Intelligent Importation of Rasterized Data via Neural Networks
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing business applications lacking built-in image management capabilities face challenges in linking digital images with corresponding records, especially those in non-ASCII, rasterized text formats, as conventional image enablement techniques are not suited for graphics-based displays.
Innovation Solution
An intelligent importation process utilizing artificial neural networks to extract and recognize rasterized data from applications, converting it into ASCII text format for linking images or documents between applications without affecting the host application's operation, employing raster, feature, and vector processing methods.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If conventional image enablement techniques are used for text-based applications, then linking capability is achieved, but the solution cannot be applied to graphics-based displays
Solution Approach 1:
The patent introduces an intermediary component (the intelligent importation process with neural networks) that mediates between the graphics-based display system and the image management system. This intermediary captures raster data from the display buffer, processes it through neural networks to recognize and extract meaningful information, and then uses that extracted data to link images, thereby enabling graphics-based applications to function with image management capabilities without modifying the original application
Solution Approach 2:
The patent replaces the mechanical/text-based data extraction method (reading from display buffer or intercepting ASCII output) with an intelligent system using artificial neural networks. The neural networks analyze raster graphics data, recognize patterns, and extract meaningful information, substituting the simple text-based approach with a more sophisticated visual recognition system that can handle graphics-based displays
2Reliability
If raster data is processed directly without conversion, then display fidelity is maintained, but data cannot be used for linking images
Solution Approach 1:
The patent performs preliminary processing of the raster data by capturing it from the display buffer before it is rendered to the screen. The intelligent importation process intercepts the raster data in its raw form, processes it through neural networks to extract meaningful information, and converts it to a usable format for image linking, all before the data is displayed to the user
Solution Approach 2:
The patent creates a copy of the raster data from the display buffer for processing. The original display data remains unchanged and intact, while a copy is made and processed through the neural network system to extract linking information. This ensures that the original display fidelity is maintained while enabling image linking capabilities through the processed copy
Data Source
AI summary
A process for intelligent importation of information from a foreign application user interface includes extraction of raster data from a pre-designated region of a screen displayed in the foreign application, segmentation of the raster data into prospective sets of character raster data; application of the character raster data and a feature data set and a vector data set derived from the character raster data as inputs to respective raster, feature, and vector artificial neural networks to generate candidate characters; using a voting process to identify a character represented by the character raster data from the candidate characters; assembly of the remaining characters as recognized by the neural networks into a key; and association of the key with an external data file which may be stored and thereafter retrieved in association with the screen displayed in the foreign application.