Abstract: A system for re-ranking retrieved matching images. The system comprises a processor configured to extract at least one QI global feature from query image by global feature extractor module, and extract plurality of QI local features for the query image by local feature extractor module, and then search and retrieve top-k reference images from plurality of reference images based on at least one QI global feature and at least one KRI global feature associated with top-k reference images by filtering module. The processor is configured to perform matching of the plurality of QI local features with the plurality of KRI local features associated with the top-k reference images by fine tuning module and generate matching distance by distance fusion module, wherein the top-k reference images are re-ranked based on the matching distance and generate confidence score for the top-n reference images by confidence score generation module.

Abstract: A system to extract checkbox symbol and checkbox option pertaining to checkbox question from a document is provided. The system comprises of processors configured to identify location of checkbox symbols and their relative location with respect to checkbox options. The processor is configured to determine context of textual information corresponding to checkbox options using textual processing and a pictorial representation of non-textual information corresponding to checkbox symbols using visual processing is detected. The processor is configured to group the textual information corresponding to the checkbox options with the corresponding checkbox symbols by unique visual token using the textual processing and the visual processing on the document. The unique visual token is utilized as an anchor to group the textual information with the non-textual information in the digital document. The processor is configured to identify at least a link between the checkbox options with corresponding checkbox questions.

Abstract: A system to calculate a reconfigured confidence score is configured to receive a text, a plurality of labels, and a plurality of confidence scores from a plurality of models and assign a weightage to the inputs received from the plurality of models. The system is configured to select a first text with a first label and retrieve a second text, a third text, and a second label. The system is further configured to generate a first, second and third output confidence score for the first text, second text and third text, and corresponding labels. The system compares the plurality of output confidence scores and generates an output which comprises of the first text, the first label, and a final confidence score, wherein the final confidence score is one among the first, second and third output confidence scores.

Abstract: A system for template invariant information extraction. The system comprises of processor, a first neural network model and a second neural network model. The processor is configured to recognize and extract entities and location of the entities in the input document using the first neural network model. The processor is further configured to classify whether the input document belongs to at least a template of the documents of the first training dataset using the second neural network model. The second neural network model comprises a linear classifier configured to generate a plurality of confidence scores for the input document corresponding to a unique template of the documents of the first training dataset. A threshold value to classify the input document belonging to template of the documents of the first training dataset is determined, Classification is done by comparing the confidence score with the threshold value.

Abstract: A system to extract checkbox symbol and checkbox option pertaining to checkbox question from a document is provided. The system comprises of processors configured to identify location of checkbox symbols and their relative location with respect to checkbox options. The processor is configured to determine context of textual information corresponding to checkbox options using textual processing and a pictorial representation of non-textual information corresponding to checkbox symbols using visual processing is detected. The processor is configured to group the textual information corresponding to the checkbox options with the corresponding checkbox symbols by unique visual token using the textual processing and the visual processing on the document. The unique visual token is utilized as an anchor to group the textual information with the non-textual information in the digital document. The processor is configured to identify at least a link between the checkbox options with corresponding checkbox questions.

Abstract: The present invention discloses a system for linking first type of entities and second type of entities in a page. The system is configured to generate a feature vector for each of the first type of entities and each of the second type of entities. Further, the system is configured to receive into a neural network, a pair of the feature vectors, wherein one of the pair of the feature vector corresponds to a feature vector of a first type of entity and another feature vector corresponds to a feature vector of a second type of entity. The entities corresponding to the pair of feature vectors are neighboring each other. The neural network is configured to generate an output, indicating the likelihood of the pair of entities being linked.

Abstract: A system to calculate a reconfigured confidence score is configured to receive a text, a plurality of labels, and a plurality of confidence scores from a plurality of models and assign a weightage to the inputs received from the plurality of models. The system is configured to select a first text with a first label and retrieve a second text, a third text, and a second label. The system is further configured to generate a first, second and third output confidence score for the first text, second text and third text, and corresponding labels. The system compares the plurality of output confidence scores and generates an output which comprises of the first text, the first label, and a final confidence score, wherein the final confidence score is one among the first, second and third output confidence scores.

Abstract: System for optimizing training dataset comprising sample documents. The system comprises one or more processors configured to create graph embedding vector for each of the sample documents of the training dataset and cluster the graph embedding vectors of the sample documents of the training dataset into clusters based on the similarity between the graph embedding vectors. Further, the processor is configured to select a first set of training data, using an optimization model, wherein the first set of training data comprises a finite number of graph embedding vectors of the sample documents from the clustered training dataset. Finally, the first set of training data is fed as for a machine learning model.

