Systems and methods for classifying objects in digital images captured using mobile devices
원문보기
IPC분류정보
국가/구분
United States(US) Patent
등록
국제특허분류(IPC7판)
G06K-009/00
G06K-009/22
출원번호
US-0802226
(2013-03-13)
등록번호
US-9355312
(2016-05-31)
발명자
/ 주소
Amtrup, Jan Willers
Macciola, Anthony
Thompson, Steve
Ma, Jiyong
Shustorovich, Alexander
Thrasher, Christopher W.
출원인 / 주소
Kofax, Inc.
대리인 / 주소
Zilka-Kotab, PC
인용정보
피인용 횟수 :
15인용 특허 :
252
초록▼
In one embodiment, a method includes receiving a digital image captured by a mobile device; and using a processor of the mobile device: generating a first representation of the digital image, the first representation being characterized by a reduced resolution; generating a first feature vector base
In one embodiment, a method includes receiving a digital image captured by a mobile device; and using a processor of the mobile device: generating a first representation of the digital image, the first representation being characterized by a reduced resolution; generating a first feature vector based on the first representation; comparing the first feature vector to a plurality of reference feature matrices; and classifying an object depicted in the digital image as a member of a particular object class based at least in part on the comparing.
대표청구항▼
1. A method, comprising: receiving a digital image captured by a mobile device; andusing a processor of the mobile device: generating a first representation of the digital image, the first representation being characterized by a reduced resolution;generating a first feature vector based on the first
1. A method, comprising: receiving a digital image captured by a mobile device; andusing a processor of the mobile device: generating a first representation of the digital image, the first representation being characterized by a reduced resolution;generating a first feature vector based on the first representation;comparing the first feature vector to a plurality of reference feature matrices;classifying an object depicted in the digital image as a member of a particular object class based at least in part on the comparing; andbinarizing the digital image based at least in part on one or more of the classifying and a result thereof;wherein the binarizing comprises: determining an object class color scheme;adjusting one or more binarization parameters based on the object class color scheme; andthresholding the digital image using the one or more adjusted binarization parameters. 2. The method as recited in claim 1, wherein generating the first representation comprises: dividing the digital image into a plurality of sections; anddetermining, for each section, at least one characteristic value, each characteristic value corresponding to one or more features descriptive of the section. 3. The method as recited in claim 1, further comprising defining at least one hyperplane between at least some of the reference feature matrices, each hyperplane defining a boundary between first objects corresponding to one of the reference feature matrices and second objects corresponding to another of the reference feature matrices. 4. The method as recited in claim 1, wherein the first representation is a color image. 5. The method as recited in claim 1, wherein one or more of the reference feature matrices comprises a plurality of feature vectors, and wherein each feature vector of the reference feature matrices corresponds to at least one characteristic of an object. 6. The method as recited in claim 1, wherein the comparing comprises an N-dimensional comparison, and wherein N is greater than 50. 7. The method as recited in claim 1, wherein the first feature vector is characterized by a feature vector length greater than 500. 8. The method as recited in claim 1, further comprising: determining one or more object features of the object based at least in part on the particular object class. 9. The method as recited in claim 1, wherein generating the first feature vector comprises determining a color profile of some or all of the object. 10. The method as recited in claim 1, further comprising predicting an identity of text depicted on the object using optical character recognition (OCR), wherein the predicting is based at least in part on the particular object class. 11. The method as recited in claim 10, further comprising modifying at least one identity predicted using OCR based on an expected format of text depicted on the object, wherein the expected format is determined based at least in part on the particular object class. 12. The method as recited in claim 1, further comprising one or more of: detecting the object depicted in the digital image based at least in part on one or more of the classifying and a result thereof;cropping the digital image based at least in part on one or more of the classifying and the result thereof;rectangularizing the object depicted in the digital image based at least in part on one or more of the classifying and the result thereof. 13. The method as recited in claim 1, wherein the binarizing comprises: determining an object class mask;applying the object class mask to the digital image; andthresholding a subregion of the digital image based on the object class mask. 14. The method as recited in claim 13, wherein the binarizing further comprises: adjusting one or more binarization parameters based on the object class mask; andthresholding the digital image using the one or more adjusted binarization parameters. 15. The method as recited in claim 1, further comprising: determining a geographical location associated with the mobile device, wherein the classifying is further based at least in part on the geographical location. 