USRE45201E1 - Systems and method for image processing - Google Patents

Systems and method for image processing Download PDF

Info

Publication number
USRE45201E1
USRE45201E1 US13630973 US201213630973A USRE45201E US RE45201 E1 USRE45201 E1 US RE45201E1 US 13630973 US13630973 US 13630973 US 201213630973 A US201213630973 A US 201213630973A US RE45201 E USRE45201 E US RE45201E
Authority
US
Grant status
Grant
Patent type
Prior art keywords
image
frame
blank
pixels
edge
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.)
Active
Application number
US13630973
Inventor
Richard M. Sanford
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Facebook Inc
Original Assignee
Facebook Inc
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Grant date

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K9/00Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
    • G06K9/00624Recognising scenes, i.e. recognition of a whole field of perception; recognising scene-specific objects
    • G06K9/00711Recognising video content, e.g. extracting audiovisual features from movies, extracting representative key-frames, discriminating news vs. sport content
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/10Segmentation; Edge detection
    • G06T7/13Edge detection
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/10Segmentation; Edge detection
    • G06T7/136Segmentation; Edge detection involving thresholding
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/90Determination of colour characteristics
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/10Image acquisition modality
    • G06T2207/10016Video; Image sequence

Abstract

A facility is provided for recognizing blank and nearly blank images. In various embodiments, the facility receives an indication of an image, creates an analysis image based on the received image by detecting edges, determines an edge ratio for the analysis image, determines whether the edge ratio exceeds a threshold and, when the edge ratio does not exceed the threshold, identifies the received image as a blank image. The facility can include an edge detector component that creates an analysis image based on a selected image by detecting edges in the selected image, a calculator component that calculates an edge ratio for the analysis image, and an analysis component that determines whether the calculated edge ratio exceeds a threshold.

Description

This application is a continuation of and claims the benefit of priority of U.S. application Ser. No. 11/557,420 (now U.S. Pat. No. 7,711,193), filed Nov. 7, 2006, the entire contents of which are incorporated herein by reference.

BACKGROUND

Images sometimes need to be analyzed to determine whether they are blank or nearly blank. An image is blank when it appears to a user to be a single, solid color. An image is nearly blank when a dominating portion of it appears to a user to be a single, solid color. An example of a nearly blank image is a black screen with a corporate or television network logo appearing in a portion (e.g., corner) of the screen. Such a nearly blank screen may be displayed by a television network between a program and an advertisement. Because nearly blank images can be considered to be blank from a viewer's perspective, the term “blank” in this specification includes actually blank and nearly blank.

An image that is selected from a video may need to be analyzed to determine whether it is blank. A video is generally a sequence of images (e.g., “frames”), or a sequential set of key frames and delta frames. A key frame describes an image completely and delta frames describe portions of the key frame's image that change before a subsequent key frame is received from the sequence. An image can be selected from the video to identify the video. As an example, an Internet World Wide Web (“Web”) page may display a “thumbnail” image to identify a linked video. When a user viewing the Web page selects the thumbnail image, the linked video may play.

The image may be selected automatically. As an example, when a Web site enables users to upload videos, the Web site may automatically select a thumbnail image to associate with the video to provide a link to the video. Commonly, the image is selected from a frame near the beginning of the video, end of the video, or randomly. Sometimes, the automatically selected image is blank. This can occur because some videos have transitions from a solid color (commonly white or black), such as near the beginning of the video.

When the selected image is blank, the image is not a useful thumbnail image because a user viewing a Web page containing the blank image would not readily know to which video the image relates. It is thus desirable to select images that are not blank.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG. 1A is a user interface diagram illustrating a Web page containing several thumbnail images.

FIG. 1B is a user interface diagram illustrating a Web page containing a video associated with a selected thumbnail image.

FIGS. 2A and 2B are block diagrams illustrating portions of videos.

FIG. 3A is a frame illustrating an image.

FIG. 3B is an analysis frame.

FIG. 4 is a flow diagram illustrating a locate_frame routine invoked by the facility in some embodiments.

FIG. 5 is a flow diagram illustrating a check_frame routine invoked by the facility in some embodiments.

FIG. 6 is a flow diagram illustrating a calculate_ratio routine invoked by the facility in some embodiments.

DETAILED DESCRIPTION

A facility is provided for recognizing blank and nearly blank images (jointly, “blank images”). In various embodiments, the facility selects a frame from a video, employs an edge-detection algorithm to detect edges in the selected frame, creates an analysis frame containing the detected edges, calculates an edge ratio associated with the analysis frame, and determines whether the calculated edge ratio indicates whether or not the frame is blank. A nearly blank frame is considered to be blank. The facility can employ any commonly employed edge-detection algorithm. The edge detection algorithm may have a pixel variance factor that can be changed to select the sensitivity of edge detection. The facility may employ the pixel variance factor when determining whether a pixel is a part of an edge. The facility may also employ an edge ratio threshold that can be changed to select the edge ratio. By detecting edges and analyzing the edge ratio, the facility is able to determine whether or not a selected image is blank. When the selected image is blank, the facility can select another frame from the video and repeat the analysis.

