# US 12,118,763 B2 · Cognitive load scoring of a visual stimulus > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,118,763 B2 - Document ID: US12118763B2 - Status: Granted - Kind: B2 - Application number: 17/723,733 - Filed: 2022-04-19 - Published: 2023-10-19 - Granted: 2024-10-15 - Earliest claimed: 2022-04-19 - Assignees: Dell Products L.P. - Applicants: Dell Products L.P. - Inventors: Annamarie Huttunen; Jordan E. Lord; Shannon Rogers - Web page: https://patentgrep.com/patent/US12118763B2 ## CPC - G06V 10/40: Extraction of image or video features - G06V 10/50: by performing operations within image blocks; by using histograms, e.g. histogram of oriented gradients [HoG]; by summing image-intensity values; Projection analysis - G06V 10/464: {using a plurality of salient features, e.g. bag-of-words [BoW] representations} - G06V 10/761: {Proximity, similarity or dissimilarity measures} - G06V 10/762: using clustering, e.g. of similar faces in social networks - G06V 20/70: Labelling scene content, e.g. deriving syntactic or semantic representations - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## Abstract An apparatus comprises at least one processing device comprising a processor coupled to a memory. The at least one processing device is configured to obtain an information density matrix for an input visual stimulus, the information density matrix characterizing information density of feature points in the input visual stimulus, and to identify one or more clusters of feature points in the input visual stimulus by performing spatial clustering of the feature points utilizing the information density matrix. The at least one processing device is also configured to determine a cognitive load score for the input visual stimulus based at least in part on the identified one or more clusters of feature points, the cognitive load score characterizing cognitive energy required to mentally process the input visual stimulus. The at least one processing device is further configured to modify a design of the input visual stimulus to adjust the cognitive load score of the input visual stimulus. ## Claims ### Claim 1 An apparatus comprising: at least one processing device comprising a processor coupled to a memory; the at least one processing device being configured to perform steps of: obtaining an information density matrix for an input visual stimulus, the information density matrix characterizing information density of feature points in the input visual stimulus; identifying one or more clusters of feature points in the input visual stimulus by performing spatial clustering of the feature points utilizing the information density matrix; determining a cognitive load score for the input visual stimulus based at least in part on the identified one or more clusters of feature points, the cognitive load score characterizing cognitive energy required to mentally process the input visual stimulus; and modifying a design of the input visual stimulus to adjust the cognitive load score of the input visual stimulus. ### Claim 2 (depends on 1) The apparatus of claim 1 wherein the input visual stimulus comprises an image file. ### Claim 3 (depends on 1) The apparatus of claim 1 wherein determining the cognitive load score for the input visual stimulus is based at least in part on a number of the identified one or more clusters of feature points, wherein the cognitive load score for the input visual stimulus increases with the number of the identified one or more clusters of feature points. ### Claim 4 (depends on 3) The apparatus of claim 3 wherein identifying the one or more clusters of feature points in the input visual stimulus comprises performing a density-based clustering algorithm on the information density matrix to generate a normalized number of the identified one or more clusters of feature points, the cognitive load score for the input visual stimulus being based at least in part on the normalized number of the identified one or more clusters of feature points. ### Claim 5 (depends on 4) The apparatus of claim 4 wherein the normalized number of the identified one or more clusters of feature points is generated utilizing a minimum-maximum scalar algorithm. ### Claim 6 (depends on 1) The apparatus of claim 1 wherein determining the cognitive load score comprises calculating distances between the identified one or more clusters, wherein the cognitive load score for the input visual stimulus increases as distances between the identified one or more clusters increases. ### Claim 7 (depends on 6) The apparatus of claim 6 wherein calculating the distances between the identified one or more clusters comprises calculating Euclidean distances between centroids of the identified one or more clusters, normalizing the calculated Euclidean distances, and determining an average of the normalized Euclidean distances. ### Claim 8 (depends on 1) The apparatus of claim 1 wherein determining the cognitive load score comprises calculating sizes of the identified one or more clusters, wherein the cognitive load score for the input visual stimulus increases as the sizes of the identified one or more clusters increases. ### Claim 9 (depends on 8) The apparatus of claim 8 wherein calculating the sizes of the identified one or more clusters comprises: for each of the identified one or more clusters, identifying a centroid of that cluster, drawing lines