EZEQUIEL, Ruiz Rodriguez (Calle Aquilino de la Guardia n.8, IGRA BuildingPanama, 7, PA)
| CLAIMS 1. Apparatus (1) for image data recording and reproducing, said apparatus (1) comprising: - an imaging system (10) for capturing an image; - a signal processor (20) coupled to said imaging system (10) for processing the captured image as a digital image file; - an audio system (30) coupled to said signal processor (20) for acquiring at least one speech annotation apt to be associated with said digital image file; - a speech recognition unit (40) for recognizing said at least one speech annotation and converting the speech annotation into text data, said speech recognition unit (40) being associated to the signal processor (20) for generating metadata using the text data and adding the generated metadata to the digital image file, characterized in that said speech recognition unit (40) comprises a plurality of subsets (41) of words, each subset (41) having a limited number of words, in order to recognize and convert into text speech annotations acquired from a corresponding plurality of languages. 2. Apparatus (1) according to claim 1, characterized in that each subset (41) of words comprises a relative translation in a determined language only of a limited number of words, choosing and memorizing them at the manufacturer site only between the words more frequently used for being associated to a determined image. 3. Apparatus (1) according to one or more of the preceding claims, characterized in that said speech recognition unit (40) is associated to activating means (42) that allow the user to activate the speech recognition unit (40) in order to convert the speech annotation into text data. 4. Apparatus (1) according to claim 1, characterized in that said apparatus (1) comprises a memory (50) coupled to the signal processor (20) for storing the digital image file and/or the speech annotation and/or the speech annotation converted into text data. 5. Apparatus (1) according to claim 1, characterized in that said apparatus (1) comprises a display (60) associated to the signal processor (20). 6. Apparatus (1) according to claim 5, characterized in that said display (60) comprises an On Screen Display (OSD) system apt to choose both a language between a plurality of languages for displaying the operation of the apparatus (1), both one of said subsets (41) of a limited number of words. 7. Apparatus (1) according to claim 1, characterized in that said apparatus (1) comprises input means for generating metadata using said text data and coding them according to a determined international standard. 8. Method for image data recording and reproducing comprising the following steps: - capturing an image by means of an apparatus (1) comprising an imaging system (10) (step 100); - processing the captured image as a digital image file through a signal processor (20) coupled to said imaging system (10) (step 110); - recording at least one speech annotation, in particular in a memory (50), by means of an audio system (30) coupled to said signal processor (20), said speech annotation being apt to be associated with said digital image file (step 120); - recognising said speech annotation and converting at least one speech annotation into text data by means of a speech recognition unit (40) associated to the signal processor (20) (step 130); - generating metadata using the text data and adding the generated metadata to the digital image file (step 140), said method being characterized by the fact that said step (130) of recognising and converting the at least one speech annotation into text data is performed by means of a step (150) of storing at the manufacturer site a plurality of subsets (41) of a limited number of words in said speech recognition unit (40) and using them for recognising and converting into text the speech annotations acquired from a corresponding plurality of languages. 9. Method according to claim 8, characterized by comprising a step (160) of actuating activating means (42) of the speech recognition unit (40), said activating means (42) allowing the user to activate the speech recognition unit (40) in order to convert the speech annotation into text data. 10. Method according to claim 9, characterized in that said step (160) of actuating said activating means (42) is performed after the step (110) of processing the captured image. 11. Method according to claim 9, characterized in that said step (160) of actuating said activating means (42) is performed before said step (100) of capturing an image. 12. Method according to claim 11, characterized by comprising a step of characterized in that said step (160) of actuating said activating means (42) is preceded by a step (161) of generating an image file having a conventional filename. 13. Method according to claim 8, characterized by comprising a step (180) of choosing both a language between a plurality of languages for displaying the operation of the apparatus (1), both one of said subsets (41) of a limited number of words by means of an On Screen Display (OSD) system comprised in said display (60). 14. Method according to claim 13, characterized in that said step (180) of choosing a language and a subset of a limited number of words is performed before said step (100) of capturing an image. 15. Method according to claim 13, characterized in that said step (180) of choosing a language and a subset of words is performed after said step (160) of actuating said activating means (42). 16. A computer program product adapted to perform the method of any one of claims 8 to 15. 17. A computer readable storage medium/data carrier used in association with the computer program product of claim 16. |
19 Rue Eugene Ruppert, L-2453 Luxembourg
APPARATUS FOR IMAGE DATA RECORDING REPRODUCING, AND METHOD THEREOF
DESCRIPTION
The present invention relates to an apparatus for image data recording and reproducing according to the preamble of claim 1.