The facility can use various algorithms to select a frame for analysis. The facility may indicate to these algorithms to select a frame from a specified portion of the video. In some embodiments, the facility may employ a scene detection algorithm to select a frame based on the screen's content. An example of a scene detection algorithm is described in Frédéric Dufaux, Key frame selection to represent a video, 275-278 (Proceedings of the IEEE Signal Processing Society's 2000 International Conference on Image Processing, 2000), which is incorporated herein by reference in its entirety. In other embodiments, the facility may select a frame randomly, such as from the portion of the video the facility specifies. In other embodiments, the facility may select frames in a video sequentially, starting with the first frame.

The facility employs an edge detection algorithm to detect edges in the selected frame. There are many algorithms available for edge detection. One or more edge detection algorithms can be employed to create an analysis image based on a source image. An example of an edge detection algorithm is spatial convolution. A type of spatial convolution can be represented by equation 1:

M = [ 0.0 - 1.0 0.0 - 1.0 4.0 - 1.0 0.0 - 1.0 0.0 ] C x , y = P x , y M i , j M I , j ( 1 )

The facility can employ equation 1 when determining a color values for a destination pixel in the analysis image based on a source pixel of the selected image. For each source pixel, Px,y the convolution equation calculates a destination pixel, Cx,y. Each value of the source pixel (e.g., each color component's value) can undergo the convolution. As an example suppose source pixel Px,y has color values (RP, GP, BP). The color values for destination pixel Cx,y would be (RC, GC, BC). Each color component of the destination pixel (e.g., RC, GC, or BC) can be determined from the corresponding color value of the source pixel using the equation by substituting the color values for Px,y and Cx,y.

A convolution mask, M, indicates which pixel's values are to be included in the convolution. In equation 1, M indicates that the eight pixels surrounding the subject pixel are to be included. The pixels immediately below, above, and to the right have mask values of −1.0. The pixels at the diagonal locations have mask values 0.

Each element in M is multiplied by the corresponding pixel value adjacent to each source pixel, Px,y, in the source image, P. The results of the multiplications are summed and the sum is divided by the sum of the convolution matrix's values. The result of the division is a pixel, Cx,y, in the convolution output image, C, which is the analysis image.

Thus, this convolution equation cancels out colors of destination pixels when neighboring pixels of the source pixel have equal color values. If pixels surrounding the source pixel have the same colors, the destination pixel is colored black. In various embodiments, a black pixel can be represented by color values (0,0,0) and a non-black pixel can be represented by having at least one color component that is non-zero.

The facility calculates an edge ratio for the analysis image by calculating the number of black and non-black pixels in the analysis image. This edge ratio is computed by dividing the number of non-black pixels by the number of black pixels. This quotient (edge ratio) is compared to an edge ratio threshold. When the ratio is less than or equal to an edge ratio threshold of approximately 0.023, the facility may determine that the image is blank or nearly blank. This edge ratio threshold can be varied, such as programmatically or via user input. As the edge ratio threshold is raised, more images may be considered to be non-blank. Conversely, when the edge ratio threshold is lowered, more images may be considered to be blank or nearly blank.

Turning now to the figures, FIG. 1A is a user interface diagram illustrating a Web page containing several thumbnail images. A display 100 of a computing device a user employs can display an Internet browser 102. The Internet browser displays a Web page within its window 105. When the user navigates to a Web page, such as Web page 107, that links to one or more videos, the Web page may show one or more thumbnails 104. When the user selects a thumbnail, such as by clicking a mouse pointer on the thumbnail, a video associated with the thumbnail may be displayed.

FIG. 1B is a user interface diagram illustrating a Web page containing a video associated with a selected thumbnail image. The Web page may embed an object, such as a video viewer object, to display a video in a video region 106 when a user selects a thumbnail.

FIGS. 2A and 2B are block diagrams illustrating portions of videos. FIG. 2 illustrates a portion of a video 200 comprising frames 202, 204, 206, and 208. The frames can be a combination of key frames and delta frames. Alternatively, each frame may be a key frame. As previously discussed, a key frame describes an entire image whereas a delta frame describes changes to an image described by a prior key frame. Each frame may also identify whether it is a key frame or delta frame. A video can have sequences of frames that are blank (e.g., actually blank or nearly blank) or non-blank. As an example, a portion of a video illustrated in FIG. 2B has sequences of frames that are blank (302 and 306) and other sequences of frames that are not blank (304 and 308). Blank sequences 302 and 306 may be transitions between the non-blank sequences.

FIG. 3A is a frame illustrating an image. The frame 320 contains an image 322. Although the image is depicted in the illustration as black, it can be one or more colors. As an example, the image may be an actual photograph.

FIG. 3B is an analysis frame. The analysis frame indicates edges an edge detector detected in the selected frame. Edge 342 corresponds to image 320. Although the illustrated edge is depicted in black, it may be depicted in white or the color of the original image.

