Claims:WE CLAIM:
1. The system for patent image search comprising of;
a. a communication device such as computer/laptop/desktop;
b. user interface such as internet/a LAN or WAN network ; and
c. a host website where the registration of user is carried out.
2. The system as claimed in claim1, wherein the said provides image search is a sub-image/part-image search.
3. The system as claimed in claim 1, wherein the said system allows the user to search from multiple images.
4. The method for patent image search comprising of;
a. registering user with the host database;
b. selecting an image;
c. uploading the image in host database;
d. retrieving the results; and
e. sorting the results in order to match with the patent image.
, Description:FIELD OF THE INVENTION:
The present invention relates to query processing search techniques for free database. The present invention more particularly relates to a system and method for image search or files containing visual information to retrieve patents.
BACKGROUND OF THE INVENTION:
Traditional image search relies on the user’s search strategies of keywords used in the search. If search is carried out only at pointing some object or some photo or some abstract idea, but is entirely useless when what you are searching for can only be expressed by pointing at an object or another photo, or an abstract idea.
Image search on the Internet involves a search engine specialized on finding pictures, images, animations, and other similar media. A user may enter keywords and search phrases into an image search engine to receive back a set of thumbnail images as search results that may be sorted by relevancy.
These methods and systems are usable for receiving a query for an image of an object and providing a ranked list of query results to the user based on a ranking of the images. The object-sensitive image searches may generate a pre-trained multi-instance learning (MIL) model trained from free training data from users sharing images at web sites to identify a common pattern of the object.
Searches based around images are also known in the patent literature. For example, US2012123976 describes methods and systems for object-sensitive image searches. These methods and systems are usable for receiving a query for an image of an object and providing a ranked list of query results to the user based on a ranking of the images. The object-sensitive image searches may generate a pre-trained multi-instance learning (MIL) model trained from free training data from users sharing images at web sites to identify a common pattern of the object.
There are problems with obtaining representative and diverse views of the world landmarks from community-contributed collections on the web. For example, text annotations to the images provided by users often are inaccurate. The images themselves are of varying quality and the sheer volume of landmark images in any one collection
makes image content hard to browse and represent, since more photos are added everyday to a given database.
The existing content-based image retrieval (CBIR) techniques mostly exploit the color and texture features of the images which make them less useful in the patent image domain.
So there is a need for a system and method for patent image search which can retrieve correct results based on search done. The present invention allows the user to start a search by supplying an image to search based on content rather than by entering keyword queries.
OBJECTS OF THE INVENTION:
The main object of the present invention is to provide accurate, targeted and correct results based on search terms in short and precise manner to consume less effort and time.
Yet another object of the present invention is to provide a easy and fast system and method for retrieval of patent easily.
Other objects and benefits of the present invention will be more apparent from the following description, which is not intended to bind the scope of the present invention.
SUMMARY OF THE INVENTION:
Accordingly, a system and method for patent image search using host website is disclosed. The present invention provides accurate, targeted and correct results based on search terms in short and precise manner to consume less effort and time. The method for patent image search comprising of; Registering user with the host database; Selecting an image; Uploading the image in host database; Retrieving the results; and Sorting the results in order to match with the patent image.
DESCRIPTION OF THE DRAWINGS:
Fig 1 shows the system and method for patent image search using host website.
DETAILED DESCRIPTION OF THE INVENTION:
The present invention is a system and method for patent image search using host website. The present invention helps in full image search, its sub image search. The present invention provides accurate, targeted and correct results based on search terms in short and precise manner to consume less efforts and time and to provide an easy and fast system and method for retrieval of patent easily.
The present invention helps in reducing the time spent on searching and allows me to spend more time on analysis. The present invention finds images similar to those entered by the searcher. Reverse image searching includes an option to use images along with attributes such as tags, qualifiers, domains and categories, which allows the reverse image search algorithm to narrow search process and yield better results.
When searching using an image, results may include:
• similar images; and
• sites that include that image.
In this system, a user registers himself with the host database and carry out a full image search. The user upload the image in search bar and some results are obtained. A full image is put as a query input and it retrieves almost all the visually similar images (from a structural/geometric point of view) to it following a query-by-example paradigm in a patent image collection.
A patent image composed of different geometric objects arranged in a spatial configuration, to retrieve the object of interest (an interesting pattern) found in a collection of patent images can be called sub-image or part-based search in images. The present invention provides sub-image/part-image search capability which will be helpful to patent experts/analysts in examination of patent images at part level.
Due to the millions of images in patent databases, the scalability of a patent image retrieval system and method is a major concern. To cope with the scalability issue, computationally low-cost features and retrieval are major preferences. The response time of the system and method should be low (approaching real time). To improve the retrieved results according to the visual similarity of a query image, an iterative search process is useful, taking advantage of relevance feedback from the user.
The method for patent image search comprising of: registering user with the host database; selecting an image; uploading the image in host database; retrieving the results; and sorting the results in order to match with the patent image.
By combining features from two images, the invention allows the user to search from multiple images as well as specifying what exactly it is about an image that they want to search for. Once a search query has been formulated, the search query is searched using known techniques.
There is provided a preferred system and method of conducting a search comprising forming a search query, searching for results which match said composite image; outputting said search results to a user; receiving a new user selected image which is selected from within said search results; receiving a new user selection of a feature within said new user selected image; searching for results which match said new user selected feature; and outputting a new set of results.
Each feature may be a subsection of said user selected image, e.g. a chair within a picture of a room. The feature may be a shape, color, texture, pattern or other parameter of an object within said user selected image. There may be more than one feature selected from within each selected image. For example, a user selection of a first feature may be received from within said first user selected image and a user selection of a second and third feature may be received from within said second user selected image. The composite image may combine all three features.
At least one of said user selected images may be segmented into a plurality of objects which may be presented to a user, e.g. on a user interface. Said feature is selected from one of said plurality of objects, e.g. by clicking on said object. A weight may be applied to each selected feature when combining to form said composite image. Said weight may be adjusted by said user.
The system for patent image search comprising of: a communication device such as computer/laptop/desktop; user interface such as internet/a LAN or WAN network; and a host website where the registration of user is carried out.