predetermined captions enhancing trigger condition; 12 pairs of said captioned tests of captioned test processing unit carry out enhancement process, so that said captioned test clear appearing in said video image.
The captions enhancing trigger condition of for example, being scheduled to is that the resolution of video image is lower than its predetermined threshold; When the video that detects current broadcast, when its resolution was lower than this predetermined threshold, captioned test recognition device 11 detected and obtains the caption area in the video image, and through the captioned test in these caption areas of OCR identification; Captioned test processing unit 12 carries out edge sharpening to these captioned tests to be handled, thereby makes these captioned tests clear appearing in its corresponding video image.
In another preferred exemplary of the present invention, captioned test recognition device 11 obtains the caption area in the said video image, when satisfying predetermined captions enhancing trigger condition, obtains the captioned test in the said caption area; 12 pairs of said captioned tests of captioned test processing unit carry out enhancement process, so that said captioned test clear appearing in said video image.
For example, predetermined captions enhancing trigger condition is that the background colour of caption area and the color of captioned test are similar to; Captioned test recognition device 11 obtains the caption area in the video image; When the color of the subtitle file that is comprised in the background colour that detects this caption area and this caption area is similar to, the captioned test that comprises in captioned test recognition device 11 these caption areas of identification; Captioned test processing unit 12 is according to the color value of the background colour of this caption area, and the color value of this captioned test of inverse ratio adjustment is so that this captioned test clear appearing in its corresponding video image.
Fig. 2 is a device sketch map in accordance with a preferred embodiment of the present invention, and a kind of captions intensifier that is used for the captioned test of video image is carried out enhancement process is shown.
As shown in Figure 2, captions intensifier 1 comprises captioned test recognition device 21, captioned test processing unit 22, video file deriving means 23 and video file generator 24.Particularly, video file deriving means 23 obtains pending video file; Captioned test recognition device 21 according to the caption area of video image in the said video file, is discerned the captioned test in the said caption area when satisfying predetermined captions enhancing trigger condition; 22 pairs of said captioned tests of captioned test processing unit carry out enhancement process, so that said captioned test clear appearing in said video image; Video file generator 24 will comprise that the said video file of the captioned test after the said enhancement process provides to target device.
Wherein, Among Fig. 2 the performed operation of the captioned test recognition device 21 of captions intensifier 1 and captioned test processing unit 22 respectively with Fig. 1 in the performed content of operation of captioned test recognition device 11 and the captioned test processing unit 12 of captions intensifier 1 identical or basic identical; For for simplicity; Repeat no more, be contained in this with way of reference.
Video file deriving means 23 obtains pending video file.For example, captions intensifier 1 is installed and is run on the webserver, and all or part of video file that 1 pair of this webserver of this captions intensifier is stored carries out the captions enhancement process; Video file deriving means 23 obtains pending video file from the video resource storehouse of this webserver.And for example, captions intensifier 1 is installed and is run on subscriber equipment, and this subscriber equipment is a node in the P2P network; Video file deriving means 23 obtains pending video file from a plurality of video files of the local storage of this subscriber equipment.
Subsequently, captioned test recognition device 21 according to the caption area of video image in the said video file, is discerned the captioned test in the said caption area when satisfying predetermined captions enhancing trigger condition.
22 pairs of said captioned tests of captioned test processing unit carry out enhancement process, so that said captioned test clear appearing in said video image.
In the preferred exemplary of this embodiment, video file deriving means 23 obtains and the corresponding video file of said video association requests according to the video association requests of target device; Captioned test recognition device 21 according to the caption area of video image in the said video file, is discerned the captioned test in the said caption area when satisfying predetermined captions enhancing trigger condition; 22 pairs of said captioned tests of captioned test processing unit carry out enhancement process, so that said captioned test clear appearing in said video image; Video file generator 24 will comprise that the said video file of the captioned test after the said enhancement process provides to said target device.
At this, said video association requests includes but not limited to any applicable to of the present invention, such as video access request, the request of captions enhancement process etc. and directly or indirectly relevant request of video.