FIG. 4 is a flow diagram illustrating a locate_frame routine invoked by the facility in some embodiments. The facility may invoke the routine to locate a frame in a video, such as to identify a thumbnail image. The routine begins at block 402.

At block 404, the routine receives an indication of a video. As an example, the routine may receive an indication of a file location at which the video is stored.

At block 406, the routine selects a portion of the video from which to locate a frame. As an example, the routine may select as a range the first thirty seconds of the video.

At block 408, the routine invokes an identify_frame subroutine to select a frame from the video. The routine may provide an indication of the portion of the video from which to select a frame, such as from the beginning to thirty seconds. The identify_frame subroutine may use one or more of various algorithms to select a frame. As an example, the subroutine may use a scene selection algorithm, random selection, first frame, etc.

At block 410, the routine invokes a check_frame subroutine to determine whether the selected frame appears to be blank. In some embodiments, the check_frame subroutine returns NULL to indicate that the selected frame is blank. The check_frame subroutine is described in further detail below in relation to FIG. 5.

At decision block 412, the algorithm determines, based on the check_frame subroutine's return value, whether the frame appears to be blank. If the frame appears to be blank, the routine continues at block 414. Otherwise, the routine continues at block 416, where it returns an indication of the selected frame.

At block 414, the routine selects another portion of the video from which to select a frame. As an example, the routine may add 30 seconds to the range identified at block 406.

FIG. 5 is a flow diagram illustrating a check_frame routine invoked by the facility in some embodiments. The facility may invoke the routine to determine whether a selected frame is blank. The routine begins at block 502.

At block 504, the routine receives an indication of a frame. The routine initially sets a frame identifier to identify the indicated frame. The routine may also receive an indication of a video from which the frame was selected.

At block 506, the routine invokes a detect_edges subroutine. In various embodiments, the detect_edges subroutine may receive an indication of a frame and a video from which the frame was selected, and provide a new frame in which edges are identified. The new frame is an analysis frame that the facility can use to determine whether the frame is blank. The detect_edges subroutine may employ any suitable edge detection algorithm. Examples of edge detection algorithms include convolution (described above), Canny, Sobel, and Laplacian edge detectors.

At block 508, the routine invokes a calculate_ratio subroutine to calculate a ratio of non-black to black pixels (e.g., edge ratio) in the new frame returned by the detect_edges subroutine. The calculate_ratio subroutine is described in further detail below in relation to FIG. 6.

At decision block 510, the routine determines whether the ratio returned by the calculate_ratio subroutine is smaller than or equal to an edge ratio threshold. If the routine is less than or equal to the edge ratio threshold, the routine continues at block 512. Otherwise, the routine continues at block 514. In various embodiments, the check_frame routine may also receive an indication of the edge ratio threshold at block 504, e.g., so as to configure the routine.

At block 512, the routine sets the frame identifier to NULL to indicate that the frame appears to be blank.

At block 514, the routine returns the frame identifier.

FIG. 6 is a flow diagram illustrating a calculate_ratio routine invoked by the facility in some embodiments. The facility may invoke the routine to calculate an edge ratio. The routine begins at block 602.

At block 604, the routine receives a frame. The frame may be an analysis frame that identifies edges that were detected by an edge detection algorithm in a frame selected from a video.

At block 606, the routine sets to zero counters indicating the number of black (“num_black”) pixels and the number of non-black (“num_white”) pixels.

Between the loop of blocks 608-620, the routine counts the number of black and non-black pixels. At block 608, the routine selects a pixel.

At decision block 610, the routine determines whether the pixel is black. If the pixel is black, the routine continues at block 612. Otherwise, the routine continues at block 616.

At block 612, the routine increments the counter for black pixels and then continues at block 620.

At block 616, the routine increments the counter for non-black pixels.

At block 620, the routine selects another pixel. If there are no further pixels, the routine continues at block 622 where it returns the quotient determined by dividing the number of non-black pixels by the number of black pixels. Otherwise, the routine continues at block 610.

While various embodiments are described in terms of the environment described above, those skilled in the art will appreciate that the facility may be implemented in a variety of other environments including a single, monolithic computer system, as well as various other combinations of computer systems or similar devices connected in various ways.

Those skilled in the art will appreciate that the logic illustrated in FIGS. 4-6 and in their associated descriptions may be altered in various ways. For example, the order of the logic may be rearranged; substeps may be performed in parallel; shown logic may be omitted or other logic may be included; etc.

It will be appreciated by those skilled in the art that the above-described facility may be straightforwardly adapted or extended in various ways. For example, the facility can be employed to recognize blank and nearly-blank images in general and not just from a video. While the foregoing description makes reference to particular embodiments, the scope of the invention is defined solely by the claims that follow and the elements recited therein.

