sobota, 7 maja 2011
The idea of designing an image-to-text translator originated from my personal experience of coming to a foreign country. I am an exchange student from Poland, who got a chance of spending a semester in Graphic Design course at University for the Creative Arts in Maidstone. From the first day I entered England I have been constantly struggling with managing my life far away from home, in a new environment, and most importantly, using a foreign language in my everyday life. I personally believe it is one of the most important experiences, which will influence my entire life and carrier as a designer. So far I have enjoyed every aspect of it, however I have also had a chance to experience how overwhelming it may be. It has sensitized me for the needs of people in similar situation, therefore I decided to come up with an idea which could help them to get used to new circumstances and overcome some of the difficulties they may find. I wish that, hopefully, one day we would all not be separated by invisible boundaries of a language we were born to speak anymore.
One of the factors which could help in achieving success for the Image-teller is creative management. Gathering a team of trained specialist would be inevitable step in implementation of the concept. Turning the idea of Image-teller into an application would require a long term cooperation of a designer, IT specialists, linguists and translators of different languages. As a graphic designer I am able to coordinate the work of different team members and make sure the application will meet with the needs of potential customers and design standards.
Researching all opportunities waiting for designers in Great Britain while working as a freelancer may be difficult. Because of lack of professional experience a help from a financial advisor on how to search for resources inevitable to start work would be crucial.
What would also be required is a business advice provided by a person or organization accustomed with british business market such as FinanceSouthEast.
In 2007 Google filed for a patent for recognizing text in images (http://www.wipo.int/pctdb/en/ia.jsp?IA=US2007072578), therefore a legal advice and explanation of software patents is a key element which will most probably strongly influence the way the idea can be executed. Any decisions referring to Google patent claim have not been made yet.
Researching all opportunities waiting for designers in Great Britain while working as a freelancer may be difficult. Because of lack of professional experience a help from a financial advisor on how to search for resources inevitable to start work would be crucial.
What would also be required is a business advice provided by a person or organization accustomed with british business market such as FinanceSouthEast.
In 2007 Google filed for a patent for recognizing text in images (http://www.wipo.int/pctdb/en/ia.jsp?IA=US2007072578), therefore a legal advice and explanation of software patents is a key element which will most probably strongly influence the way the idea can be executed. Any decisions referring to Google patent claim have not been made yet.
In a foreign language words do not differ from images. Imagine turning those images back into words within seconds. Image-teller is an image-to-text translator capable of recognizing words in pictures and translating them into any language imaginable. It is a simple smartphone application allowing its user not only to translate writings from pictures taken with their phones, but also provides them with number of features making their every day life in a foreign country easier. Translations along with original pictures can be stored in personalized glossaries serving educational purposes. A feature which reads translated text out helps to learn correct pronunciation in order to avoid misunderstandings while spending time abroad. For more demanding users Image-teller allows to search converted phrases on the Internet, share translated information on social services and find out more about them in most popular on-line databases and encyclopedias. It is dedicated to everyone traveling to a foreign country regardless of their mother-tongue and time to be spend abroad. Thanks to its simplicity and functionality Image-teller has the chance to be a breakthrough in the process of leaping language barrier worldwide. However, to be successful it needs a collective effort of designer, IT specialists, linguists and translators over a long period of time. It needs to be introduced gradually and requires a lot of work to be infallible.Nevertheless its market potential combined with reported rapid growth of smartphone market, which are likely to become the leading technology in the following years, guarantees success of the undertaking.
As a foreigner in the United Kingdom and a speaker of a 'one-country' language I tried to estimate possibilities offered by the application. A number of foreign students including representatives of Poland, Hungary, Finland, China and Spain was also invited to present their opinion on Image-teller concept. The students were mostly temporary students located in England and polish students occasionally visiting other countries.
The translator seems to be a useful tool in running every day errands for example doing shopping or dealing with office matters. Although English is said to be a widespread language there is still number of people who can speak it on basic level only, and they would benefit from such application the most. Nevertheless mastering language skills is a very complex and time consuming process, especially if one does not decide to move permanently to other country, so that the application could be also purchased by people with better language abilities.
Besides people migrating to different countries the largest target group would be tourists. Image-teller can be widely used to translate information in public space, restaurant menus, price charts, warning signs, map keys etc. What deserves to be highlighted is the potential utility of translating cyrillic and other non-latin scripts, which make the use of a traditional dictionary impossible for speakers of latin derived languages. The interface and the way of using the application were assessed in positive way by the potential users, no major functionality issues were raised. Majority of researched students declared to be interested in buying such application at a reasonable price.
Because the idea is purely theoretical, for technology required to implement it does not exist in completed version yet, it is difficult to point specific companies who would take the risk and invest in such undertaking.
The potential success of the application is strictly connected to the growth of smartphone market.