For example, video file deriving means 23 from the local repository of captions intensifier 1 corresponding device or the resources bank of other equipment, obtains the pairing video file of this captions enhancement process request according to the captions enhancement process request of target device; It is the captions enhancement process request to video file from other equipment that predetermined captions strengthen trigger condition, and captioned test recognition device 21 according to the caption area of video image in this video file, is discerned the captioned test in these caption areas in view of the above; Captioned test processing unit 22 carries out enhancement process to these captioned tests, so that these captioned tests clear appearing in its corresponding video image; Video file generator 24 will comprise that the video file of the captioned test after the enhancement process provides to this target device.
At this, when the equipment under the captions intensifier 1 and target device are the node in the P2P network, improved the resource service quality of this P2P network.And the equipment under captions intensifier 1 is the network equipment, and when target device was subscriber equipment, this network equipment can be based on " cloud computing provides the captions enhancement service of video file for a large number of users equipment.
In addition; Captions intensifier 1 described in the present invention can be used as the player plug-in unit; Install also and run in the existing various media player, aforementioned media player includes but not limited to that PPTV player, a sudden peal of thunder look at player, MPC player, media player player etc.
Fig. 3 is a method flow diagram according to a further aspect of the present invention, and a kind of process of the captioned test in the video image being carried out enhancement process by the captions intensifier is shown.At this, the subscriber equipment or the network equipment can installed and run on to the captions intensifier; Subscriber equipment includes but not limited to anyly can carry out mutual electronic product with the user through mouse, keyboard, touch-screen etc. applicable to of the present invention, such as personal computer, notebook computer, panel computer, mobile phone, PDA, palmtop PC (PPC), game machine (PSP) etc.; The network equipment includes but not limited to network host, single network server, a plurality of webserver collection or based on the set of computers of cloud computing; Wherein, Cloud computing is a kind of of Distributed Calculation, a super virtual machine of being made up of the loosely-coupled computer collection of a group.
Particularly, among the present invention, the operating system of subscriber equipment, subscriber equipment or the media player of subscriber equipment can installed and run on to the captions intensifier; Perhaps; The operating system of the network equipment, the network equipment can installed and run on to the captions intensifier; And when the network equipment comprised the set of being made up of a plurality of servers or computer, wherein a station server or computer can installed and run on to the captions intensifier.
Those skilled in the art will be understood that the above-mentioned subscriber equipment and the network equipment are merely for example; Other subscriber equipmenies existing or that possibly occur from now on or the network equipment are as applicable to the present invention; Also should be included in the protection range of the present invention, and be contained in this with way of reference.
As shown in Figure 3, in step S301, the captions intensifier according to the caption area in the video image, is discerned the captioned test in the said caption area when satisfying predetermined captions enhancing trigger condition; In step S302, the captions intensifier carries out enhancement process to said captioned test, so that said captioned test clear appearing in said video image.
In step S301, the captions intensifier according to the caption area in the video image, is discerned the captioned test in the said caption area when satisfying predetermined captions enhancing trigger condition.
At this, said predetermined captions strengthen trigger condition and include but not limited to, below at least each:
1) the corresponding threshold value with it of the attribute information of said video image is not inconsistent;
2) color of the background colour of said caption area and said captioned test is approximate;
3) from the captions enhancement process request to video file of other equipment.
Particularly; 1) said attribute information includes but not limited to any applicable to of the present invention; Influence the definition of video image, the image association attributes of the definition of captions in the video image especially, the multiplication factor during such as the resolution of video image, video playback, code check of video etc.; For example, when user's displaying video, the multiplication factor of this video is 2, surpasses its corresponding threshold value 1.5, thinks that then satisfying captions strengthens trigger condition.
2) when the color of the background colour of caption area and captioned test is approximate, as is dark color or is light color, think that then satisfying captions strengthens trigger condition; For example; Based on gray value caption area is carried out binary conversion treatment; As to handle back caption area intermediate value be that 1 pixel quantity is 0 pixel quantity greater than value; Think that then the background colour of caption area and the color of captioned test are similar to, and be dark color, and judge that satisfying captions this moment strengthens trigger condition.
