FORM 2
THE PATENTS ACT, 1970
(39 of 1970)
&
THE PATENT RULES, 2003
COMPLETE SPECIFICATION
(See Section 10 and Rule 13)
Title of application:
METHOD AND SYSTEM FOR DIFFERENTIATING PLURALITY OF SCRIPTS OF TEXT IN BROADCAST VIDEO STREAM
Applicant:
TATA Consultancy Services Limited A company Incorporated in India under The Companies Act, 1956
Having address:
Nirmal Building, 9th Floor,
Nariman Point, Mumbai 400021,
Maharashtra, India
The following specification particularly describes the application and the manner in which it is to be performed.

FIELD OF THE APPLICATION
The present application relates to broadcasting and telecommunications. The application relates to a method and system for differentiating plurality of scripts of text in broadcast video stream. Particularly the application enables a cost effective method and system for differentiating at least first set of language scripts from at least second set of the language script text in broadcast video stream.
BACKGROUND OF THE APPLICATION
In the recent past, multilingual broadcasting and telecommunication technologies have gained wider popularity in spite of language diversity of any given geographical location. In today's scenario, interactivity with various communication devices particularly broadcasting video devices such as television is highly required for enhanced user experience, irrespective of the native language.
Considering the Indian scenario, wherein more that 15-16 major regional languages are used for communication. There are number of television channels are available in most of the regional languages which constitutes almost 90% of the total channels available. The regional television channels broadcasts the video streams which may be a text rich show such as news. The text is generally in the channel specific regional language, however often such text may include texts in either English or in some other regional language.
Identification of script in the broadcast stream of video and differentiations thereof over other one or more scripts in the said broadcast stream is critical even though there is availability of text detection tools. Language differentiation and recognition may further be utilized in broadcast video's optical character recognition (OCR) and other viewer oriented applications.

Lots of efforts have been made to devise a solution for differentiation, segregation and recognition of the language of text in broadcast video stream for television.
in order to achieve differentiation, segregation and recognition of the language of text in broadcast video streams for television a method and system is required to differentiate, segregate and recognize the regional language scripts mixed with some English text in a streamed Indian television broadcast video.
However, the existing method and systems are not capable of providing automatic differentiation, segregation and recognition of the language of text in broadcast video streams for television. The existing methods and systems particularly are not capable of providing segregating regional language scripts from the English text in a broadcasted video stream for television. Some of them known to us are as follows:
US6005986 to Ratner teaches about a method of identifying the script and orientation of a document image. The patent does not teach about identifying the script in video frame of the television transmission. The patent does not disclose the use of the Matra/ Sirorekha to identify the Indian scripts.
US5444797 to Spitz et al. teaches about an automatic script determining apparatus automatically determines the gross script-type of the text image of a document. The patent does not disclose the use of the Matra/ Sirorekha to identify the Indian scripts.
US5425110 to Spitz teaches about an automatic language determining apparatus automatically determines the particular Asian language of the text image of a document when the gross script-type is known to be, or is determined to be, an Asian script-type. The patent does not teach about segregating the English text language from the other non English text language such as Indian. The patent does not disclose the use of the Matra/ Sirorekha to identify the Indian scripts.

US5062143 to Schmitt teaches about a mechanism for examining a body of text and identifying its language compares successive trigrams.into which the body of text is parsed with a library of sets of trigrams. The patent teaches about identified the language by parsing body of text is with a library of key sets. The patent does not disclose the use of the Matra/ Sirorekha to identify the Indian scripts.
US5375176 to Spitz teaches about a method and apparatus for automatic character type classification of European script documents. The patent disclose about the character type classification which is specific to European script documents.
US5377280 to Nakayama teaches about a method and apparatus for automatic language determination of European script documents. The patent disclose about the language determination which is specific to European script documents.
Ghosh et al, in "Multimodal Indexing of Multilingual News Video" examines the problems associated with automatic analysis of news telecasts that are more severe in a country like India, where there are many national and regional language channels, besides English. Ghosh et al. discloses the use of speech to separate the text of the language.
Sun et al. in "Effective text extraction and recognition for WWW images" proposes a new text extraction and recognition algorithm, wherein the character strokes in the image are first extracted by color clustering and connected component analysis. Sun et al. does not identify the Indian language from English or vice versa.
Liu et al. in "Extracting individual features from moments for Chinese writer identification" teaches about a moment-based feature method to identify Chinese writers in which normalized individual features are derived from geometric