The present invention also relates to a method for image data recording and reproducing, in particular for automatically creating metadata for digital image file.
Apparatuses and methods for image data recording and reproducing are well known at the state of the art; in particular, said apparatuses comprise digital cameras apt to capture images and store them on a digital medium. It should be noted that, in the present text, the words "apparatus" and/or "camera" can be used in order to relate to digital still cameras, digital video cameras, mobile telephones having integrated digital cameras, and the like.
With the apparatuses known at the state of the art, between the time an image is captured and the time it is printed or otherwise displayed, the user (that usually is also the photographer) may forget or lose access to information related to the image, such as the time at which it was captured and/or the location in which it was captured and/or the persons depicted in it.
Some digital cameras allow text, such as text representing the date and the time on which an image was captured, to be associated with a photograph; this text is typically created by the camera and superimposed on the image at a predetermined location and in a predetermined format.
Said text only contains a small amount of information, and it conveys little or no useful information to the user of the digital camera that will help him for distinguishing one image from another. 10 057747
The same problem arise with the default file naming scheme, that is used in digital cameras in order to identify and track digital image files; in fact, said default file naming scheme only employs:
- a combination of letters (for example: "DSC", "IMG", "PICT", "DSCN", etc.) for indicating the type of digital image file,
- a sequence number (for example: "001", "002", etc.) appended to said indicator to identify a digital image from another, and
- a file type extension (for example, ".TEF", "JPG", etc.) appended after the sequence number in order to identify the type of the file.
Therefore, also with the default file naming scheme the user has little or no useful information about the contents of a particular image file. In fact, the user must open and view each image file to determine if said image file contains a desired image of a person, of a place, and so on. Eventually the user can edit the naming scheme with the help of a computer, but this possibility is practically of no use when done some time after having recorded the images.
Document No. EP 1876596 relates to an apparatus for image data recording and reproducing, said apparatus comprising:
- a signal processor for capturing images, processing the captured images to generate image data, and generating an image file comprising the image data;
- a speech recognition unit for recognizing speech and converting the speech into text data; and
- a controller for generating metadata using the text data and adding the generated metadata to the image file.
According to what is described in document No. EP1876596, the metadata to be included in the image file are generated by using the text data converted by the speech recognition unit, so that it is possible to add reliable metadata (such as, for example, shooting locations or persons being displayed in the image) to the image file just after the capture of the image and/or while reviewing the image file.
In addition, the name of the folder in which the image file is to be stored is generated based on the text data that is converted by using speech recognition, so that it is possible to classify the image files at a time when the image is captured. 0 057747
However, it has been observed that even the apparatus described in document No. EP 1876596 suffers from some drawbacks, since it is adapted to recognize and convert only one predetermined language.
In fact, the programs and software for recognizing speech and converting the speech into text data are expensive, large and very big in size, usually in the order of many megabyte (or a gigabyte) for each language that has to be recognized and converted into text; therefore, said programs and software cannot be utilized in a image data recording and reproducing apparatus without making a choice of only one predetermined language for each apparatus.
This implies that each apparatus realized in accordance with the teachings of the document No. EP 1876596 needs to comprise a program apt to recognize and convert into text only one language.
This necessarily means that the apparatus cannot be versatile and eclectic, since it is necessary for the user to have an apparatus comprising a specific program for recognizing his own language, in order to convert said language into text.
This also means that the producer of the apparatus is not able to produce a single product that can be sold in different countries, where the users speak different languages. The consequence of that are an increased number of models for the same product and an increase of cost of production
In this frame, it is the main object of the present invention to overcome the above-mentioned drawbacks by providing an apparatus and a method for image data recording and reproducing which allow to recognize and convert into text a plurality of languages.
It is a further object of the present invention to provide an apparatus and a method for image data recording and reproducing conceived in a manner to be versatile and eclectic.
It is a further object of the present invention to provide a single apparatus and method for image data recording and reproducing able to recognize and convert into text a plurality of different languages.