3) captions intensifier 1 can be used as video equipment is provided; Such as service node that resource is provided for other nodes in video server, the P2P network etc.; When this captions intensifier 1 receive from other equipment to the captions enhancement process request of video file the time, think that then satisfying captions strengthens trigger condition.
Those skilled in the art will be understood that above-mentioned captions strengthen trigger condition and are merely for example; Other captions existing or that possibly occur from now on strengthen trigger conditions as applicable to the present invention; Also should be included in the protection range of the present invention, and be contained in this with way of reference.
At this, the RM of said caption area includes but not limited to any applicable to caption area recognition methods of the present invention, comprises based on the caption area recognition methods of single frames video image with based on the caption area recognition methods of multi-frame video image.
Wherein, Caption area recognition methods based on the single frames video image comprises: 1) based on the recognition methods of connected domain; This method utilizes same caption area to have information such as close color and size, and video image is divided into a plurality of little connected domains, remerges these little connected domains; Forming big connected domain, thereby obtain the caption area in this video image; 2) based on the recognition methods at edge; This method is utilized the edge rich of caption area; And other the regional edges in the video image are simple relatively; Utilize the edge strength that detects each pixel in the video image like the sobel edge detection operator,, obtain the caption area of this video image through filtering and denoising; 3) based on the recognition methods of texture; Obtain the texture maps of video image according to wavelet transformation, Gabor conversion, Fourier transform etc.; Through methods such as svm classifier device, K-means clusters wherein textural characteristics is carried out classification processing, to confirm the caption area and other zones in this video image.
Caption area recognition methods based on the multi-frame video image mainly utilizes caption area redundancy feature in time, and identical caption area is contained in the continuous multi-frame video image; For example, have the multi-frame video image of identical caption area, these video images are asked average and image, eliminating the background information in these video images, thereby obtain the caption area in these video images through dichotomy inquiry.
Those skilled in the art will be understood that above-mentioned caption area recognition methods is merely for example; Other caption area recognition methodss existing or that possibly occur from now on are as applicable to the present invention; Also should be included in the protection range of the present invention, and be contained in this with way of reference.
At this, the RM of said captioned test includes but not limited to following mode:
1) through optical character identification (OCR) technology, the text in the caption area is discerned, to obtain corresponding captioned test;
2) obtain the multi-frame video image that comprises identical caption area; These caption areas are asked average and image, the average and image that is obtained is carried out OTSU cut apart, to generate the caption area image that only comprises the black-and-white two color connected domain; Confirm that which kind of color is a character area, thereby obtain captioned test.
Those skilled in the art will be understood that the RM of above-mentioned captioned test is merely for example; The RM of other captioned tests existing or that possibly occur from now on is as applicable to the present invention; Also should be included in the protection range of the present invention, and be contained in this with way of reference.
In step S302, the captions intensifier carries out enhancement process to said captioned test, so that said captioned test clear appearing in said video image.
At this, the captions intensifier includes but not limited to the mode that said captioned test carries out enhancement process, below each mode at least:
1) the edge pixel point to each literal in the said captioned test carries out the sharpening processing; For example, the edge pixel point of each literal in the captioned test is carried out sharpening handle, increasing the contrast of these edge pixel points and its neighborhood pixels point, thereby make captioned test clear appearing in video image.
2) gray value of each literal in the said captioned test of increase; For example,, increase these gray values of pixel points, so that captioned test clear appearing in video image according to the pairing pixel of each literal in the captioned test.
3) when the color of the background colour of said caption area and said captioned test is close, according to the color value of the background colour of said caption area, inverse ratio is adjusted the color value of said captioned test; For example, the background colour of caption area and the color of captioned test are dark color, and according to the color value of the background colour of caption area, as 90%, the color value of this captioned test of inverse ratio adjustment is as being adjusted to 45% from 90%.
4) when the color of the background colour of said caption area and said captioned test is close, said caption area is filled the background color opposite with said background colour; For example, the background colour of caption area and the color of captioned test are dark color, with filling light color in this caption area, so that captioned test clear appearing in video image.