moments of character images. Liu et al. addresses about the write identification problem.
Yousefi et al. in "Recognition of Arabic Characters" teaches about a statistical approach for the recognition of Arabic characters. Yousefi et al. addresses a method for Arabic optical character recognition.
The above mentioned prior arts fail to disclose an efficient and economic method and system for differentiation, segregation and recognition of the language of text in broadcast video stream for the television. The prior art also fail to disclose about segregating regional language scripts from the English text in a transmitted television broadcast video stream.
Thus, in the fight of the above mentioned background art, it is evident that, there is a need for such a solution that can provide a cost effective method and system for differentiation, segregation and recognition of the scripts of text in broadcast video stream for the television. There is also a need for such a solution that enables a cost effective method and system for segregating regional language scripts from the English text in a transmitted television broadcast video stream.
OBJECTS OF THE APPLICATION
The primary object of the present application is to provide a method and system for differentiating plurality of scripts of text in broadcast video stream.
Another object of the application is to enable a cost effective method and system for differentiating regional language scripts from the English text in broadcast video stream.

Another object of the application is to provide a method and system differentiating regional language scripts from the English text in broadcast video stream using connected component analysis based clustering.
SUMMARY OF THE APPLICATION
Before the present methods, systems, and hardware enablement are described, it is to be understood that this application in not limited to the particular systems, and methodologies described, as there can be multiple possible embodiments of the present application which are not expressly illustrated in the present disclosure. It is also to be understood that the terminology used in the description is for the purpose of describing the particular versions or embodiments only, and is not intended to limit the scope of the present application which will be limited only by the appended claims.
The present application provides a method and system for differentiating plurality of scripts of text in broadcast video stream.
in one embodiment of the application a cost effective method and system is provided for differentiating regional language scripts from the English text in broadcast video stream,
The application provides a method and system for differentiating regional language scripts from the English text in broadcast video stream using connected component analysis based clustering.
In an embodiment of the application a method and system is provided for differentiating plurality of scripts of text in broadcast video stream. The name of the broadcast video streaming channel is recognized. The method and system identifies the major language script which used in the above said broadcast video streaming channel which is other than any Latin. Anglo-Saxon and European

language script such as English. The text regions which are region of interest (Rol) are identified in the video frame of the said broadcast video streaming channel. The connected components in Rol of the video frame of the said broadcast video streaming channel are obtained and further they are clustered based on their width using k-Means. It is checked if the cluster contains bigger characters and accordingly based on the detection of the language script of the text regional or any Latin, Anglo-Saxon and European language script such as English OCR implemented.
The above said method and system are preferably a method and system for differentiating plurality of scripts of text in broadcast video stream but also can be used for many other applications.
BRIEF DESCRIPTION OF DRAWINGS
The foregoing summary, as well as the following detailed description of preferred embodiments, are better understood when read in conjunction with the appended drawings. For the purpose of illustrating the application, there is shown in the drawings exemplary constructions of the application; however, the application is not limited to the specific methods and system disclosed. In the drawings:
Figure 1 shows flow diagram of the process for differentiating plurality of scripts of text in broadcast video stream.
DETAILED DESCRIPTION OF THE APPLICATION
Some embodiments of this application, illustrating all its features, will now be discussed in detail.
The words "comprising," "having," "containing," and "including," and other forms thereof, are intended to be equivalent in meaning and be open ended in that an