16. The method as recited in claim 1, further comprising: outputting an indication of the particular object class to a display of the mobile device; andreceiving user input via the display of the mobile device in response to outputting the indication, the user input comprising either a confirmation, a negation, or a modification of the particular object class. 17. The method as recited in claim 1, further comprising: determining one or more object features of the object based at least in part on the particular object class; anddetecting one or more additional objects belonging to the particular object class based on the determined object feature(s),wherein the one or more additional objects are depicted either in the digital image or another digital image received by the mobile device. 18. A method, comprising: generating a first feature vector based on a digital image captured by a mobile device;comparing the first feature vector to a plurality of reference feature matrices;classifying an object depicted in the digital image as a member of a particular object class based at least in part on the comparing; anddetermining one or more object features of the object based at least in part on the particular object class;determining one or more object features of the object based at least in part on the particular object class; anddetecting one or more additional objects belonging to the particular object class based on the determined object feature(s),wherein the one or more additional objects are depicted either in the digital image or another digital image received by the mobile device. 19. The method as recited in claim 18, wherein the one or more object features comprise an object color scheme, and wherein the method comprises binarizing the digital image based at least in part on: determining the object color scheme;adjusting one or more binarization parameters based on the object color scheme; andthresholding the digital image using the one or more adjusted binarization parameters. 20. The method as recited in claim 18, wherein the one or more object features comprise an object class mask, and wherein the method comprises binarizing the digital image based at least in part on: determining the object class mask;applying the object class mask to the digital image; andthresholding a subregion of the digital image based on the object class mask. 21. The method as recited in claim 20, wherein the one or more object features further comprise an object color scheme, and wherein the binarizing comprises: determining the object color scheme;adjusting one or more binarization parameters based on the object color scheme; andthresholding the digital image using the one or more adjusted binarization parameters. 22. A system, comprising: a processor; andlogic in and/or executable by the processor to cause the processor to: generate a first representation of a digital image captured by a mobile device;generate a first feature vector based on the first representation;compare the first feature vector to a plurality of reference feature matrices;classify an object depicted in the digital image as a member of a particular object class based at least in part on the comparison;determine one or more object features of the object based at least in part on the particular object class; anddetect one or more additional objects belonging to the particular object class based on the determined object feature(s), wherein the one or more additional objects are depicted either in the digital image or another digital image received by the mobile device. 23. A computer program product comprising: a non-transitory computer readable storage medium having program code embodied therewith, the program code readable/executable by a processor to: generate a first representation of a digital image captured by a mobile device;generate a first feature vector based on the first representation;compare the first feature vector to a plurality of reference feature matrices;classify an object depicted in the digital image as a member of a particular object class based at least in part on the comparison;determine one or more object features of the object based at least in part on the particular object class;detect one or more additional objects belonging to the particular object class based on the determined object feature(s); andwherein the one or more additional objects are depicted either in the digital image or another digital image received by the mobile device.
연구과제 타임라인
LOADING...
LOADING...
LOADING...
LOADING...
LOADING...
이 특허에 인용된 특허 (252)
Kawasaki, Somei; Goden, Tatsuhito, Active matrix type display apparatus and driving method thereof.
Nakatsuka Kimihiro,JPX, Apparatus for determining image processing parameter, method of the same, and computer program product for realizing the method.
Barrett Terence W. (Vienna VA), Automata networks and methods for obtaining optimized dynamically reconfigurable computational architectures and control.
Sang ; Jr. Henry W. (Cupertio CA) Tahn Whei-Tsu H. (Sunnyvale CA) Zhang Xiao B. (Foster City CA), Automated method for creating templates in a forms recognition and processing system.
McElroy, John F.; Chorvat, Robert J., Cannabinoid receptor antagonists/inverse agonists useful for treating metabolic disorders, including obesity and diabetes.
Nishimura Kazuyuki (Ichikawa JPX) Sato Shinichi (Yokohama JPX), Color picture processing apparatus for reproducing a color picture having a smoothly changed gradation.
Suzuki,Masahiro; Tamune,Michihiro; Chen,Zhe Hong; Juen,Masahiro, Digital camera, storage medium for image signal processing, carrier wave and electronic camera.
Rowe Edward R. ; Priyadarshan Eswar ; Anderson Kenneth S. ; Al-Shamma Nabeel A. ; Taft Edward A. ; McQuarrie Elizabeth M. ; Cohn Richard, Displaying electronic documents with substitute fonts.