These objects are achieved by the present invention through an apparatus and a method for image data recording and reproducing, incorporating the features set out in the appended claims, which are intended as an integral part of the present description.
Further objects, features and advantages of the present invention will become apparent from the following detailed description and from the annexed drawings, which are supplied by way of non-limiting example, wherein:
- Fig. 1 is a block diagram of an apparatus for image data recording and reproducing, in particular a digital camera, according to the present invention;
- Fig. 2 is a block diagram illustrating a first embodiment of a method for image data recording and reproducing according to the present invention;
- Fig. 3 is a block diagram illustrating a second embodiment of a method for image data recording and reproducing according to the present invention.
In Fig. 1, reference numeral 1 designates as a whole an apparatus for image data recording and reproducing, according to the present invention.
The apparatus 1 for image data recording and reproducing according to the exemplary embodiment of the present invention may be a digital still camera, a digital video camera, a mobile telephone having an integrated or associated digital camera, and the like.
Said apparatus 1 comprises:
- an imaging system 10 for capturing an image;
- a signal processor 20 coupled to said imaging system 10 for processing the captured image as a digital image file;
- an audio system 30 coupled to said signal processor 20 for acquiring at least one speech annotation apt to be associated with said digital image file;
- a speech recognition unit 40 for recognizing said at least one speech annotation and converting the speech annotation into text data, said speech recognition unit 40 being associated to the signal processor 20 for generating metadata using the text data and adding the generated metadata to the digital image file. Said imaging system 10 may comprise a lens/shutter assembly 11, which directs and focuses light onto a sensor 12 for capturing images of a subject; in particular, said sensor 12 can comprise one or more CCD (Charge Coupled
Device) or one or more CMOS (Complementary Metal-Oxide Semiconductor). Therefore, said signal processor 20 controls the operations of the lens/shutter assembly 11 and processes image information received from the sensor 12 for generating an image file containing the captured image in a digital format.
When the image file includes still image data, the digital image file may be in Joint Photographic Experts Group (JPEG) or Tag Image File Format (TIFF) format; when the image file includes moving image data, the digital image file may be in Moving Picture Experts Group (MPEG) format or other video formats known on the state of the art.
Moreover, as known at the state of the art, each of the image files includes an area for storing the image data and an area for storing information regarding the image. This is done in accordance to international standards. In fact there are some entities that have defined how to add metadata to image files, like:
- IPTC Information Interchange Model ΓΓΜ (International Press Telecommunications Council),
- IPTC Core Schema for XMP, · XMP - Extensible Metadata Platform (an Adobe standard),
- EXTF - Exchangeable image file format, Maintained by CIPA (Camera & Imaging Products Association) and published by JEITA (Japan Electronics and Information Technology Industries Association),
- Dublin Core (Dublin Core Metadata Initiative -DCMI),
- PLUS (Picture Licensing Universal System).
As it can be seen from Fig. 1, the audio system 30 preferably comprises a microphone 31 for allowing a user to record a short audio or voice annotation, record sound for digital video recording, input voice commands, and the like. Said audio system 30 may also comprise a speaker 32.
In accordance with the present invention, said speech recognition unit 40 comprises a plurality of subsets 41 of words, each subset 41 having a limited number of words, in order to recognize and convert into text speech annotations acquired from a corresponding plurality of languages.
In particular, each subset 41 of words does not comprise a complete dictionary of words of a specific language, but each subset 41 of words comprises a relative translation in a determined language only of a limited number of words, choosing and memorizing them at the manufacturer site only between the words more frequently used for being associated to a determined image.