Claims (31)

I claim:
1. A computer-implemented method for processing an image, comprising:
identifying at least one characteristic of the image;
determining a number of first colored pixels and a number of non-first colored pixels associated with the identified characteristic of the image;
randomly selecting an image from a video;
calculating, using a processor, a ratio for the image based on the a number of first colored pixels and the a number of non-first colored pixels;
comparing the ratio for the image with a threshold; and
identifying the image as being blank based on the comparison of the ratio to the threshold.
2. The method of claim 1, wherein the first colored pixels are black pixels and the non-first colored pixels are non-black pixels.
3. The method of claim 2, wherein calculating the ratio for the image comprises calculating a quotient based on the number of black pixels and the number of non-black pixels.
4. The method of claim 1, wherein the at least one characteristic of the image comprises an edge.
5. The method of claim 4, further comprising:
detecting edge pixels in the image; and
determining, based on the detected edge pixels, a number of black pixels and a number of non-black pixels.
6. The method of claim 4, wherein the ratio is an edge ratio.
7. The method of claim 1, wherein the image is associated with a frame in a the video.
8. The method of claim 7, further comprising:
generating a thumbnail image based on the frame when the image is not identified as being blank; and
linking the thumbnail image to the video.
9. The method of claim 1, wherein identifying the image as being blank comprises identifying the image as being blank or nearly blank based on the comparison of the ratio to the threshold.
10. A non-transitory computer-readable storage medium storing computer-executable instructions for processing an image that, when executed by a processor, perform the steps of:
identifying at least one characteristic of the image;
determining a number of first colored pixels and a number of non-first colored pixels associated with the identified characteristic of the image;
randomly selecting an image from a video;
calculating, using a processor, a ratio for the image based on the a number of first colored pixels and the a number of non-first colored pixels;
comparing the ratio for the image with a threshold; and
identifying the image as being blank based on the comparison of the ratio to the threshold.
11. The computer-readable storage medium of claim 10, wherein the first colored pixels are black pixels and the non-first colored pixels are non-black pixels.
12. The computer-readable storage medium of claim 11, wherein calculating the ratio for the image comprises calculating a quotient based on the number of black pixels and the number of non-black pixels.
13. The computer-readable storage medium of claim 10, wherein the at least one characteristic of the image comprises an edge.
14. The computer-readable storage medium of claim 13, further storing instructions for:
detecting edge pixels in the image; and
determining, based on the detected edge pixels, a number of black pixels and a number of non-black pixels.
15. The computer-readable storage medium of claim 13, wherein the ratio is an edge ratio.
16. The computer-readable storage medium of claim 10, wherein the image is associated with a frame in a the video.
17. The computer-readable storage medium of claim 16, further storing instructions for:
generating a thumbnail image based on the frame when the image is not identified as being blank; and
linking the thumbnail image to the video.
18. The computer-readable storage medium of claim 10, wherein identifying the image as being blank comprises identifying the image as being blank or nearly blank based on the comparison of the ratio to the threshold.
19. A device for processing an image, comprising:
a storage for storing instructions; and
a processor for executing the instructions to perform the steps of:
identifying at least one characteristic of the image;
determining a number of first colored pixels and a number of non-first colored pixels associated with the identified characteristic of the image;
randomly selecting an image from a video;
calculating a ratio for the image based on the a number of first colored pixels and the a number of non-first colored pixels;
comparing the ratio for the image with a threshold; and
identifying the image as being blank based on the comparison of the ratio to the threshold.
20. The device of claim 19, wherein the first colored pixels are black pixels and the non-first colored pixels are non-black pixels.
21. The device of claim 20, wherein calculating the ratio for the image comprises calculating a quotient based on the number of black pixels and the number of non-black pixels.
22. The device of claim 19, wherein the at least one characteristic of the image comprises an edge.
23. The device of claim 22, further storing instructions for:
detecting edge pixels in the image; and
determining, based on the detected edge pixels, a number of black pixels and a number of non-black pixels.
24. The device of claim 22, wherein the ratio is an edge ratio.
25. The device of claim 19, wherein the image is associated with a frame in a the video.
26. The device of claim 25, further storing instructions for:
generating a thumbnail image based on the frame when the image is not identified as being blank; and
linking the thumbnail image to the video.
27. The device of claim 19, wherein identifying the image as being blank comprises identifying the image as being blank or nearly blank based on the comparison of the ratio to the threshold.
28. A computer-implemented method comprising:
randomly identifying a first frame within a video file;
determining, using a processor, that the first frame is blank;
randomly identifying a second frame within the video file;
determining that the second frame is not blank; and
generating a thumbnail representative of the video file using the second frame.
29. The method of claim 28, wherein determining that the first frame is blank comprises:
calculating an edge ratio for the first frame;
comparing the edge ratio to a threshold; and
determining that the first frame is blank based on the comparison of the edge ratio to the threshold.
30. A system for processing an image, comprising:
one or more processors configured to:
randomly identify a first frame within a video file;
determine that the first frame is blank;
randomly identify a second frame within the video file;
determine that the second frame is not blank; and
generate a thumbnail representative of the video file using the second frame.
31. The system of claim 30, wherein the one or more processors are further configured to:
calculate an edge ratio for the first frame;
compare the edge ratio to a threshold; and
determine that the first frame is blank based on the comparison of the edge ratio to the threshold.
US13630973 2006-11-07 2012-09-28 Systems and method for image processing Active USRE45201E1 (en)