5) the pairing literal of said captioned test is superimposed to said captioned test; For example, the captioned test that identifies word for word is superimposed in the caption area corresponding literal, covering the former captioned test in the caption area, thereby makes captioned test clear appearing in video image.
Among the present invention,, make that the captioned test in video image can clearly appear, make that the user obtains better to play to experience when video playback through the captioned test that comprises in the video image is carried out enhancement process.And through setting the trigger condition of captioned test being carried out enhancement process, the captions intensifier needn't be in running order all the time, as can only responding the captions enhancement process request from other equipment, to start the operation of captions enhancement process; Maybe needn't carry out the captions enhancement process to the whole video file, unintelligible as the captions that cause being play in the video amplification for the user, only need carry out the captions enhancement process to pairing video image after amplifying broadcast.The present invention has alleviated the load pressure and/or the calculated load of captions intensifier corresponding device; For example; The network equipment is installed and run on to the captions intensifier; This network equipment and a plurality of subscriber equipment carry out alternately, can be merely the video of submitting to after captions enhancement process requesting users equipment provides the captions enhancement process, thereby have alleviated the load pressure and the calculated load of this network equipment; And for example, the captions intensifier is installed and is run on subscriber equipment, and this subscriber equipment can only carry out the captions enhancement process to the unclear video image of part captions in the video file of current broadcast, to reduce the calculated load of this subscriber equipment.
In a preferred exemplary of the present invention, in step S301, the captions intensifier obtains the caption area in the said video image, thereby obtains the captioned test in the said caption area when satisfying predetermined captions enhancing trigger condition; In step S302, the captions intensifier carries out enhancement process to said captioned test, so that said captioned test clear appearing in said video image.
The captions enhancing trigger condition of for example, being scheduled to is that the resolution of video image is lower than its predetermined threshold; In step S301, when the video that detects current broadcast, when its resolution was lower than this predetermined threshold, the captions intensifier detected and obtains the caption area in the video image, and through the captioned test in these caption areas of OCR identification; In step S302, the captions intensifier carries out edge sharpening to these captioned tests to be handled, thereby makes these captioned tests clear appearing in its corresponding video image.
In another preferred exemplary of the present invention, in step S301, the captions intensifier obtains the caption area in the said video image, when satisfying predetermined captions enhancing trigger condition, obtains the captioned test in the said caption area; In step S302, the captions intensifier carries out enhancement process to said captioned test, so that said captioned test clear appearing in said video image.
For example, predetermined captions enhancing trigger condition is that the background colour of caption area and the color of captioned test are similar to; In step S301; The captions intensifier obtains the caption area in the video image; When the color of the subtitle file that is comprised in the background colour that detects this caption area and this caption area is similar to, the captioned test that comprises in this caption area of captions intensifier identification; In step S302, the captions intensifier is according to the color value of the background colour of this caption area, and the color value of this captioned test of inverse ratio adjustment is so that this captioned test clear appearing in its corresponding video image.
Fig. 4 is a method flow diagram in accordance with a preferred embodiment of the present invention, and a kind of process of the captioned test in the video image being carried out enhancement process by the captions intensifier is shown.
As shown in Figure 4, in step S400, the captions intensifier obtains pending video file; In step S401, the captions intensifier according to the caption area of video image in the said video file, is discerned the captioned test in the said caption area when satisfying predetermined captions enhancing trigger condition; In step S402, the captions intensifier carries out enhancement process to said captioned test, so that said captioned test clear appearing in said video image; In step S403, the captions intensifier will comprise that the said video file of the captioned test after the said enhancement process provides to target device.
Wherein, Among Fig. 4 the captions intensifier in step S401 and step S402 performed operation respectively with Fig. 3 in captions intensifier performed content of operation in step S301 and step S302 identical or basic identical; For for simplicity, repeat no more, be contained in this with way of reference.