Nagatsuka,Tetsuro; Miyachi,Tatsuo; Shimada,Atsuo; Takeya,Kazutoshi; Kemmochi,Eiji; Nakajima,Akiko; Yamasaki,Makoto; Fujita,Katsuhiko, Document classification system and method for classifying a document according to contents of the document.
Borrey Roland G. (19251 Canyon Dr. Villa Park CA 92667) Borrey Daniel G. (19251 Canyon Dr. Villa Park CA 92667), Document identification by characteristics matching.
Clark ; Jr. Louis George (St. Charles MO) Gummow ; Jr. Donald Romaine (O\Fallon MO) Vanacht Marc (St. Louis MO), Hand-held GUI PDA with GPS/DGPS receiver for collecting agronomic and GPS position data.
LeBrun Thomas Q. (Dallas TX) Cage Kerry (Carrollton TX) Arnold Dennis D. (Carrollton TX), Image based document processing and information management system and apparatus.
Naofumi Yamamoto JP; Haruko Kawakami JP; Gururaj Rao JP, Image processing apparatus for discriminating image field of original document plural times and method therefor.
Appelt, Douglas E.; Arnold, James Frederick; Bear, John S.; Hobbs, Jerry Robert; Israel, David J.; Kameyama, Megumi; Martin, David L.; Myers, Karen Louise; Ravichandran, Gopalan; Stickel, Mark Edward, Information retrieval by natural language querying.
Walnut David Francis ; Berenstein Carlos Alberto ; Liu K. J. Ray ; Rashid-Farrokhi Farrokh, Method and apparatus for processing data from a tomographic imaging system.
Withers,William Douglas, Method and apparatus for recognizing a digitized form, extracting information from a filled-in form, and generating a corrected filled-in form.
Guberman Shelja A. (Moscow RUX) Lossev Ilia (Moscow RUX) Pashintsev Alexander V. (Moscow RUX), Method and apparatus for recognizing cursive writing from sequential input information.
Guberman Shelja A. (Moscow RUX) Lossev Ilia (Moscow RUX) Pashintsev Alexander V. (Moscow RUX), Method and apparatus for recognizing cursive writing from sequential input information.
Polyakov Vladislav G. (Moscow RUX) Ryleev Mikhail A. (Moscow RUX), Method and apparatus for representing image data using polynomial approximation method and iterative transformation-repa.
Green, Stephen J.; Lamere, Paul B.; Alexander, Jeffrey L.; Haberl, Karl R., Method and apparatus for searching and resource discovery in a distributed enterprise system.
Winkelman Kurt-Helfried (Kiel DEX), Method and apparatus for the automatic analysis of density range, color cast, and gradation of image originals on the Ba.
Berman, Arie; Vlahos, Paul; Dadourian, Arpag, Method and apparatus for the automatic generation of subject to background transition area boundary lines and subject shadow retention.
Verstraelen,Boudewijn Joseph Angelus; Verstraelen,Sebastiaan Paul, Method and apparatus for visualization of biological structures with use of 3D position information from segmentation results.
Tischler, Karl M., Method arrangement and computer software for the printing of a separator sheet by means of an electrophotographic printer or copier.
Kurosu Yasuo (Yokosuka JPX) Yokoyama Yoshihiro (Yokohama JPX) Nishikawa Kenichi (Yokohama JPX) Masuzaki Hidefumi (Hadano JPX) Fujinawa Masaaki (Tokyo JPX), Method for determining the amount of skew of image, method for correcting the same, and image data processing system.
Henderson Todd R. ; Spaulding Kevin E. ; Couwenhoven Douglas W., Method for segmenting a digital image into a foreground region and a key color region.
Kohchi Tsukasa JP, Method of and system for extracting predetermined elements from input document based upon model which is adaptively modified according to variable amount in the input document.
Beaulieu Dennis N. (Churchville NY) Compton John T. (LeRoy NY) Wojtanik Eugene R. (Plano TX), Method of calibration of image scanner signal processing circuits.
Dumais Susan T. ; Heckerman David ; Horvitz Eric ; Platt John Carlton ; Sahami Mehran, Methods and apparatus for classifying text and for building a text classifier.
