# US 12,120,279 B2 · Output resolution selections > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,120,279 B2 - Document ID: US12120279B2 - Status: Granted - Kind: B2 - Application number: 18/271,725 - Filed: 2021-01-13 - Published: 2024-02-29 - Granted: 2024-10-15 - Earliest claimed: 2021-01-13 - Assignees: Hewlett-Packard Development Company, L.P.; Purdue Research Foundation - Applicants: Hewlett-Packard Development Company, L.P.; Purdue Research Foundation - Inventors: Todd J. Harris; Peter Bauer; Jan Allebach; Zhenhua Hu; Litao Hu - Web page: https://patentgrep.com/patent/US12120279B2 ## CPC - H04N 1/00816: {Determining the reading area, e.g. eliminating reading of margins} - G06V 10/44: Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components - G06V 10/764: using classification, e.g. of video objects - G06V 10/82: using neural networks - G06V 30/414: Extracting the geometrical structure, e.g. layout tree; Block segmentation, e.g. bounding boxes for graphics or text - H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## Abstract In some examples, a computing device can include a processor resource and a non-transitory memory resource storing machine-readable instructions stored thereon that, when executed, cause the processor resource to: identify a plurality of regions within a captured document, determine a quantity of vertical transitions and horizontal transitions within the plurality of regions, and select an output resolution for the plurality of regions based on the quantity of vertical transitions and horizontal transitions within the plurality of regions. ## Claims ### Claim 1 A computing device, comprising: a processor resource; and a non-transitory memory resource storing machine-readable instructions stored thereon that, when executed, cause the processor resource to: identify a plurality of regions within a captured document; determine a quantity of vertical transitions and horizontal transitions within the plurality of regions; and select an output resolution for the plurality of regions based on the quantity of vertical transitions and horizontal transitions within the plurality of regions. ### Claim 2 (depends on 1) The computing device of claim 1, wherein the processor resource is to determine a quantity of transition pixels along a vertical axis to determine the quantity of vertical transitions. ### Claim 3 (depends on 1) The computing device of claim 1, wherein the processor resource is to determine a quantity of transition pixels along a horizontal axis to determine the quantity of horizontal transitions. ### Claim 4 (depends on 1) The computing device of claim 1, wherein the processor resource is to determine an edge density of the captured document based on the quantity of vertical transitions and horizontal transitions within the plurality of regions. ### Claim 5 (depends on 1) The computing device of claim 1, wherein the output resolution is selected based on a determined threshold quantity of vertical transitions and horizontal transitions within the plurality of regions. ### Claim 6 (depends on 5) The computing device of claim 5, wherein the processor resource is to lower an output resolution for a first region when the first region is below the threshold quantity of vertical transitions and horizontal transitions and increase an output resolution for a second region when the second region is above the threshold quantity of vertical transitions and horizontal transitions. ### Claim 7 (depends on 1) The computing device of claim 1, wherein the processor resource is to determine an edge contrast for the plurality of regions base on the quantity of vertical transitions and horizontal transitions within the plurality of regions. ### Claim 8 A non-transitory memory resource storing machine-readable instructions stored thereon that, when executed, cause a processor resource to: identify a plurality of regions within a captured document, wherein one of the plurality of regions includes a symbol region; generate a plurality of resolution tiers for the symbol region; assign a classification to the symbol region for the plurality of resolution tiers, wherein the classification is one of a readable classification and a non-readable classification; and select an output resolution for the captured document based on the classification of the symbol region for the plurality of resolution tiers. ### Claim 9 (depends on 8) The memory resource of claim 8, wherein the processor resource is to determine a minable reproduceable resolution for symbols within the symbol region. ### Claim 10 (depends on 8) The memory resource of claim 8, wherein the processor resource is to split the symbol region into a plurality of sub-regions to perform a convolutional neural network (CNN) calculation on the plurality of sub-regions at the plurality of resolution tiers. ### Claim 11 (depends on 8) The memory resource of claim 8, wherein the plurality of regions are identified by raw captured data and the selected output resolution is utilized for post-processing of the captured document. ### Claim 12 A scanning device, comprising: an image captured device; and a processor resource to: receive image data of a document from the image capture device; identify an image portion from the image data of the document; identify a plurality of regions within the image portion; determine a quantity of vertical transitions and horizontal transitions within the plurality of regions; determine an edge density of the plurality of regions based on the quantity of vertical transitions and horizontal transitions within the plurality of regions; select an output resolution for the image portion based on the edge density; and perform post-processing on the captured image using the selected output resolution for the document. ### Claim 13 (depends on 12) The scanning device of claim 12, wherein the output resolution includes a first output resolution for the image portion and a second output resolution for a text portion of the captured document. ### Claim 14 (depends on 12) The scanning device of claim 12, wherein the output resolution is selected based on a minimal edge density for the image portion. ### Claim 15 (depends on 14) The scanning device of claim 14, wherein the processor resource is to perform machine learning to determine the minimal edge density for the image portion.