Priority Applications (3)

Application Number Priority Date Filing Date Title
US11557420 US7711193B2 (en) 2006-11-07 2006-11-07 Recognizing blank and nearly blank images
US12752320 US7805007B2 (en) 2006-11-07 2010-04-01 Systems and methods for image processing
US13630973 USRE45201E1 (en) 2006-11-07 2012-09-28 Systems and method for image processing

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
US13630973 USRE45201E1 (en) 2006-11-07 2012-09-28 Systems and method for image processing

Related Parent Applications (1)

Application Number Title Priority Date Filing Date
US12752320 Reissue US7805007B2 (en) 2006-11-07 2010-04-01 Systems and methods for image processing

Publications (1)

Publication Number Publication Date
USRE45201E1 true USRE45201E1 (en) 2014-10-21

Family

ID=39359794

Family Applications (5)

Application Number Title Priority Date Filing Date
US11557420 Active 2029-03-04 US7711193B2 (en) 2006-11-07 2006-11-07 Recognizing blank and nearly blank images
US12752320 Active US7805007B2 (en) 2006-11-07 2010-04-01 Systems and methods for image processing
US12873504 Active US7899257B2 (en) 2006-11-07 2010-09-01 Systems and methods for image processing
US13025269 Active US7983488B2 (en) 2006-11-07 2011-02-11 Systems and methods for image processing
US13630973 Active USRE45201E1 (en) 2006-11-07 2012-09-28 Systems and method for image processing

Family Applications Before (4)

Application Number Title Priority Date Filing Date
US11557420 Active 2029-03-04 US7711193B2 (en) 2006-11-07 2006-11-07 Recognizing blank and nearly blank images
US12752320 Active US7805007B2 (en) 2006-11-07 2010-04-01 Systems and methods for image processing
US12873504 Active US7899257B2 (en) 2006-11-07 2010-09-01 Systems and methods for image processing
US13025269 Active US7983488B2 (en) 2006-11-07 2011-02-11 Systems and methods for image processing

Country Status (1)

Country Link
US (5) US7711193B2 (en)

Families Citing this family (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8396878B2 (en) 2006-09-22 2013-03-12 Limelight Networks, Inc. Methods and systems for generating automated tags for video files
US9015172B2 (en) 2006-09-22 2015-04-21 Limelight Networks, Inc. Method and subsystem for searching media content within a content-search service system
US8966389B2 (en) 2006-09-22 2015-02-24 Limelight Networks, Inc. Visual interface for identifying positions of interest within a sequentially ordered information encoding
US7711193B2 (en) * 2006-11-07 2010-05-04 Aol Inc. Recognizing blank and nearly blank images
US7853079B1 (en) * 2006-12-08 2010-12-14 Adobe Systems Incorporated Technique for automatic poster frame detection
US8214374B1 (en) 2011-09-26 2012-07-03 Limelight Networks, Inc. Methods and systems for abridging video files
KR20130112162A (en) * 2012-04-03 2013-10-14 삼성전자주식회사 Video display terminal and method for displaying a plurality of video thumbnail simultaneously
US9003445B1 (en) * 2012-05-10 2015-04-07 Google Inc. Context sensitive thumbnail generation
US9064317B2 (en) * 2012-05-15 2015-06-23 Palo Alto Research Center Incorporated Detection of near-field camera obstruction
CN104298982A (en) * 2013-07-16 2015-01-21 深圳市腾讯计算机系统有限公司 Text recognition method and device
WO2016115277A1 (en) * 2015-01-13 2016-07-21 Arris Enterprises, Inc. Detection of solid color frames for determining transitions in video content
CN104735521B (en) * 2015-03-30 2018-04-13 北京奇艺世纪科技有限公司 A rolling method and apparatus for detecting subtitles

