Method and system of identifying an entity from a digital image of a physical text

1. A server-side method of identifying a wine entity from text in a digital image of a wine menu comprising:

obtaining a digital image from a mobile device, wherein the digital image comprises a digital photograph of a physical text, wherein at least a portion of the physical text is related to a pre-defined topic, wherein the digital image comprises a digital photograph of a wine menu, wherein the pre-defined topic comprises a wine-related topic, and wherein the digital photograph is obtained with a digital camera system in the mobile device of a user;

converting the digital photograph of the physical text to a text in a computer-readable format;

providing a word dictionary, wherein the word dictionary comprises a set of words related to the pre-defined topic;

matching a set of words of the text to similar words in the set of words in the word dictionary;

identifying a word cluster in the text, wherein each word in the word cluster is associated with a category of a single entity, wherein the single entity is a member of a class of entities demarcated by the pre-defined topic, wherein the class of entities demarcated by the pre-defined topic comprises a set of wine items, and wherein a set of categories of the wine item comprises a wine varietal, a wine producer and a wine vintage;

searching a database comprising a list of members of the class of entities demarcated by the pre-defined topic for one or more entities matching one or more of word-category associations of the word cluster;

receiving a user instruction that identifies the word cluster; and

implementing a linear n-gram scanning processes to convert a set of character strings of each word in the set of words of the text to words related to the pre-defined topic according to a statistical algorithm.

2. The method of claim 1 , wherein the word cluster is identified based on a set of pre-defined rules for determining that each word in the word cluster is related to a category.

3. The method of claim 2 , wherein the set of pre-defined rules comprises a vintage rule that allows for only a single vintage-related word to define a vintage category of the set of wine items.

4. The method of claim 3 , wherein the set of pre-defined rules are based on a prior knowledge of a normative layout of an entity type on a physically-printed text.

5. The method of claim 1 further comprising:

returning a sorted list of the one Or more entities matching the one or more of word-category associations of the word cluster, Wherein in the list is ranked based on the number of matches between the word-category associations of the word cluster for each entity in the list.

6. A. computerized .system of identifying a wine entity from text in a digital image of a wine menu comprising:

a processor configured to execute instructions;

a memory including instructions when executed on the processor, causes the processor to perform operations that:

obtains a digital image from a mobile device, wherein the digital image comprises a digital photograph of a physical text, wherein at least a portion of the physical text is related to a pre-defined topic, wherein the digital image comprises a digital photograph of the wine menu, and Wherein the pre-defined topic comprises a wine-related topic;

converts the digital photograph of the physical text to a text in a computer-readable format;

provides a word dictionary, wherein the word dictionary comprises a set of words related to the pre-defined topic;

matches a set of words of the text to similar words in the set of words in the word dictionary;

identifies a word cluster in the text, wherein each word in the word cluster is associated with a category of a single entity, wherein the single entity is a member of a class of entities demarcated by the pre-defined topic, wherein the class of entities demarcated by the pre-defined topic comprises a set of wine items, and wherein a set of categories of the wine item comprises a wine varietal, a wine producer and a wine vintage;

searches a database comprising; a list of members of the class of entities demarcated by the pre-defined topic for one or more entities matching one or more of word-category associations of the word cluster;

receives a user instruction that identifies the word cluster;

returns a sorted list of the one or more entities matching the one or more of word-category associations of the word cluster, wherein in the list is ranked based on the number of matches between the word-category associations of the word cluster for each entity in the list; and

implement a linear n-gram scanning processes to convert a set of character strings of each word in the set of words of the text to words related to the pre-defined topic according to a statistical algorithm.

7. The computerized system of claim 6 , wherein the digital image is obtained with a digital camera system in the mobile device of a user.

8. The computerized system of claim 7 , wherein the word cluster is identified based on a set of pre-defined rules for determining that each word in the word cluster is related to a wine category.

9. The computerized system of claim 8 , wherein the set of rules are based on a prior knowledge of a normative layout of an entity type on a physically-printed wine-menu text.