Michimoto Yasuyuki,JPX ; Onda Katsumasa,JPX ; Nishizawa Masato,JPX, Object detecting apparatus in which the position of a planar object is estimated by using hough transform.
Ellis, Stephen M.; Kennedy, Michael J.; Kurani, Ashish Bhoopen; Lowry, Melissa; Meyyappan, Uma; Sahni, Bipin; Stroke, Nikolai, System and method for a mobile wallet.
Woolf,Susan D.; Baird,Andrew; Jiang,Sheng; Beezer,John L.; Rubin,Darryl E., System and method for annotating an electronic document independently of its content.
Vazquez, Nicolas; Kodosky, Jeffrey L.; Kudukoli, Ram; Schultz, Kevin L.; Nair, Dinesh; Caltagirone, Christophe, System and method for automatically generating a graphical program to perform an image processing algorithm.
Emerson,Geoffrey A.; Moon,Rodney G.; Rector,Gerald C.; Stokes,Raymond F.; Sutton,Andrew H., System and method of sorting document images based on image quality.
Heidenreich,James R.; Higgins,Linda S., System and method to customize the facilitation of development of user thinking about and documenting of an arbitrary problem.
Sampath, Meera; Nichols, Stephen J.; Richenderfer, Elizabeth A., Systems and methods for automated image quality based diagnostics and remediation of document processing systems.
Ferlitsch,Andrew Rodney; DeVore,Darwin Alan, Systems and methods for manipulating electronic information using a three-dimensional iconic representation.
Roach, John J.; Nepomniachtchi, Grisha; Couch, Robert; Avergun, Mikhail, Systems and methods for obtaining financial offers using mobile image capture.
Gorski, Nikolai D.; Semenov, Andrey V.; Anisimov, Valery; Maksimov, Sergey K.; Sashov, Sergey N., Systems and methods for recognizing information in objects using a mobile device.
Borrey, Roland G.; Schmidtler, Mauritius A. R.; Taylor, Robert A.; Fechter, Joel S.; Asuri, Hari S., Systems and methods of accessing random access cache for rescanning.
Schmidtler, Mauritius A. R.; Borrey, Roland G.; Amtrup, Jan W.; Thompson, Stephen Michael, Systems, methods and computer program products for determining document validity.
Schmidtler, Mauritius A. R.; Borrey, Roland G.; Amtrup, Jan W.; Thompson, Stephen Michael, Systems, methods and computer program products for determining document validity.
Schmidtler, Mauritius A. R.; Borrey, Roland G.; Amtrup, Jan W.; Thompson, Stephen Michael, Systems, methods, and computer program products for determining document validity.
Ma, Jiyong; Thompson, Stephen Michael; Amtrup, Jan W., Content-based detection and three dimensional geometric reconstruction of objects in image and video data.
Macciola, Anthony; Ma, Jiyong; Shustorovich, Alexander; Thrasher, Christopher; Amtrup, Jan W., Determining distance between an object and a capture device based on captured image data.
Thrasher, Christopher W.; Shustorovich, Alexander; Thompson, Stephen Michael; Amtrup, Jan W.; Macciola, Anthony, Iterative recognition-guided thresholding and data extraction.
Shustorovich, Alexander; Thrasher, Christopher W.; Ma, Jiyong; Macciola, Anthony; Amtrup, Jan W., Mobile document detection and orientation based on reference object characteristics.
Amtrup, Jan W.; Macciola, Anthony; Thompson, Steve; Ma, Jiyong; Shustorovich, Alexander; Thrasher, Christopher W., Systems and methods for classifying objects in digital images captured using mobile devices.
Amtrup, Jan W.; Macciola, Anthony; Thompson, Steve; Ma, Jiyong; Shustorovich, Alexander; Thrasher, Christopher W., Systems and methods for classifying objects in digital images captured using mobile devices.
Macciola, Anthony; Amtrup, Jan W.; Ma, Jiyong; Shustorovich, Alexander; Thrasher, Christopher W.; Thompson, Stephen Michael, Systems and methods for classifying objects in digital images captured using mobile devices.
Thrasher, Christopher W.; Shustorovich, Alexander; Thompson, Stephen Michael; Amtrup, Jan W.; Macciola, Anthony; Borrey, Roland G.; Schmidtler, Mauritius A. R.; Taylor, Robert A.; Fechter, Joel S.; Asuri, Hari S., Systems and methods of processing scanned data.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.