In particular, said plurality of words may comprise:
- terms indicating a celebration and/or a recurrence and/or a festivity (such as, for example: "Party", "Holiday", "Baptism", "Marriage", "Birthday", "Christmas", "Easter", etc.);
- terms indicating a geographic place (such as, for example: "Sea", "Desert", "Hill", "Mountain", "Lake", etc.);
- terms indicating countries all around the world (such as "Germany", "France", "Italy", "The United States of America", "Japan", "China", "Korea" etc.) and the major cities in these countries (such as "Frankfurt", "Munich", "Paris", "Rome", "Los Angeles", "Las Vegas", "Tokyo" "Shanghai", "Hong Kong", "Macau", "Seoul"), as well as famous buildings and pieces of fine art in these cities (such as "Chinese Wall", "Casino",
"Coliseum", "Tour Eiffel", etc.;
- terms indicating a season (such as: "Spring", "Summer", "Autumn", "Winter") and/or a month and/or a day of the week;
- terms indicating a number, in particular numbers from zero to nine in order to be able to compose each number;
- terms indicating a relationship with a person (such as, for example: "Brother", "Sister", "Father", "Mother ", "Grandfather", "Grandmother", "Uncle", "Aunt", "Cousin", "Friend", "Husband", "Wife");
- terms indicating the name of a person (such as, for example: "Carl", "Paul", "Peter", "John" , "Frank", "Robert", "Abbie", "Jane", "Mary", "Beth");
- terms indicating an animal (such as, for example: "Dog", "Cat", "Horse", "Bird") and/or a thing (such as, for example: "House", "Office", "Garden", "Church", "Cathedral", "Car" , "Bike").
This provision allows to obtain an apparatus and a method for image data recording and reproducing which allow to recognize and convert into text a plurality of languages, even if limited to a subset of words. It is clear that if the word that the user wants to associate to a certain image is not provided by the limited subset of words memorized and recognizable by the apparatus, this particular word can be edited manually by making use of one of the several tools known in the state of the art for writing words: keyboards, touch screen systems, etc.
In particular, the apparatus 1 and the method according to the present invention allows to recognize speech and to convert the speech into text data without the need of using a speech recognition unit 40 expensive, large and very big in size, usually in the order of many megabyte (or a gigabyte), for each language that has to be recognized and converted into text. Therefore, this solution can be implemented in consumer products like digital still cameras, digital video cameras, mobile telephones having integrated digital cameras, and the like, without charging these products with a cost that cannot accepted by the market.
It is therefore clear that said speech recognition unit 40 can be utilized in the apparatus 1 without making a choice at the manufacturer site of a predetermined language to be used, and that said speech recognition unit 40 allows to indicate one single apparatus 1 and method conceived in such a manner to be extremely versatile and eclectic.
Preferably, said speech recognition unit 40 is associated to activating means 42 that allow the user to activate the speech recognition unit 40 in order to convert the speech annotation into text data.
In particular, said activating means 42 can be actuated by the user before the image is captured and/or displayed; otherwise, said activating means 42 can be actuated by the user after the image is captured, in particular when said image is displayed. For example, said activating means 42 may comprise a button (not shown in the drawings) preferably positioned on an external surface of the apparatus 1.
The apparatus 1 comprises also a memory 50 coupled to the signal processor 20 for storing the digital image file and/or the speech annotation and/or the speech annotation converted into text data. Said memory 50 can comprise a Random Access Memory (RAM), a Read Only Memory (ROM), an Electrically Erasable Programmable Read Only Memory (EEPROM), or the like.
Moreover, the apparatus 1 further comprises a display 60 associated to the signal processor 20. As known, said display 60 can be used for a plurality of purposes, in particular:
- for displaying the image to be captured to the user; in this case the display 60 allows the user to center and focus the image, pose persons appearing in the image, and the like;
- for displaying a captured image, stored in the memory 50 as a digital image files;
- for displaying menus apt to convey information to the user,
- for selecting features of the apparatus 1 ;
- for controlling operation of the apparatus 1 , and the like.
In a preferred embodiment of the present invention, said display 60 comprises an On Screen Display (OSD) system apt to choose both a language between a plurality of languages for displaying the operation of the apparatus 1, both one of said subsets 41 of words.
As said before, it is clear that the apparatus 1 can comprise input means (not shown in Fig. 1) for generating metadata in a traditional manner and in accordance to international standards, i.e. producing text data for generating metadata to be added to the digital image file; for example, said input means may comprise a keyboard or a touch screen.
Figures 2 and 3 respectively relate to a first and to a second representation of a method for image data recording and reproducing according to the present invention.