Citations (37)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5835163A (en) 1995-12-21 1998-11-10 Siemens Corporate Research, Inc. Apparatus for detecting a cut in a video
US6084988A (en) * 1996-02-19 2000-07-04 Kabushiki Kaisha Toshiba Image processing apparatus
US20020114504A1 (en) * 1997-09-22 2002-08-22 Hiroyuki Shinbata Image discrimination apparatus and image discrimination method
US6587115B2 (en) * 2000-02-22 2003-07-01 Riso Kagaku Corporation Method of an apparatus for distinguishing type of pixel
US20040095396A1 (en) 2002-11-19 2004-05-20 Stavely Donald J. Video thumbnail
US20040128317A1 (en) * 2000-07-24 2004-07-01 Sanghoon Sull Methods and apparatuses for viewing, browsing, navigating and bookmarking videos and displaying images
US6804294B1 (en) * 1998-08-11 2004-10-12 Lucent Technologies Inc. Method and apparatus for video frame selection for improved coding quality at low bit-rates
US20050190382A1 (en) * 2004-02-26 2005-09-01 Visioneer, Inc. Method for suppressing blank pages in a multi-page scanning process and software therefor
US20050200903A1 (en) * 2002-04-01 2005-09-15 Nobuyuki Okubo Image processing device
US20050240967A1 (en) * 2004-04-27 2005-10-27 Anderson Glen J System and method for improved channel surfing
US20060026524A1 (en) * 2004-08-02 2006-02-02 Microsoft Corporation Systems and methods for smart media content thumbnail extraction
US7042525B1 (en) 2000-07-06 2006-05-09 Matsushita Electric Industrial Co., Ltd. Video indexing and image retrieval system
US20060107289A1 (en) * 2004-07-28 2006-05-18 Microsoft Corporation Thumbnail generation and presentation for recorded TV programs
US20060110057A1 (en) * 2004-11-23 2006-05-25 Microsoft Corporation Method and system for detecting black frames in a sequence of frames
US20060153456A1 (en) * 2005-01-10 2006-07-13 Fuji Xerox Co., Ltd. System and method for detecting and ranking images in order of usefulness based on vignette score
US20060195859A1 (en) * 2005-02-25 2006-08-31 Richard Konig Detecting known video entities taking into account regions of disinterest
US20060221410A1 (en) * 2005-03-29 2006-10-05 Kabushiki Kaisha Toshiba Image processing apparatus
US20070268966A1 (en) 2006-05-17 2007-11-22 Samsung Electronics Co., Ltd. Apparatus and method for retrieving video
US20080016469A1 (en) * 2001-12-28 2008-01-17 Jong Yeul Suh Apparatus and method for generating thumbnail images
US20080031595A1 (en) * 2006-08-07 2008-02-07 Lg Electronics Inc. Method of controlling receiver and receiver using the same
US20080066107A1 (en) * 2006-09-12 2008-03-13 Google Inc. Using Viewing Signals in Targeted Video Advertising
US20080107343A1 (en) * 2006-11-07 2008-05-08 Sanford Richard M Recognizing blank and nearly blank images
US20080118226A1 (en) * 2002-07-30 2008-05-22 Kim Eung T PVR-support video decoding system
US20080127244A1 (en) * 2006-06-30 2008-05-29 Tong Zhang Detecting blocks of commercial content in video data
US20080291492A1 (en) * 2007-05-22 2008-11-27 Sharp Kabushiki Kaisha Printer driver program and image forming apparatus
US20090097076A1 (en) * 2007-10-11 2009-04-16 Brother Kogyo Kabushiki Kaisha Image processing apparatus, methods of controlling such image processing apparatus, and computer-readable media which, when executed, control such image processing apparatus
US20090116738A1 (en) * 2007-10-10 2009-05-07 Sharp Kabushiki Kaisha Image processing apparatus, image forming apparatus, image processing method, and recording medium on which image processing program is recorded
US20090214112A1 (en) * 2005-03-24 2009-08-27 Borrey Roland G Systems and methods of accessing random access cache for rescanning
US20090285551A1 (en) * 2008-05-14 2009-11-19 Digitalsmiths Corporation Systems and Methods for Identifying Pre-Inserted and/or Potential Advertisement Breaks in a Video Sequence
US20100053682A1 (en) * 2008-08-27 2010-03-04 Sharp Kabushiki Kaisha Image processing apparatus, image forming apparatus, image processing method, and computer-readable storage medium containing image processing program
US7697149B2 (en) * 2005-08-10 2010-04-13 Kyocera Mita Corporation System for detecting and avoiding printing of solid black areas
US7751071B2 (en) * 2003-03-20 2010-07-06 Ricoh Company, Ltd. Image reproduction apparatus, image reproduction method, and program for implementing the method on a computer
US20100182618A1 (en) * 2009-01-20 2010-07-22 Toshio Akiyama Image processing system, image processing apparatus, image processing method
US7853079B1 (en) * 2006-12-08 2010-12-14 Adobe Systems Incorporated Technique for automatic poster frame detection
US7990475B1 (en) * 2006-09-05 2011-08-02 Adobe Systems Incorporated Methods and apparatus for automated representative image selection
US20120081766A1 (en) * 2010-09-30 2012-04-05 Brother Kogyo Kabushiki Kaisha Image processing apparatus, image processing method and image scanning apparatus
US20120203924A1 (en) * 2007-06-28 2012-08-09 Brian Dote Generating low resolution user interfaces for transmission to mobile devices