In step S400, the captions intensifier obtains pending video file.For example, the captions intensifier is installed and is run on the webserver, and all or part of video file that this captions intensifier is stored this webserver carries out the captions enhancement process; The captions intensifier obtains pending video file from the video resource storehouse of this webserver.And for example, the captions intensifier is installed and is run on subscriber equipment, and this subscriber equipment is a node in the P2P network; The captions intensifier obtains pending video file from a plurality of video files of the local storage of this subscriber equipment.
Subsequently, in step S401, the captions intensifier according to the caption area of video image in the said video file, is discerned the captioned test in the said caption area when satisfying predetermined captions enhancing trigger condition.
In step S402, the captions intensifier carries out enhancement process to said captioned test, so that said captioned test clear appearing in said video image.
In step S403, the captions intensifier will comprise that the said video file of the captioned test after the said enhancement process provides to target device.At this; The equipment under the captions intensifier and the communication mode of said target device comprise the various modes that can in two equipment, transmit data and/or information, include but not limited to based on 3GPP, LTE standard mobile communication, based on the compunication of the network transmission protocols such as TCP/IP, UDP, FTP, ICMP, NetBEUI or be present in other forms of communication in the computer; For example, the communication between the object of OOP the inside, the message transmission protocol in the operating system between distinct program or the computer disparate modules.Those skilled in the art will be understood that above-mentioned communication mode is merely for example, and other communication modes existing or that possibly occur from now on also should be included in the protection range of the present invention, and be contained in this with way of reference as applicable to the present invention.
In the preferred exemplary of this embodiment, in step S400, the captions intensifier obtains and the corresponding video file of said video association requests according to the video association requests of target device; In step S401, the captions intensifier according to the caption area of video image in the said video file, is discerned the captioned test in the said caption area when satisfying predetermined captions enhancing trigger condition; In step S402, the captions intensifier carries out enhancement process to said captioned test, so that said captioned test clear appearing in said video image; In step S403, the captions intensifier will comprise that the said video file of the captioned test after the said enhancement process provides to said target device.
At this, said video association requests includes but not limited to any applicable to of the present invention, such as video access request, the request of captions enhancement process etc. and directly or indirectly relevant request of video.
For example, in step S400, the captions intensifier from the local repository of this captions intensifier corresponding device or the resources bank of other equipment, obtains the pairing video file of this captions enhancement process request according to the captions enhancement process request of target device; It is the captions enhancement process request to video file from other equipment that predetermined captions strengthen trigger condition; In step S401; The captions intensifier according to the caption area of video image in this video file, is discerned the captioned test in these caption areas in view of the above; In step S402, the captions intensifier carries out enhancement process to these captioned tests, so that these captioned tests clear appearing in its corresponding video image; In step S403, the captions intensifier will comprise that the video file of the captioned test after the enhancement process provides to this target device.
At this, when the equipment under the captions intensifier and target device are the node in the P2P network, improved the resource service quality of this P2P network.And the equipment under the captions intensifier is the network equipment, and when target device was subscriber equipment, this network equipment can be based on " cloud computing provides the captions enhancement service of video file for a large number of users equipment.
To those skilled in the art, obviously the invention is not restricted to the details of above-mentioned example embodiment, and under the situation that does not deviate from spirit of the present invention or essential characteristic, can realize the present invention with other concrete form.Therefore; No matter from which point; All should regard embodiment as exemplary; And be nonrestrictive, scope of the present invention is limited accompanying claims rather than above-mentioned explanation, therefore is intended to the implication of the equivalents that drops on claim and all changes in the scope are included in the present invention.Should any Reference numeral in the claim be regarded as limit related claim.In addition, obviously other unit or step do not got rid of in " comprising " speech, and odd number is not got rid of plural number.A plurality of unit of stating in system's claim or device also can be realized through software or hardware by a unit or device.The first, the second word such as grade is used for representing title, and does not represent any specific order.
Claims (15)
1. one kind is used for the captioned test of video image is carried out enhancement processing method, and wherein, this method may further comprise the steps:
A according to the caption area in the video image, discerns the captioned test in the said caption area when satisfying predetermined captions enhancing trigger condition;
B carries out enhancement process to said captioned test, so that said captioned test clear appearing in said video image.