item or items following any one of these words is not meant to be an exhaustive listing of such item or items, or meant to be limited to only the listed item or items.
It must also be noted that as used herein and in the appended claims, the singular forms "a," "an," and "the" include plural references unless the context clearly dictates otherwise. Although any systems and methods similar or equivalent to those described herein can be used in the practice or testing of embodiments of the present application, the preferred, systems and methods are now described.
The disclosed embodiments are merely exemplary of the application, which may be embodied in various forms.
The present application provides a method for differentiating plurality of scripts of text in broadcast video stream, the method comprising of:
a. applying connected component analysis on the at least one region of
interest (Rol) of at least one frame of the broadcast video stream;
b. obtaining plurality of connected component in the said region of
interest (Rol) of the said frame;
c. clustering each of the obtained connected component according to
width value thereof using k-Means;
d. determining a compactness coefficient associated with each of the
connected component; and
e. segregating each of the connected component in the said region of
interest (Rol) into corresponding language cluster based on the
compactness coefficient thereof.
The present application provides a system for differentiating plurality of scripts of text in broadcast video stream, the system comprising of:

a. a plurality of display devices communicatively coupled with at least
one network server and adapted to display broadcast video stream;
b. a optical character recognition engine adapted to recognize optical
character of at least one frame of the broadcast video stream: and
c. a network server adapted to host at least one regional language optical
character recognition.
Referring to Figure 1 is a flow diagram of the process for differentiating plurality of scripts of text in broadcast video stream.
The process starts at the step 102, the channel name is recognized. At the step 104, the major language used in that channel is found which is other than English. At the step 106, the text regions which are region of interest (Rol) are found in the video frame. At the step 108, the connected components in Rol are obtained. At the step 110, the connected components are clustered based en their width using k-Means. At the step 112, it is checked if the cluster contains bigger characters? At the step 114, the regional optical character recognition (OCR) technique is implemented. The process ends at the step 116, the English optical character recognition (OCR) technique is implemented.
In one of the embodiment of the present application, a method and system is provided for differentiating plurality of scripts of text in broadcast video stream. The application enables a cost effective method and system for differentiating regional language scripts from any Latin, Anglo-Saxon and European language script such as English text in broadcast video stream. Further, the application enables a method and system for differentiating regional language scripts from any Latin, Anglo-Saxon and European language script such as English text in broadcast video stream using connected component analysis based clustering. The broadcast video streaming channel's name is determined and recognized using any of the known techniques, such as by identifying the channel logo. Though, the broadcast video streaming channel information may be determined from the

website of the corresponding channel. The television broadcast video streaming channel may contain any Latin, Anglo-Saxon and European language script such as English or regional language. The method and system further identifies the major language script which is used in the above mentioned broadcast video streaming channel which is other than any Latin, Anglo-Saxon and European language script such as English. The present application is employed to separate any Latin, Anglo-Saxon and European language script such as English texts from that regional language text of the said broadcast video stream for the television. The video frames of the said channel transmission are utilized to identify the text regions which are region of interest (Rol) in the said video frame of the said broadcast video streaming channel. The regions containing text in that video frame may be obtained using any of the know techniques available in the prior art.
In one of the specific embodiment of the present application, connected component analysis is applied on each region containing text. The connected components in Rol of the said video frame of the said broadcast video streaming channel are obtained. The obtained connected components in Rol of the said video frame of the said broadcast video streaming channel are then clustered based on their width using k-Means. Since the letters in Indian language scripts are connected by ascender such as Siro rekha or Matra, the connected component for Indian languages will have more width in compare to the any Latin, Anglo-Saxon and European language script such as English. The K-means clustering is applied on the available connected components obtained from the Rol of the said video frame of the said broadcast video streaming channel, wherein the K-means is considered to be k=2. The K-means clustering results in two separate and clear cluster with one representing the Latin, Anglo-Saxon and European language script such as English language with loser component width and the other one representing the Indian language characters with broader width. Further, it is checked if the cluster contains bigger characters width and accordingly based on the detection of the language of the text, regional or any Latin. Anglo-Saxon and