Patent Citations (50)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5835163A (en) 1995-12-21 1998-11-10 Siemens Corporate Research, Inc. Apparatus for detecting a cut in a video
US6084988A (en) * 1996-02-19 2000-07-04 Kabushiki Kaisha Toshiba Image processing apparatus
US6263118B1 (en) * 1996-02-19 2001-07-17 Kabushiki Kaisha Toshiba Image processing apparatus
US20020114504A1 (en) * 1997-09-22 2002-08-22 Hiroyuki Shinbata Image discrimination apparatus and image discrimination method
US6804294B1 (en) * 1998-08-11 2004-10-12 Lucent Technologies Inc. Method and apparatus for video frame selection for improved coding quality at low bit-rates
US6587115B2 (en) * 2000-02-22 2003-07-01 Riso Kagaku Corporation Method of an apparatus for distinguishing type of pixel
US7042525B1 (en) 2000-07-06 2006-05-09 Matsushita Electric Industrial Co., Ltd. Video indexing and image retrieval system
US20040128317A1 (en) * 2000-07-24 2004-07-01 Sanghoon Sull Methods and apparatuses for viewing, browsing, navigating and bookmarking videos and displaying images
US20080016469A1 (en) * 2001-12-28 2008-01-17 Jong Yeul Suh Apparatus and method for generating thumbnail images
US7912303B2 (en) * 2001-12-28 2011-03-22 Lg Electronics Inc. Apparatus and method for generating thumbnail images
US20050200903A1 (en) * 2002-04-01 2005-09-15 Nobuyuki Okubo Image processing device
US8249167B2 (en) * 2002-07-30 2012-08-21 Lg Electronics Inc. PVR-support video decoding system
US8259812B2 (en) * 2002-07-30 2012-09-04 Lg Electronics Inc. PVR-support video decoding system
US20080118226A1 (en) * 2002-07-30 2008-05-22 Kim Eung T PVR-support video decoding system
US20080181301A1 (en) * 2002-07-30 2008-07-31 Eung Tae Kim PVR-support video decoding system
US20040095396A1 (en) 2002-11-19 2004-05-20 Stavely Donald J. Video thumbnail
US7751071B2 (en) * 2003-03-20 2010-07-06 Ricoh Company, Ltd. Image reproduction apparatus, image reproduction method, and program for implementing the method on a computer
US20050190382A1 (en) * 2004-02-26 2005-09-01 Visioneer, Inc. Method for suppressing blank pages in a multi-page scanning process and software therefor
US20050240967A1 (en) * 2004-04-27 2005-10-27 Anderson Glen J System and method for improved channel surfing
US20060107289A1 (en) * 2004-07-28 2006-05-18 Microsoft Corporation Thumbnail generation and presentation for recorded TV programs
US7986372B2 (en) * 2004-08-02 2011-07-26 Microsoft Corporation Systems and methods for smart media content thumbnail extraction
US20060026524A1 (en) * 2004-08-02 2006-02-02 Microsoft Corporation Systems and methods for smart media content thumbnail extraction
US20060110057A1 (en) * 2004-11-23 2006-05-25 Microsoft Corporation Method and system for detecting black frames in a sequence of frames
US20060153456A1 (en) * 2005-01-10 2006-07-13 Fuji Xerox Co., Ltd. System and method for detecting and ranking images in order of usefulness based on vignette score
US20060195859A1 (en) * 2005-02-25 2006-08-31 Richard Konig Detecting known video entities taking into account regions of disinterest
US20090214112A1 (en) * 2005-03-24 2009-08-27 Borrey Roland G Systems and methods of accessing random access cache for rescanning
US20060221410A1 (en) * 2005-03-29 2006-10-05 Kabushiki Kaisha Toshiba Image processing apparatus
US7697149B2 (en) * 2005-08-10 2010-04-13 Kyocera Mita Corporation System for detecting and avoiding printing of solid black areas
US20070268966A1 (en) 2006-05-17 2007-11-22 Samsung Electronics Co., Ltd. Apparatus and method for retrieving video
US20080127244A1 (en) * 2006-06-30 2008-05-29 Tong Zhang Detecting blocks of commercial content in video data
US20080031595A1 (en) * 2006-08-07 2008-02-07 Lg Electronics Inc. Method of controlling receiver and receiver using the same
US7990475B1 (en) * 2006-09-05 2011-08-02 Adobe Systems Incorporated Methods and apparatus for automated representative image selection
US20110289531A1 (en) * 2006-09-12 2011-11-24 Google Inc. Using Viewing Signals In Targeted Video Advertising
US20080066107A1 (en) * 2006-09-12 2008-03-13 Google Inc. Using Viewing Signals in Targeted Video Advertising
US7711193B2 (en) * 2006-11-07 2010-05-04 Aol Inc. Recognizing blank and nearly blank images
US7899257B2 (en) * 2006-11-07 2011-03-01 Aol Inc. Systems and methods for image processing
US20100189347A1 (en) * 2006-11-07 2010-07-29 Aol Inc. Systems and methods for image processing
US7983488B2 (en) * 2006-11-07 2011-07-19 Aol Inc. Systems and methods for image processing
US20080107343A1 (en) * 2006-11-07 2008-05-08 Sanford Richard M Recognizing blank and nearly blank images
US7805007B2 (en) * 2006-11-07 2010-09-28 Aol Inc. Systems and methods for image processing
US7853079B1 (en) * 2006-12-08 2010-12-14 Adobe Systems Incorporated Technique for automatic poster frame detection
US20080291492A1 (en) * 2007-05-22 2008-11-27 Sharp Kabushiki Kaisha Printer driver program and image forming apparatus
US8407363B2 (en) * 2007-06-28 2013-03-26 Apple Inc. Generating low resolution user interfaces for transmission to mobile devices
US20120203924A1 (en) * 2007-06-28 2012-08-09 Brian Dote Generating low resolution user interfaces for transmission to mobile devices
US20090116738A1 (en) * 2007-10-10 2009-05-07 Sharp Kabushiki Kaisha Image processing apparatus, image forming apparatus, image processing method, and recording medium on which image processing program is recorded
US20090097076A1 (en) * 2007-10-11 2009-04-16 Brother Kogyo Kabushiki Kaisha Image processing apparatus, methods of controlling such image processing apparatus, and computer-readable media which, when executed, control such image processing apparatus
US20090285551A1 (en) * 2008-05-14 2009-11-19 Digitalsmiths Corporation Systems and Methods for Identifying Pre-Inserted and/or Potential Advertisement Breaks in a Video Sequence
US20100053682A1 (en) * 2008-08-27 2010-03-04 Sharp Kabushiki Kaisha Image processing apparatus, image forming apparatus, image processing method, and computer-readable storage medium containing image processing program
US20100182618A1 (en) * 2009-01-20 2010-07-22 Toshio Akiyama Image processing system, image processing apparatus, image processing method
US20120081766A1 (en) * 2010-09-30 2012-04-05 Brother Kogyo Kabushiki Kaisha Image processing apparatus, image processing method and image scanning apparatus