2. method according to claim 1, wherein, said step a comprises:
-when satisfying predetermined captions enhancing trigger condition, obtain the caption area in the said video image;
Captioned test in the said caption area of-identification.
3. method according to claim 1, wherein, said step a comprises:
-obtain the caption area in the said video image;
-when satisfying predetermined captions enhancing trigger condition, discern the captioned test in the said caption area.
4. according to each described method in the claim 1 to 3, wherein, this method also comprises:
I obtains pending video file;
Wherein, said step a comprises:
-when satisfying predetermined captions enhancing trigger condition,, discern the captioned test in the said caption area according to the caption area of video image in the said video file;
Wherein, this method also comprises:
-will comprise that the said video file of the captioned test after the said enhancement process provides to target device.
5. method according to claim 4, wherein, said step I comprises:
-according to the video association requests of said target device, obtain and the corresponding said video file of said video association requests.
6. according to each described method in the claim 1 to 5, wherein, said predetermined captions strengthen trigger condition comprise following at least each:
The corresponding threshold value with it of the attribute information of-said video image is not inconsistent;
The background colour of-said caption area and the color of said captioned test are approximate;
-from the captions enhancement process request to video file of other equipment.
7. according to each described method in the claim 1 to 6, wherein, the mode of among the said step b said captioned test being carried out enhancement process comprise following at least each:
-the edge pixel point of each literal in the said captioned test is carried out the sharpening processing;
The gray value of each literal in the said captioned test of-increase;
-when the color of the background colour of said caption area and said captioned test was close, according to the color value of the background colour of said caption area, inverse ratio was adjusted the color value of said captioned test;
-when the color of the background colour of said caption area and said captioned test is close, said caption area is filled the background color opposite with said background colour;
-the pairing literal of said captioned test is superimposed to said captioned test.
8. device that is used for the captioned test of video image is carried out enhancement process, wherein, this device comprises:
The captioned test recognition device is used for when satisfying predetermined captions enhancing trigger condition, according to the caption area in the video image, discerning the captioned test in the said caption area;
The captioned test processing unit is used for said captioned test is carried out enhancement process, so that said captioned test clear appearing in said video image.
9. device according to claim 8, wherein, said captioned test recognition device is used for:
-when satisfying predetermined captions enhancing trigger condition, obtain the caption area in the said video image;
-obtain the captioned test in the said caption area.
10. device according to claim 8, wherein, said captioned test recognition device is used for:
-obtain the caption area in the said video image;
-when satisfying predetermined captions enhancing trigger condition, obtain the captioned test in the said caption area.
11. each described device in 10 according to Claim 8, wherein, this device also comprises:
The video file deriving means is used to obtain pending video file;
Wherein, said captioned test recognition device is used for:
-when satisfying predetermined captions enhancing trigger condition,, discern the captioned test in the said caption area according to the caption area of video image in the said video file;
Wherein, this device also comprises:
The video file generator is used for the said video file that comprises the captioned test after the said enhancement process is provided to target device.
12. device according to claim 11, wherein, said video file deriving means is used for:
-according to the video association requests of said target device, obtain and the corresponding said video file of said video association requests.
13. each described device in 12 according to Claim 8, wherein, said predetermined captions strengthen trigger condition comprise following at least each:
The corresponding threshold value with it of the attribute information of-said video image is not inconsistent;
The background colour of-said caption area and the color of said captioned test are approximate;
-from the captions enhancement process request to video file of other equipment.
14. each described device in 13 according to Claim 8, wherein, the mode that said captioned test processing unit carries out enhancement process to said captioned test comprise following at least each:
-the edge pixel point of each literal in the said captioned test is carried out the sharpening processing;
The gray value of each literal in the said captioned test of-increase;
-when the color of the background colour of said caption area and said captioned test was close, according to the color value of the background colour of said caption area, inverse ratio was adjusted the color value of said captioned test;
-when the color of the background colour of said caption area and said captioned test is close, said caption area is filled the background color opposite with said background colour;
-the pairing literal of said captioned test is superimposed to said captioned test.
