Real time motion picture segmentation and superposition
IPC분류정보
국가/구분
United States(US) Patent
등록
국제특허분류(IPC7판)
H04N-009/76
H04N-009/74
출원번호
US-0784397
(2010-05-20)
등록번호
US-8098332
(2012-01-17)
발명자
/ 주소
Sheraizin, Vitaly S.
Sheraizin, Semion M.
출원인 / 주소
Somle Development, L.L.C.
인용정보
피인용 횟수 :
0인용 특허 :
133
초록▼
Various embodiments of separating a picture part of interest from an arbitrary background are described. The background may be a moving or still frame. The picture part of interest and background frames may be in or out of focus. One separation approach employs the difference between luminance and c
Various embodiments of separating a picture part of interest from an arbitrary background are described. The background may be a moving or still frame. The picture part of interest and background frames may be in or out of focus. One separation approach employs the difference between luminance and chrominance values of the input and background frames where changes in luminance from frame to frame are compensated for. In another approach, picture part of interest separation is based on spatial resolution differences between the background and the picture part of interest frames. Parameter matching can also be performed for the picture part of interest and the basic picture into which the picture part of interest is embedded. Further, a separated picture part of interest can be embedded into a basic picture containing text.
대표청구항▼
1. A method comprising: selecting, by a processing device, signal data from input frames based on criteria; andbased on the signal data, locating text in at least one of the input frames, wherein the locating comprises determining, by a decoder, a number of consecutive frames of the input frames hav
1. A method comprising: selecting, by a processing device, signal data from input frames based on criteria; andbased on the signal data, locating text in at least one of the input frames, wherein the locating comprises determining, by a decoder, a number of consecutive frames of the input frames having text in one or more corresponding pixel positions and comparing the number of consecutive frames to a consecutive frame threshold value. 2. The method of claim 1, wherein the criteria is associated with a sharpness of one or more edges of the signal data. 3. A system comprising: a decoder configured to decode signal data associated with one or more input frames to provide pixel data;a text mask generator configured to generate a text mask utilizing the pixel data; andan embedding unit configured to embed a scaled picture part of interest in the text mask. 4. The system of claim 3, further comprising: one or more comparators configured to select the signal data based on a sharpness of one or more edges of the signal data; anda storage unit configured to store the signal data for access by the decoder, the signal data stored on a pixel-by-pixel basis for individual input frames. 5. A method comprising: detecting text within an image by a text detector unit;generating, by the text detector unit, a text mask for the text detected within the image; andembedding, by a combining unit, a picture part of interest into the text mask to produce an output image that combines the picture part of interest with the text. 6. The method as recited in claim 5, wherein embedding the picture part of interest into the text mask comprises super-positioning the text mask with the picture part of interest. 7. The method as recited in claim 5, wherein detecting text within the image comprises detecting differences between time edges in the image that are indicative of text. 8. The method as recited in claim 5, further comprising obtaining the picture part of interest from a separator unit configured to separate the picture part of interest from an arbitrary background. 9. The method as recited in claim 5, further comprising scaling the picture part of interest based upon a size of the text indicated by the text mask. 10. The method as recited in claim 5, further comprising: converting color signals of the image to generate a luminance signal; andfiltering the luminance signal to distinguish text from other portions of the image based on sharper and higher contrast edges that are associated with the text. 11. The method as recited in claim 5, further comprising decoding the detected text pixel by pixel. 12. The method as recited in claim 11, further comprising producing the text mask based on pixel data obtained from the decoding. 13. The method as recited in claim 5, further comprising counting a number of consecutive frames having text; and determining if the number of consecutive frames exceeds a threshold value. 14. An image processing system comprising; a text detector unit configured to: locate text within an image based upon resolution differences between the text and other portions of the image; andgenerate a mask corresponding to located text; anda combining unit configured to produce an embedded image, including a picture part of interest and the located text, by at least super-positioning the picture part of interest with a generated mask. 15. The image processing system of claim 14, further comprising a picture part of interest separator configured to: convert signals of a frame input to the picture part of interest separator to a frame luminance signal and frame chrominance signals;identify pixels of the input frame corresponding to the picture part of interest based in part upon the converted signals;generate a mask indicating a location of the picture part of interest within the input frame; andseparate the picture part of interest from the input frame using the mask to produce the separated picture part of interest. 16. The image processing system of claim 14, wherein the image comprises a video image. 17. The image processing system claim 4, wherein the image comprises a still image. 18. The image processing system of claim 14, wherein the text detector comprises one or more high pass filters configured to locate the text. 19. The image processing system of claim 14, wherein the combining unit further comprises a switch configured to: obtain the generated mask;obtain the picture part of interest from a separator unit; andcombine the picture part of interest and the generated mask to produce the embedded image. 20. A system comprising: a storage unit configured to store frame data in conjunction with processing of an image; andone or more image processing components configured to position a picture part of interest in an image containing text by: locating text in the image using luminance values corresponding to the image;generating a text mask for text located in the image, the text mask indicative of a location of the text in the image;obtaining the picture part of interest;scaling the picture part of interest in relation to a size of the text located in the image; andsuper-positioning the text mask with the scaled picture part of interest. 21. The system 20, wherein locating the text in the image comprises: obtaining the frame data having the luminance values corresponding to the image from the storage unit; anddecoding the frame data to determine a number of consecutive frames having luminance values indicative of text and comparing the number of consecutive frames to a consecutive frame threshold value. 22. The system of claim 20, wherein locating the text in the image comprises: obtaining the frame data having the luminance values corresponding to the image from the storage unit; anddecoding the frame data on a pixel-by-pixel basis for individual frames to determine a number of pixels having luminance values indicative of text and comparing the number of pixels to an individual frame threshold value. 23. The system of claim 20, wherein locating the text in the image comprises: filtering signal data for the image using one or more high pass filters produce a filtered luminance signal for the image;comparing the filtered luminance signal to a threshold luminance value to identify luminance values indicative of text in the image; andstoring the luminance values indicative of text in the storage unit on a pixel-by-pixel and per frame basis. 24. The system of claim 20, wherein super-positioning the text mask with the scaled picture part of interest comprises embedding the picture part of interest in the image containing the text to produce an embedded image. 25. The system of claim 20, wherein the one or more image processing components include a text detector unit configured to perform the locating and generating, a scaler unit configured to perform the obtaining and scaling, and a combining unit configured to perform the super-positioning.