to form a polygon around border feature points of that cluster, and calculating an area within the polygon; and normalizing the areas of the polygons for the identified one or more clusters. ### Claim 10 (depends on 1) The apparatus of claim 1 wherein determining the cognitive load score comprises determining text complexity scores for one or more areas of the input visual stimulus. ### Claim 11 (depends on 1) The apparatus of claim 1 wherein determining the cognitive load score comprises determining a weighted average of two or more cognitive load score components, the two or more cognitive load score components comprising two or more of: a normalized number of the identified one or more clusters; an average normalized distance between the identified one or more clusters; and an average normalized size of the identified one or more clusters. ### Claim 12 (depends on 11) The apparatus of claim 11 wherein the two or more cognitive load score components further comprises an average normalized readability score of the input visual stimulus. ### Claim 13 (depends on 1) The apparatus of claim 1 wherein modifying the design of the input visual stimulus comprises modifying the identified one or more clusters of feature points to reach a target cognitive load score, the target cognitive load score being personalized for a given end-user viewing the input visual stimulus. ### Claim 14 (depends on 1) The apparatus of claim 1 wherein modifying the design of the input visual stimulus to adjust the cognitive load score of the input visual stimulus comprises at least one of: modifying a number of the identified one or more clusters; modifying a distance between a first one of the identified one or more clusters and a second one of the identified one or more clusters; and modifying a size of at least one of the identified one or more clusters. ### Claim 15 A computer program product comprising a non-transitory processor-readable storage medium having stored therein program code of one or more software programs, wherein the program code when executed by at least one processing device causes the at least one processing device to perform steps of: obtaining an information density matrix for an input visual stimulus, the information density matrix characterizing information density of feature points in the input visual stimulus; identifying one or more clusters of feature points in the input visual stimulus by performing spatial clustering of the feature points utilizing the information density matrix; determining a cognitive load score for the input visual stimulus based at least in part on the identified one or more clusters of feature points, the cognitive load score characterizing cognitive energy required to mentally process the input visual stimulus; and modifying a design of the input visual stimulus to adjust the cognitive load score of the input visual stimulus. ### Claim 16 (depends on 15) The computer program product of claim 15 wherein determining the cognitive load score comprises determining a weighted average of two or more cognitive load score components, the two or more cognitive load score components comprising two or more of: a normalized number of the identified one or more clusters; an average normalized distance between the identified one or more clusters; and an average normalized size of the identified one or more clusters. ### Claim 17 (depends on 15) The computer program product of claim 15 wherein modifying the design of the input visual stimulus comprises modifying the identified one or more clusters of feature points to reach a target cognitive load score, the target cognitive load score being personalized for a given end-user viewing the input visual stimulus. ### Claim 18 A method comprising steps of: obtaining an information density matrix for an input visual stimulus, the information density matrix characterizing information density of feature points in the input visual stimulus; identifying one or more clusters of feature points in the input visual stimulus by performing spatial clustering of the feature points utilizing the information density matrix; determining a cognitive load score for the input visual stimulus based at least in part on the identified one or more clusters of feature points, the cognitive load score characterizing cognitive energy required to mentally process the input visual stimulus; and modifying a design of the input visual stimulus to adjust the cognitive load score of the input visual stimulus; wherein the method is performed by at least one processing device comprising a processor coupled to a memory. ### Claim 19 (depends on 18) The method of claim 18 wherein determining the cognitive load score comprises determining a weighted average of two or more cognitive load score components, the two or more cognitive load score components comprising two or more of: a normalized number of the identified one or more clusters; an average normalized distance between the identified one or more clusters; and an average normalized size of the identified one or more clusters. ### Claim 20 (depends on 18) The method of claim 18 wherein modifying the design of the input visual stimulus comprises modifying the identified one or more clusters of feature points to reach a target cognitive load score, the target cognitive load score being personalized for a given end-user viewing the input visual stimulus.