15. a player plug-in unit that is used for the captioned test of video image is carried out enhancement process, wherein, this player plug-in unit comprises like each described device that is used for the captioned test of video image is carried out enhancement process in the claim 8 to 14.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011104487145A CN102547147A (en) | 2011-12-28 | 2011-12-28 | Method for realizing enhancement processing for subtitle texts in video images and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011104487145A CN102547147A (en) | 2011-12-28 | 2011-12-28 | Method for realizing enhancement processing for subtitle texts in video images and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN102547147A true CN102547147A (en) | 2012-07-04 |
Family
ID=46352987
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2011104487145A Pending CN102547147A (en) | 2011-12-28 | 2011-12-28 | Method for realizing enhancement processing for subtitle texts in video images and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102547147A (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105120302A (en) * | 2015-08-27 | 2015-12-02 | 广州市百果园网络科技有限公司 | Video processing method and device |
| CN105447847A (en) * | 2014-09-24 | 2016-03-30 | Juki株式会社 | Form detection means and sewing machine |
| CN106303579A (en) * | 2016-09-20 | 2017-01-04 | 上海斐讯数据通信技术有限公司 | Video play device and method |
| CN107846622A (en) * | 2017-10-27 | 2018-03-27 | 北京雷石天地电子技术有限公司 | A kind of method and device for detecting captions definition |
| CN107967163A (en) * | 2017-11-24 | 2018-04-27 | 维沃移动通信有限公司 | A kind of display methods of subtitle, device and mobile terminal |
| CN108271061A (en) * | 2016-12-30 | 2018-07-10 | 央视国际网络无锡有限公司 | A kind of method for being inserted into high contrast frame subtitle in video |
| CN108307245A (en) * | 2018-02-07 | 2018-07-20 | 中译语通科技股份有限公司 | A kind of subtitle font color acquisition methods, display based on context-aware technology |
| CN109284751A (en) * | 2018-10-31 | 2019-01-29 | 河南科技大学 | The non-textual filtering method of text location based on spectrum analysis and SVM |
| CN109361950A (en) * | 2018-11-27 | 2019-02-19 | Oppo广东移动通信有限公司 | Method for processing video frequency, device, electronic equipment and storage medium |
| CN113051872A (en) * | 2021-04-01 | 2021-06-29 | 竞技世界（北京）网络技术有限公司 | Method, device and equipment for displaying highlighted characters |
| WO2023195912A3 (en) * | 2022-04-07 | 2023-11-30 | 脸萌有限公司 | Processing method and apparatus, terminal device, and medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101175164A (en) * | 2006-11-01 | 2008-05-07 | 株式会社日立制作所 | Image reproduction device |
| EP1978522A2 (en) * | 2003-10-04 | 2008-10-08 | Samsung Electronics Co., Ltd. | Method for reproducing a text-based subtitle from an information storage medium using selectable style informations |
| CN101360193A (en) * | 2008-09-04 | 2009-02-04 | 北京中星微电子有限公司 | Video subtitle processing apparatus and method |
| CN101867733A (en) * | 2009-04-14 | 2010-10-20 | 联发科技（新加坡）私人有限公司 | Processing method of subtitle data stream of video programme and video displaying system |
-
2011
- 2011-12-28 CN CN2011104487145A patent/CN102547147A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1978522A2 (en) * | 2003-10-04 | 2008-10-08 | Samsung Electronics Co., Ltd. | Method for reproducing a text-based subtitle from an information storage medium using selectable style informations |
| CN101175164A (en) * | 2006-11-01 | 2008-05-07 | 株式会社日立制作所 | Image reproduction device |
| CN101360193A (en) * | 2008-09-04 | 2009-02-04 | 北京中星微电子有限公司 | Video subtitle processing apparatus and method |
| CN101867733A (en) * | 2009-04-14 | 2010-10-20 | 联发科技（新加坡）私人有限公司 | Processing method of subtitle data stream of video programme and video displaying system |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105447847A (en) * | 2014-09-24 | 2016-03-30 | Juki株式会社 | Form detection means and sewing machine |
| CN105120302A (en) * | 2015-08-27 | 2015-12-02 | 广州市百果园网络科技有限公司 | Video processing method and device |