Abstract: System for graph-based clustering of documents. The system comprises one or more processors configured to receive a digital copy of a document to convert the document into a graph object. Further, the processor is configured to identify and label entities in the document, wherein each of the entities is represented as a node of the graph object. Further, the processor is configured to create the graph object for the received digital copy of the document and generate a graph embedding vector using a graph embedding neural network trained to receive the graph object as input and generate the graph embedding vector for the graph object as output. Finally, the processor is configured to cluster the graph embedding vector to a cluster comprising similar looking templates of the document.

Abstract: A system for obtaining documents from a composite file comprising a stream of multiple pages is provided. The system may comprise one or more processors configured to receive the composite file comprising the multiple pages and split the composite file to obtain individual pages of the composite file, wherein image of each of the individual pages and image vector for each of the individual pages from the image of the respective page may be obtained. The processor may further obtain text present in each of the individual pages and text vector for each of the individual pages from the text of the respective page. The processor may further determine continuity pattern between pages that are consecutive based on the image vector and the text vector of the consecutive pages and may categorize the consecutive pages as belonging to the same document in case the determined continuity pattern between the consecutive pages indicate that the consecutive pages belong to the same document.

Abstract: A method of training a system to extract information from documents comprises feeding digital form of training documents to an OCR module, which identifies multiple logical blocks in the documents and text present in the logical blocks. One or more tags for the whole of the document, the logical blocks and word tokens on the document are received by a tagging module. A text input comprising the text identified in the document and the tags for the whole of the document are received by a machine learning module. A first image of the document with layout of the one or more of the identified blocks superimposed, and the tags of the logical blocks in the document are received by the machine learning module, wherein the received text input, first image and tags for the logical blocks corresponds to a plurality of the training documents.

Abstract: A system for template invariant information extraction. The system comprises of processor, a first neural network model and a second neural network model. The processor is configured to recognize and extract entities and location of the entities in the input document using the first neural network model. The processor is further configured to classify whether the input document belongs to at least a template of the documents of the first training dataset using the second neural network model. The second neural network model comprises a linear classifier configured to generate a plurality of confidence scores for the input document corresponding to a unique template of the documents of the first training dataset. A threshold value to classify the input document belonging to template of the documents of the first training dataset is determined, Classification is done by comparing the confidence score with the threshold value.

Abstract: The present invention discloses a system for linking first type of entities and second type of entities in a page. The system is configured to generate a feature vector for each of the first type of entities and each of the second type of entities. Further, the system is configured to receive into a neural network, a pair of the feature vectors, wherein one of the pair of the feature vector corresponds to a feature vector of a first type of entity and another feature vector corresponds to a feature vector of a second type of entity. The entities corresponding to the pair of feature vectors are neighboring each other. The neural network is configured to generate an output, indicating the likelihood of the pair of entities being linked.

Abstract: A system for extracting text from images comprises a processor configured to receive a digital copy of an image and identify a portion of the image, wherein the portion comprises text to be extracted. The processor further determines orientation of the portion of the image, and extracts text from the portion of the image considering the orientation of the portion of the image.

Abstract: A system for obtaining documents from a composite file comprising a stream of multiple pages is provided. The system may comprise one or more processors configured to receive the composite file comprising the multiple pages and split the composite file to obtain individual pages of the composite file, wherein image of each of the individual pages and image vector for each of the individual pages from the image of the respective page may be obtained. The processor may further obtain text present in each of the individual pages and text vector for each of the individual pages from the text of the respective page. The processor may further determine continuity pattern between pages that are consecutive based on the image vector and the text vector of the consecutive pages and may categorize the consecutive pages as belonging to the same document in case the determined continuity pattern between the consecutive pages indicate that the consecutive pages belong to the same document.

Abstract: A method of training a system to extract information from documents comprises feeding digital form of training documents to an OCR module, which identifies multiple logical blocks in the documents and text present in the logical blocks. One or more tags for the whole of the document, the logical blocks and word tokens on the document are received by a tagging module. A text input comprising the text identified in the document and the tags for the whole of the document are received by a machine learning module. A first image of the document with layout of the one or more of the identified blocks superimposed, and the tags of the logical blocks in the document are received by the machine learning module, wherein the received text input, first image and tags for the logical blocks corresponds to a plurality of the training documents.

Abstract: A system for extracting text from images comprises a processor configured to receive a digital copy of an image and identify a portion of the image, wherein the portion comprises text to be extracted. The processor further determines orientation of the portion of the image, and extracts text from the portion of the image considering the orientation of the portion of the image.