# US 11,113,557 B2 · System and method for generating an electronic template corresponding to an image of an evidence > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,113,557 B2 - Document ID: US11113557B2 - Status: Granted - Kind: B2 - Application number: 16/268,975 - Filed: 2019-02-06 - Published: 2019-08-08 - Granted: 2021-09-07 - Earliest claimed: 2018-02-06 - Assignees: Vatbox, Ltd. - Applicants: Vatbox, Ltd. - Inventors: Isaac Saft; Noam Guzman; Natanel Davidovits - Web page: https://patentgrep.com/patent/US11113557B2 ## CPC - G06V 30/416: Extracting the logical structure, e.g. chapters, sections or page numbers; Identifying elements of the document, e.g. authors - G06T 7/11: Region-based segmentation - G06V 30/1448: {based on markings or identifiers characterising the document or the area} - G06V 30/153: {using recognition of characters or words} - G06V 30/36: {Matching; Classification} - G06V 30/10: Character recognition - G06V 2201/10: Recognition assisted with metadata - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ## Abstract A system and method for generating an electronic template corresponding to an image of an evidence, including: segmenting the image into a plurality of regions of interest (ROIs); analyzing each of the plurality ROIs to identify at least a portion of a content within the ROI and a position of each of the plurality of ROIs within the image; generating a label for each of the plurality of ROIs corresponding to the analysis, wherein the label is indicative of the at least a portion of the content and the position of the ROI within the image; and generating the electronic template for the evidence, wherein the template includes the plurality of ROIs and the labels corresponding to each ROI. ## Claims ### Claim 1 A method for generating an electronic template corresponding to an image of an evidence, comprising: generating an unlabeled template corresponding to the image, the unlabeled template formatted to include a plurality of data elements organized in an array, wherein the generating includes segmenting the image into a first plurality of regions of interest (ROIs); selecting a first labeled template from a plurality of labeled templates with a second plurality of ROIs and matching with the unlabeled template; analyzing each of the plurality ROIs to identify at least a portion of a content within the ROI and a position of each of the plurality of ROIs within the image; generating a label for each of the plurality of ROIs corresponding to the analysis, wherein the label is indicative of the at least a portion of the content and the position of the ROI within the image; and classifying and storing the unlabeled template and the generated label for the evidence based on the matching, wherein the unlabeled template includes the plurality of ROIs and the labels corresponding to each ROI. ### Claim 2 (depends on 1) The method of claim 1, wherein analyzing each of the plurality of ROIs including performing optical character recognition (OCR) to identify characters within the image. ### Claim 3 (depends on 1) The method of claim 1, further comprising: identifying metadata associated with the at least a portion of the content, the unlabeled template further includes the generated identified metadata. ### Claim 4 (depends on 1) The method of claim 1, wherein the segmenting the image is based on previously generated electronic ROI templates. ### Claim 5 (depends on 1) The method of claim 1, wherein the segmenting the image is achieved using machine learning techniques. ### Claim 6 (depends on 1) The method of claim 1, further comprising: generating the unlabeled template for each of the first plurality of ROI separately. ### Claim 7 (depends on 1) The method of claim 1, further comprising: identifying, in the image, at least one key field and at least one value; creating, based on the image, a structured dataset, wherein the created dataset includes the at least one key field and the at least one value; and analyzing the created dataset, wherein the unlabeled template is generated based on the analysis. ### Claim 8 (depends on 7) The method of claim 7, further comprising: performing a cleaning process on the at least a portion of the content of the ROIs. ### Claim 9 A non-transitory computer readable medium having stored thereon instructions for causing a processing circuitry to perform a process for generating an electronic template corresponding to an image of an evidence, the process comprising: generating an unlabeled template corresponding to the image, the unlabeled template formatted to include a plurality of data elements organized in an array, wherein the generating includes segmenting the image into a plurality of regions of interest (ROIs); selecting a first labeled template from a plurality of labeled templates with a second plurality of ROIs and matching with the unlabeled template; analyzing each of the plurality ROIs to identify at least a portion of a content within the ROI and a position of each of the plurality of ROIs within the image; generating a label for each of the plurality of ROIs corresponding to the analysis, wherein the label is indicative of the at least a portion of the content and the position of the ROI within the image; and classifying and storing the unlabeled template and the generated label for the evidence based on the matching, wherein the unlabeled template includes the plurality of ROIs and the labels corresponding to each ROI. ### Claim 10 A system for generating an electronic template corresponding to an image of an evidence, comprising: a processing circuitry; and a memory, the memory containing instructions that, when executed by the processing circuitry, configure the system to: generate an unlabeled template corresponding to the image, the unlabeled template formatted to include a plurality of data elements organized in an array, wherein the generating includes segmenting the image into a first plurality of regions of interest (ROIs); select a first labeled template from a plurality of labeled templates with a second plurality of ROIs and matching with the unlabeled template; analyze each of the plurality ROIs to identify at least a portion of a content within the ROI and a position of each of the plurality of ROIs within the image; generate a label for each of the plurality of ROIs corresponding to the analysis, wherein the label is indicative of the at least a portion of the content and the position of the ROI within the image; and classifying and storing the for the evidence, wherein the template includes the plurality of ROIs and the labels corresponding to each ROI. ### Claim 11 (depends on 10) The system of claim 10, wherein analyzing each of the ROIs including performing optical character recognition (OCR) to identify characters within the image. ### Claim 12 (depends on 10) The system of claim 10, wherein the system is further configured to: identify metadata associated with the at least a portion of the content, the unlabeled template further includes the generated identified metadata. ### Claim 13 (depends on 10) The system of claim 10, wherein the segmenting the image is based on previously generated electronic ROI templates. ### Claim 14 (depends on 10) The system of claim 10, wherein segmenting the image is achieved using machine learning techniques. ### Claim 15 (depends on 10) The system of claim 10, wherein the system is further configured to: generate the unlabeled template for each of the first plurality of ROI separately. ### Claim 16 (depends on 10) The system of claim 10, wherein the system is further configured to: identify, in the image, at least one key field and at least one value; create, based on the first image, a structured dataset, wherein the created dataset includes the at least one key field and the at least one value; and analyze the created dataset, wherein the unlabeled template is generated based on the analysis. ### Claim 17 (depends on 16) The system of claim 16, wherein the system is further configured to: performing a cleaning process on the at least a portion of the content of the ROIs.