European language script such as English optical character recognition technique is implemented.
In one of the implementation of the present application, the optical character recognition (OCR) is used to recognize the required text after the script separation. The regional language OCR is available on the server and the Latin, Anglo-Saxon and European language script such as English OCR is available at the client side. Further, based on the major language of the channel as detected by the channel logo, the required OCR engine is downloaded to the client side.
The methodology and techniques described with respect to the exemplary embodiments can be performed using a machine or other computing device within which a set of instructions, when executed, may cause the machine to perform any one or more of the methodologies discussed above. In some embodiments, the machine operates as a standalone device. In some embodiments, the machine may be connected (e.g., using a network) to other machines. In a networked deployment, the machine may operate in the capacity of a server or a client user machine in a server-client user network environment, or as a peer machine in a peer-to-peer (or distributed) network environment.
The machine may comprise a server computer, a client user computer, a personal computer (PC), a tablet PC, a laptop computer, a desktop computer, a control system, a network router, switch or bridge, or any machine capable of executing a set of instructions (sequential or otherwise) that specify actions to be taken by that machine. Further, while a single machine is illustrated, the term "machine" shall also be taken to include any collection of machines that individually or jointly execute a set (or multiple sets) of instructions to perform any one or more of the methodologies discussed herein.
The machine may include a processor (e.g., a central processing unit (CPU), a graphics processing unit (GPU, or both), a main memory and a static memory,

which communicate with each other via a bus. The machine may further include a video display unit (e.g.. a liquid crystal displays (LCD), a flat panel, a solid state display, or a cathode ray tube (CRT)). The machine may include an input device (e.g., a keyboard) or touch-sensitive screen, a cursor control device (e.g., a mouse), a disk drive unit, a signal generation device (e.g., a speaker or remote control) and a network interface device.
The disk drive unit may include a machine-readable medium on which is stored one or more sets of instructions (e.g., software) embodying any one or more of the methodologies or functions described herein, including those methods illustrated above. The instructions may also reside, completely or at least partially ^ within the main memory, the static memory, and/or within the processor during execution thereof by the machine. The main memory and the processor also may constitute machine-readable media.
Dedicated hardware implementations including, but not limited to, application specific integrated circuits, programmable logic arrays and other hardware devices can likewise be constructed to implement the methods described herein. Applications that may include the apparatus and systems of various embodiments broadly include a variety of electronic and computer systems. Some embodiments implement functions in two or more specific interconnected hardware modules or devices with related control and data signals communicated between and through the modules, or as portions of an application-specific integrated circuit. Thus, the example system is applicable to software, firmware, and hardware implementations.
In accordance with various embodiments of the present disclosure, the methods described herein are intended for operation as software programs running on a computer processor. Furthermore, software implementations can include, but not limited to, distributed processing or component/object distributed processing,

parallel processing, or virtual machine processing can also be constructed to implement the methods described herein.
The present disclosure contemplates a machine readable medium containing instructions, or that which receives and executes instructions from a propagated signal so that a device connected to a network environment can send or receive voice, video or data, and to communicate over the network using the instructions. The instructions may further be transmitted or received over a network via the network interface device.
While the machine-readable medium can be a single medium, the term "machine-readable medium" should be taken to include a single medium or multiple media (e.g., a centralized or distributed database, and/or associated caches and servers) that store the one or more sets of instructions. The term "machine-readable medium" shall also be taken to include any medium that is capable of storing, encoding or carrying a set of instructions for execution by the machine and that cause the machine to perform any one or more of the methodologies of the present disclosure.
The term "machine-readable medium" shall accordingly be taken to include, but not be limited to: tangible media; solid-state memories such as a memory card or other package that houses one or more read-only (non-volatile) memories, random access memories, or other re-writable (volatile) memories; magneto-optical or optical medium such as a disk or tape; non-transitory mediums or other self-contained information archive or set of archives is considered a distribution medium equivalent to a tangible storage medium. Accordingly, the disclosure is considered to include any one or more of a machine-readable medium or a distribution medium, as listed herein and including art-recognized equivalents and successor media, in which the software implementations herein are stored.