Non-Patent Citations (5)

* Cited by examiner, † Cited by third party
Title
Dufaux, Frederic, "Key Frame Selection to Represent a Video," Compaq Computer Corp., Cambridge Research Lab. 2000 International Conference on Image Processing; vol. II of III, Sep. 10-13, 2000. Sponsors: Institute of Electrical and Electronics Engineers Signal Processing Society.
U.S. Appl. No. 11/557,420, filed Dec. 15, 2009, Notice of Allowance.
U.S. Appl. No. 12/752,320, filed Jun. 1, 2010, Notice of Allowance.
U.S. Appl. No. 12/873,504, filed Oct. 29, 2010, Notice of Allowance.
U.S. Appl. No. 13/025,269, filed Mar. 17 2011, Notice of Allowance.

Also Published As

Publication number Publication date Type
US20110138420A1 (en) 2011-06-09 application
US20100189347A1 (en) 2010-07-29 application
US7711193B2 (en) 2010-05-04 grant
US7805007B2 (en) 2010-09-28 grant
US7899257B2 (en) 2011-03-01 grant
US20100329570A1 (en) 2010-12-30 application
US20080107343A1 (en) 2008-05-08 application
US7983488B2 (en) 2011-07-19 grant

Similar Documents

Publication Publication Date Title
US6049363A (en) Object detection method and system for scene change analysis in TV and IR data
US6782143B1 (en) Method and apparatus for processing an image
US6535254B1 (en) Method and device for noise reduction
Tonomura et al. VideoMAP and VideoSpaceIcon: tools for anatomizing video content
US6359658B1 (en) Subjective noise measurement on active video signal
US6262773B1 (en) System for conversion of interlaced video to progressive video using edge correlation
US7155058B2 (en) System and method for automatically detecting and correcting red eye
US6181376B1 (en) Method of determining missing color values for pixels in a color filter array
US7336819B2 (en) Detection of sky in digital color images
US6252975B1 (en) Method and system for real time feature based motion analysis for key frame selection from a video
US6532022B1 (en) Method and apparatus for model-based compositing
US6157744A (en) Method and apparatus for detecting a point of change in a moving image
US20050041872A1 (en) Method for converting PowerPoint presentation files into compressed image files
Mahmoud A new fast skin color detection technique
US6366706B1 (en) Method and apparatus for automatic aspect format detection in digital video pictures
US20060078055A1 (en) Signal processing apparatus and signal processing method
Phillips Iii et al. Flame recognition in video
US20100182410A1 (en) Computing a depth map
US6288703B1 (en) Method for removing from an image the background surrounding a selected subject by generating candidate mattes
US20030011679A1 (en) Method of measuring digital video quality
US6493042B1 (en) Feature based hierarchical video segmentation
US6434271B1 (en) Technique for locating objects within an image
US6205231B1 (en) Object identification in a moving video image
US20020051058A1 (en) Intruding object detecting method and intruding object monitoring apparatus employing the method
US20030194131A1 (en) Object extraction

Legal Events

Date Code Title Description
AS Assignment

Owner name: AOL LLC, VIRGINIA

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:SANFORD, RICHARD M.;REEL/FRAME:031034/0208

Effective date: 20061113

Owner name: AOL INC., VIRGINIA

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:AOL LLC;REEL/FRAME:031034/0225

Effective date: 20091204

Owner name: FACEBOOK, INC., CALIFORNIA

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:AOL INC.;REEL/FRAME:031034/0312

Effective date: 20120614

MAFP

Free format text: PAYMENT OF MAINTENANCE FEE, 8TH YEAR, LARGE ENTITY (ORIGINAL EVENT CODE: M1552)

Year of fee payment: 8