Information Processing Apparatus Positional Error Extraction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing information processing apparatuses fail to extract a predesignated area from a read image when positional errors occur, especially when processing multiple documents, as they rely on accurate positional information which may not be available.
Innovation Solution
The apparatus includes a first designation unit to set an extensive area in a read image, a second designation unit to identify the output area within this extensive area, a position acquisition unit to store positional information, and an extraction unit to locate and extract the output area in subsequent images without relying on positional information from the read image.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If positional information from the first read image is used to extract the output area in the second read image, then the extraction process is simple and fast, but the extraction fails when positional errors occur in the second document
Solution Approach 1:
The patent applies preliminary action by designating an extensive area that is larger than the actual output area in the first read image. This extensive area includes the output area plus additional object areas, creating a buffer zone that accommodates positional variations. The positional information stored is for this extensive area rather than the precise output area boundaries, allowing the same extensive area to cover the output area even when positional errors occur in subsequent documents.
Solution Approach 2:
The patent changes the parameter of area coverage by using an extensive area that is deliberately larger than the minimal required output area. This parameter change from precise bounding to extended bounding allows the system to maintain extraction reliability despite positional errors, as the extensive area provides a margin of error that absorbs positioning variations.
2Reliability
If an extensive area larger than the output area is designated in the first read image, then the output area can be reliably identified in subsequent images despite positional errors, but the area to be processed increases
Solution Approach 1:
The patent applies the taking out principle by extracting only the specific output area from the extensive area after the second read image is acquired. While the extensive area is used for positioning purposes to ensure reliability, the final extraction operation selectively extracts only the needed output area, not the entire extensive area. This separates the positioning function (using extensive area) from the extraction function (using only output area).
Data Source
AI summary
An information processing apparatus includes a first designation unit, a second designation unit, a position acquisition unit, a memory, and an extraction unit. The first designation unit designates an extensive area from a first read image, the extensive area including an output area and an object area. The second designation unit designates the output area from the designated extensive area. The position acquisition unit acquires positional information regarding the extensive area with respect to the first read image and positional information regarding the output area with respect to the extensive area. The memory stores the positional information regarding the extensive area and the positional information regarding the output area. The extraction unit identifies a position of the extensive area in a second read image in a format identical to a format of the first read image on a basis of the positional information regarding the extensive area stored by the memory. The extraction unit also extracts the output area in the second read image on a basis of the position of the extensive area and the positional information regarding the output area stored by the memory.