The illustrations of arrangements described herein are intended to provide a general understanding of the structure of various embodiments, and they are not intended to serve as a complete description of all the elements and features of apparatus and systems that might make use of the structures described herein. Many other arrangements will be apparent to those of skill in the art upon reviewing the above description. Other arrangements may be utilized and derived therefrom, such that structural and logical substitutions and changes may be made without departing from the scope of this disclosure. Figures are also merely representational and may not be drawn to scale. Certain proportions thereof may be exaggerated, while others may be minimized. Accordingly, the specification and drawings are to be regarded in an illustrative rather than a restrictive sense.
The preceding description has been presented with reference to various embodiments. Persons skilled in the art and technology to which this application pertains will appreciate that alterations and changes in the described structures and methods of operation can be practiced without meaningfully departing from the principle, spirit and scope.

WE CLAIM:
1. A method for differentiating plurality of scripts of text in broadcast video stream, the method comprising of:
a. applying connected component analysis on the at least one region of
interest (Rol) of at least one frame of the broadcast video stream;
b. obtaining plurality of connected component in the said region of
interest (Rol) of the said frame;
c. clustering each of the obtained connected component according to
width value thereof using k-Means;
d. determining a compactness coefficient associated with each of the
connected component; and
e. segregating each of the connected component in the said region of
interest (Rol) into corresponding language cluster based on the
compactness coefficient thereof.
2. The method as claimed in claim 1, wherein the clustered connected components are identified based on their width, wherein the connected component for Indian language script are having more width compared to the Latin, Anglo-Saxon and European language script.
3. The method as claimed in claim 2, wherein the letters in Indian language scripts are connected by an ascender such as Siro rekha or Matra.
4. The method as claimed in claim 1, wherein the K-means is considered to be k=2.
5. The method as claimed in claim 1, wherein the regional language scripts are segregated from the Latin, Anglo-Saxon and European language script language text in the broadcast video streams.

6. The method as claimed in claim 1, wherein the video frames of the said broadcast video streaming channel are utilized to identify the text regions which are region of interest (Rol).
7. The method as claimed in claim 1, wherein the optical character recognition (OCR) is utilized to recognize the required text after the script separation based on the width of the clustered connected components in the said region of interest (Rol) of the said frame of the broadcast video stream of the television.
8. The method as claimed in claim 1, wherein the regional language OCR is available on the server and the Latin, Anglo-Saxon and European language script OCR is available at the client side.
9. The method as claimed in claim 1, wherein the required regional OCR engine is hosted on the client side.
10. A system for differentiating plurality of scripts of text in broadcast video stream, the system comprising of:
a. a plurality of display devices communicatively coupled with at least
one network server and adapted to display broadcast video stream:
b. a optical character recognition engine adapted to recognize optical
character of at least one frame of the broadcast video stream; and
c. a network server adapted to host at least one regional language optical
character recognition.
11. The system of claim 10, wherein the differentiating plurality of scripts of
text in broadcast video stream comprises utilizing the processor to:

a. apply connected component analysis on the at least one region of
interest (Rol) of at least one frame of the broadcast video stream;
b. obtain plurality of connected component in the said region of interest
(Rol) of the said frame;
c. cluster each of the obtained connected component according to width
value thereof using k-Means;
d. determine a compactness coefficient associated with each of the
connected component; and
e. segregate each of the connected component in the said region of
interest (Rol) into corresponding language cluster based on the
compactness coefficient thereof.