“Gartner [Gartner Inc. Technology research and Business Leader Insight Company based in USA, http://www.gartner.com] forecasts that smartphones, which offer more computing power than standard phones, will already claim a 26-per-cent market share this year, growing to almost half the market (47 per cent) by 2015” ( http://indonsia-stock-exchange.blogspot.com/2011/04/market-share-today-googles-android-os.html). According to RBC Capital Markets one of the condition of the market growth will be the development of new innovative software (http://www.scribd.com/doc/17361921/Global-Smartphone-Market-Sizing). PricewaterhouseCoopers claims that by 2013 the market in North America, Europe and Africa will be worth 4.4 billion USD. (http://www.makmedia.pl/czas-na-rynek-smartphone/). It seems that the future of the mobile phone market belongs to the smartphones, which will have direct impact on the number of applications used and sold..
The technology required to implement the idea, as well as smartphone translators market, is still under development. Most companies such as Toshiba, Jibbigo, Sakhr and Google are concentrated on inventing a speech translator providing with on-demand translation. A notable exception is Fuji, which plans to release glasses translating live conversation and beaming translated 'subtitles' directly onto the retina. Unfortunately, most of those applications work with a very limited number of languages, often focusing on two, maximum three languages only. An older optical character recognition technology bears resemblance to image-to-text translator, however is not efficient enough to serve such purpose.
In 2009 Google, as the only company, presented a prototype of image-to-text translator called Goggle (http://www.google.com/mobile/goggles/#label). The prototype translates german and english text, though company aims to enable translation from all Google Translate languages (nowadays covering 52 ones). Google Goggles in the future is meant to recognize not only text but also buildings, works of arts, logos and different objects, the company does not focuses on one aspect of image recognition. In 2010 Quest Visual (http://questvisual.com/) presented a video english-spanish translator allowing its users translate text in real time. The application does not offer any additional features, currently its creators are working on expanding the number of languages translated by Word Lens.
Image-teller in many aspects is similar to Google Goggles. What may help the idea to stand out is its simplicity. Image-teller is exploring only the translation features and highlights their educational use. The translator is designed for a people looking for a useful and compact application which could replace traditional dictionaries. Possibility to collect and categorize screenshots will help in creating visual glossaries adjusted to personal demands and needs of the user. Image-teller is an application dedicated for people looking for the easiest and fastest solutions of their every day problems, not necessarily with the help of a complicated technologies and interfaces. Simplicity will also allow to lower price in comparison with more complex applications.
The idea is to create a technology which would leap language barrier. Image-teller is an image-to-text translator designed for smart phones offering its users real time translations of text in pictures taken with their smartphones. Image-teller is focused on solving communication problems, and, with the support of its educational aspects, not only helping to understand a language but also familiarizing with different cultures and phenomenons. It may be a milestone in the process of breaking boundaries and better understanding between different nations.
The application provides its user with a grid allowing to point the area in the picture containing text to be translated. The only information to be supplied by the user are the languages from and to which the text is suppose to be translated. Owning to on-line databases connection, translation is generated within seconds. Image-teller offers additional features such as saving a screenshot of the picture with the translation, and reading the translated text out. This may be helpful while traveling abroad not only memorizing different phrases but also learning the right pronunciation. Consequently, traditional dictionaries will no longer be needed. Such quality offered by the translator can be inevitable in countries using non-latin scripts, most people are not accustomed to. Moreover translated information can shared by being sent by e-mail or published on social services. Likewise, browsing the translation in search engine as well as browsing for additional information and definitions in on-line databases is provided. All mentioned aspects can be developed by cooperating with different websites and companies. As shown in the visuals the application has got a very simple and intuitive interface. With Image-teller the world is in your hand.
Besides its commercial and future sales possibilities the idea has strong social values. It originated from real-life issues encountered by hundred of thousands of people every day. Communication boundaries are not only problem of the individuals, but also restrain cross national cooperation and development of countries isolated by language barrier from world economy. Providing people with a mean of leaping the barrier could help overcome many problems and support development of countries in the world. It would have impact on most aspects of life including for example tourism and business. The translator can be a powerful tool supporting people in their every day life, helping fight with isolation and lack of understanding between immigrants and residents, which nowadays often becomes an issue in developed countries (France, Great Britain, Germany).
Because Image-teller is a virtual application its introduction and sale doesn't bring any threat to the natural environment. Although smartphones market is still developing, it is reported to be the main direction to which mobile phones produces will turn, and in few years time we can expect them to be the most popular type of phones. From the release of Apple iPhone in 2007 all companies producing electronic equipment started introducing their own smartphones. According to internet resources the smartphone market already covers approximately 22-31%, depending on the user's age, of entire mobile phones market and the outlooks for the future are even more encouraging (Olswang Report http://www.olswang.com/convergence2011/0). What is more, most smartphones are most popular among people in their 20s and 30s who are also the social group most likely to spent their money traveling.
Initial expenses and efforts connected with executing and implementing Image-teller would cover developing text recognition in images technology. Because once invented it would apply to all different languages, it would be the most costly stage of work on the application. Image-teller, as other smartphone translators currently released, could initially focus on the most popular and useful european languages written with latin script, gradually expanding to others languages and scripts, for example cyrillic. Decisions about the order in which new languages would be added to the database could be made according to number of native-speakers of different languages and surveys investigating the most urgent requirements related to global economics and migration. This would minimize the risk of loosing shareholders money for the development of the application would flexibly respond to the market's needs.
Subskrybuj:
Posty (Atom)