연구과제 타임라인
LOADING...
LOADING...
LOADING...
LOADING...
LOADING...
이 특허에 인용된 특허 (133)
Kim Jong-Il (Incheon KRX), Adaptive digital audio encoding apparatus and a bit allocation method thereof.
Lee Shih-Jong J. ; Kuan Chih-Chau L. ; Bannister Wendy R. ; Wilhelm Paul S. ; Meyer Michael G., Apparatus for identification and integration of multiple cell patterns.
Kori Teruhiko (Tokyo JPX) Iijima Koji (Kanagawa JPX) Takahashi Takao (Tokyo JPX) Yoshino Kazuo (Tokyo JPX) Kojima Masaaki (Kanagawa JPX), Apparatus for producing a composite signal from real moving picture and still picture video signals.
Metcalfe James Robert,AUX ; Long Timothy Merrick,AUX ; Politis George,AUX, Image filtering method and apparatus with interpolation according to mapping function to produce final image.
Fujisawa Tetsuo (Urawa JPX) Sakano Yukio (Fuchuu JPX), Image processing apparatus especially suitable for producing smooth-edged output multi-level tone data having fewer leve.
Lee Hsien-Che (Penfield NY) Kaplan Martin C. (Rochester NY) Goodwin Robert M. (Rochester NY), Interactive dynamic range adjustment system for printing digital images.
Kim Jin (Issaquah WA) Marquis Steven R. (Fall City WA) Banjanin Zoran (Renton WA) Liu Dong-Chyuan (Mercer Island WA), Method and apparatus for adaptive spatial image filtering.
Lubin Jeffrey ; Brill Michael Henry ; De Vries Aalbert ; Finard Olga, Method and apparatus for assessing the visibility of differences between two image sequences.
Barrett Peter T. (Palo Alto CA), Method and apparatus for compression data by generating base image data from luminance and chrominance components and de.
Takahashi,Koji, Method and apparatus for correcting white balance, method for correcting density and a recording medium on which a program for carrying out the methods is recorded.
Pizano Arturo ; Arman Farshid ; Benson Daniel Conrad ; Depommier Remi, Method and apparatus for detecting and interpreting textual captions in digital video signals.
Santamaki Harry J. (Espoo FIX) Korhonen Ilkka O. (Espoo FIX) Haikonen Pentti O. (Espoo FIX), Method and apparatus for detecting the most powerfully changed picture areas in a live video signal.
Faroudja Yves C. (26595 Anacapa Dr. Los Altos Hills CA 94022), Method and apparatus for producing from a standard-bandwidth television signal a signal which when reproduced provides a.
Lee Jungwoo (Princeton NJ) Dickinson Bradley W. (Lawrenceville NJ), Method and apparatus for video data compression using temporally adaptive motion interpolation.
Gindele, Edward B.; Gallagher, Andrew C., Method and system for generating a low resolution image from a sparsely sampled extended dynamic range image sensing device.
Sadjadian Ahmad (Woodall Park GB2) Hurley Terence R. (Pencoed Technology Park GB7), Method of and apparatus for deriving a key signal from a digital video signal.
Gehrmann Rainer (Alsbach-Hhnlein DEX), Method of and arrangement for deriving a control signal for inserting a background signal into parts of a foreground sig.
Chellappa,Ramalingam; Chowdhury,Amit K. Roy; Srinivasan,Sridhar, Method of three-dimensional object reconstruction from a video sequence using a generic model.
Mical Robert J. ; Needle David L. ; Khubchandani Teju J. ; Landrum Stephen H., Resolution enhancement for video display using multi-line interpolation.
Devaney Patrick (Freehold NJ) Gnanaprakasam Daniel (Secane PA) Westerink Peter (Mount Laurel NJ) Topper Robert (Hatboro PA), Segmentation based image compression system.
Kreitman Haim (Kfar Saba ILX) Bar-El Dan (Herzlia ILX) Amir Yoel (Kfar Saba ILX) Tirosh Ehud (Tel Aviv ILX), System for implanting an image into a video stream.
Dean Willis ; Jim Howser ; Marty Garrity ; Jack Heneghan, System for selectively routing data via either a network that supports Internet protocol or via satellite transmission network based on size of the data.
Takata Haruki (Chigasaki JPX) Katsumata Kenji (Yokohama JPX) Hirahata Shigeru (Yokohama JPX) Konno Mituo (Yokohama JPX) Ishibashi Kouichi (Chigasaki JPX) Suzuki Sunao (Fujisawa JPX), Wide-screen television receiver with aspect ratio conversion function and method of displaying a range to be magnified a.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.