| CN106303579A (en) * | 2016-09-20 | 2017-01-04 | 上海斐讯数据通信技术有限公司 | Video play device and method |
| CN108271061A (en) * | 2016-12-30 | 2018-07-10 | 央视国际网络无锡有限公司 | A kind of method for being inserted into high contrast frame subtitle in video |
| CN107846622B (en) * | 2017-10-27 | 2020-04-28 | 北京雷石天地电子技术有限公司 | Method and device for detecting definition of subtitles |
| CN107846622A (en) * | 2017-10-27 | 2018-03-27 | 北京雷石天地电子技术有限公司 | A kind of method and device for detecting captions definition |
| CN107967163A (en) * | 2017-11-24 | 2018-04-27 | 维沃移动通信有限公司 | A kind of display methods of subtitle, device and mobile terminal |
| CN108307245A (en) * | 2018-02-07 | 2018-07-20 | 中译语通科技股份有限公司 | A kind of subtitle font color acquisition methods, display based on context-aware technology |
| CN108307245B (en) * | 2018-02-07 | 2020-04-28 | 中译语通科技股份有限公司 | Subtitle font color obtaining method based on background perception technology and display |
| CN109284751A (en) * | 2018-10-31 | 2019-01-29 | 河南科技大学 | The non-textual filtering method of text location based on spectrum analysis and SVM |
| CN109361950A (en) * | 2018-11-27 | 2019-02-19 | Oppo广东移动通信有限公司 | Method for processing video frequency, device, electronic equipment and storage medium |
| CN113051872A (en) * | 2021-04-01 | 2021-06-29 | 竞技世界（北京）网络技术有限公司 | Method, device and equipment for displaying highlighted characters |
| WO2023195912A3 (en) * | 2022-04-07 | 2023-11-30 | 脸萌有限公司 | Processing method and apparatus, terminal device, and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102547147A (en) | Method for realizing enhancement processing for subtitle texts in video images and device | |
| US10896349B2 (en) | Text detection method and apparatus, and storage medium | |
| US11830230B2 (en) | Living body detection method based on facial recognition, and electronic device and storage medium | |
| US8391599B1 (en) | Systems and methods for adaptive binarization of an image | |
| US9424479B2 (en) | Systems and methods for resizing an image | |
| US9396539B2 (en) | Methods and apparatuses for face detection | |
| Guo et al. | Blind image watermarking method based on linear canonical wavelet transform and QR decomposition | |
| US9082039B2 (en) | Method and apparatus for recognizing a character based on a photographed image | |
| WO2022051080A1 (en) | Detecting a sub-image region of interest in an image using pilot signals | |
| CN103810425A (en) | Method and device for detecting malicious website | |
| CN111445424B (en) | Image processing method, device, equipment and medium for processing mobile terminal video | |
| US10360687B2 (en) | Detection and location of active display regions in videos with static borders | |
| CN106503112B (en) | Video retrieval method and device | |
| CN104079950A (en) | Video output processing method, device and system and video receiving processing method, device and system | |
| WO2021047177A1 (en) | Data encoding method and apparatus | |
| US20130084004A1 (en) | Image processing of data from scanned display | |
| CN111179195A (en) | Depth image hole filling method and device, electronic equipment and storage medium thereof | |
| JP2014535101A (en) | Method and apparatus for facilitating detection of text in an image | |
| CN103985102A (en) | Image processing method and system | |
| CN103678957A (en) | Method, device and equipment for generating picture information and obtaining identity coded information | |
| CN107844696B (en) | Verification code interference method and server | |
| CN110263708B (en) | Image source identification method, device and computer readable storage medium | |
| CN110334301B (en) | Page restoration method and device | |
| CN111111175A (en) | Game picture generation method and device and mobile terminal | |
| Sharma et al. | A single watermark based scheme for both protection and authentication of identities |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C12 | Rejection of a patent application after its publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20120704 |