In particular, said method comprises the following steps:
- storing (step 150) at the manufacturer site a plurality of subsets 41 of a limited number of words in said speech recognition unit 40 for recognising and converting into text speech annotations acquired from a corresponding plurality of languages;
- capturing an image by means of an apparatus 1 comprising an imaging system 1 (step 100); - processing the captured image as a digital image file through a signal processor 20 coupled to said imaging system 10 (step 110);
- recording at least one speech annotation, in particular in a memory 50, by means of an audio system 30 coupled to said signal processor 20, said at least one speech annotation being apt to be associated with said digital image file (step 120);
- recognising said at least one speech annotation and converting the speech annotation into text data by means of a speech recognition unit 40 associated to the signal processor 20 (step 130);
- generating metadata using the text data and adding the generated metadata to the digital image file (step 140).
According to the present invention, said step 130 of recognising and converting the speech annotation into text data is performed by making use of one of the plurality of subsets 41 of words stored in said speech recognition unit 40 for recognising and converting into text speech annotations acquired from a corresponding plurality of languages.
In Figs. 2 and 3, the line L indicates the fact that said step 150 of storing a plurality of subsets 41 of a limited number of words in said speech recognition unit 40 is accomplished at the manufacturer site.
In particular, the method according to the present invention is performed through the step 160 of actuating activating means 42 of the speech recognition unit 40, said activating means 42 allowing the user to activate the speech recognition unit 40 in order to convert the speech annotation into text data.
As can be seen in particular in Fig. 2, said step 160 of actuating said activating means 42 can be performed after the step 110 of processing the captured image, i.e. when said image is already recorded in a memory 50 of the apparatus 1. In this case, said step 160 can be preceded by a step 161 of generating an image file having a conventional filename. Moreover, in the case the user decides not to actuate said activating means 42, the apparatus 1 can perform the step 161 of generating an image file having a conventional filename.
Alternatively, as can be appreciated in particular from Fig. 3, said step 160 of actuating said activating means 42 can be performed before said step 100 of capturing an image.
Moreover, the method according to the present invention comprises the further step 180 of choosing both a language between a plurality of languages for displaying the operation of the apparatus 1, both one of said subsets 41 of words by means of an On Screen Display (OSD) system comprised in said display 60.
Preferably, with reference to the method of Fig. 2, said step 180 of choosing a language and a subset of words is performed before the step 100 of capturing an image; with reference to the method of Fig. 3, said step 180 of choosing a language and a subset of words is performed after the step 160 of actuating said activating means 42.
Moreover, it must be noticed that the present invention can also be embodied as computer readable metadata on a computer readable storage medium/data. The computer readable storage medium/data is any data storage device that can store data, which can be thereafter read by a computer system. Examples of the computer readable recording medium include Electrically Erasable Programmable Read Only Memory (EEPROM), random-access memory (RAM), CD-ROMs, magnetic tapes, floppy disks, optical data storage devices, and the like.
The advantages offered by an apparatus and a method for image data recording and reproducing according to the present invention are apparent from the above description.
In particular, such advantages are due to the fact that the provision of a speech recognition unit 40 comprising a plurality of subsets 41 of words allows to recognize and convert into text a plurality of languages; in particular, this can be done without the need of using a speech recognition unit 40 expensive, large and very big in size, usually in the order of many megabyte (or a gigabyte), for each language that has to be recognized and converted into text.
It is therefore clear that clear that said speech recognition unit 40 can be utilized in the apparatus 1 without making a choice of a predetermined language that has to be recognized and converted into text, therefore, the particular realization of the speech recognition unit 40 according to the present invention allows to indicate an apparatus 1 and a method conceived in such a manner to be versatile and eclectic.
The apparatus and method described herein by way of example may be subject to many possible variations without departing from the novelty spirit of the inventive idea; it is also clear that in the practical implementation of the invention the illustrated details may have different devices or be replaced with other technically equivalent elements, as well as providing different sequences of steps.
For instance with respect to the embodiments shown in Fig. 2 and 3, the step 180 of choosing the language can be followed immediately from the step 160 of actuating the activating means, making it manually be the user or automatically by the apparatus 1, as the consequence of having chosen both the language for displaying the operation of the apparatus 1 and one of said subsets 41 of words.
It can therefore be easily understood that the present invention is not limited to the above-described apparatus and method, but may be subject to many modifications, improvements or replacements of equivalent parts and elements without departing from the . inventive idea, as clearly specified in the following claims.
* * * * * * * * *
Next Patent: SWITCHING ARRANGEMENT FOR AN ANTENNA DEVICE