# US 11,029,781 B2 · System and method for detecting imperfections in a screen > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,029,781 B2 - Document ID: US11029781B2 - Status: Granted - Kind: B2 - Application number: 16/726,682 - Filed: 2019-12-24 - Published: 2020-04-30 - Granted: 2021-06-08 - Earliest claimed: 2018-01-11 - Assignees: ESW Holdings, Inc. - Applicants: Esw Holdings, Inc. - Inventors: Amit Gross; Oded Rozenberg; Moshe Lipsker - Web page: https://patentgrep.com/patent/US11029781B2 ## CPC - G06F 3/0418: {for error correction or compensation, e.g. based on parallax, calibration or alignment} - G01N 29/12: by measuring frequency or resonance of acoustic waves {(measuring frequency or resonant frequency of mechanical vibrations or acoustic waves in general G01H1/06, G01H3/04, G01H13/00; acoustic resonators G10K11/04; vibration or shock testing of structures G01M7/00)} - G01N 29/14: using acoustic emission techniques {(echo of particles G01N29/046; measuring mechanical vibrations or acoustic waves in solids in general G01H1/00)} - G01N 29/46: by spectral analysis, e.g. Fourier analysis {or wavelet analysis (spectral signal processing per se G06F17/14)} - G01N 2291/2697: Wafer or (micro)electronic parts - G06F 3/04883: for inputting data by handwriting, e.g. gesture or text - G06F 2203/04103: Manufacturing, i.e. details related to manufacturing processes specially suited for touch sensitive devices - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G01N: INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES (measuring or testing apparatus or processes other than immunoassay, involving enzymes or microorganisms C12M, C12Q) ## Abstract A method and system for detecting imperfections on a surface of a touchscreen of an electrical device, comprising: swiping a test object, such as a fingertip, a fingernail or a pin, along at least a portion of the touchscreen; producing, by the touchscreen, an electric signal indicative of the test object's contact with the touchscreen; receiving an acoustic signal by an acoustic sensor, during the swipe of the test object along the touchscreen; analyzing, by a processor, at least one of the electric signal and received acoustic signal; and determining existence of imperfections on the touchscreen's surface based on the analysis. ## Claims ### Claim 1 A method of detecting imperfections on a surface of a touchscreen of an electrical device, comprising: producing, by the touchscreen, an electric signal indicative of an object's contact with the touchscreen; receiving an acoustic signal by an acoustic sensor, during the contact of the object with the touchscreen; analyzing, by a processor, at least one of the electric signal and received acoustic signal, wherein the analyzing includes: referencing an initial group of labeled touchscreens, comprising at least one touchscreen with at least one known imperfection, and at least one touchscreen without imperfections, wherein: at least one feature has been extracted from an electric signal relating to each touchscreen of the initial group of labeled touchscreens; each touchscreen of the labeled group of touchscreens has been classified to classes according to said at least one feature; each class is associated with touchscreens having or not having imperfections; producing an additional electric signal, from an additional unlabeled touchscreen; extracting, by a processor, the at least one feature from the additional electric signal of the additional unlabeled touchscreen; and associating, by a processor, the additional touchscreen with a class of touchscreens having or not having imperfections; and determining an existence of imperfections on the touchscreen's surface based on the analysis. ### Claim 2 (depends on 1) The method of claim 1, further comprising: presenting a pattern on the touchscreen and prompting a user to swipe a test object along the presented pattern; analyzing, by a processor, the electric signal, indicative of the test object's contact with the touchscreen; verifying follow of the test object's swipe along the presented pattern, based on the analysis; and prompting the user to repeat the swipe along at least a portion of the presented pattern, when the verification has failed. ### Claim 3 (depends on 1) The method of claim 1, further comprising: detecting whether a screen cover is applied to the touchscreen, based on analysis of data received from the acoustic sensor; and prompting a user to remove the cover and repeat the swipe when a screen cover has been detected. ### Claim 4 (depends on 1) The method of claim 1, wherein determining the existence of imperfections based on the analysis further comprises: extracting, by a processor, values of at least one parameter of the acoustic signal; and determining existence of imperfections when the extracted values are within at least one predetermined range. ### Claim 5 (depends on 1) The method of claim 1, wherein analysis of the electric signal further comprises: forming the initial group of labeled touchscreens, comprising at least one touchscreen with at least one known imperfection, and at least one touchscreen without imperfections; extracting, by a processor, the at least one feature from the electric signal relating to each touchscreen of the initial group of labeled touchscreens; and classifying each touchscreen of the labeled group of touchscreens to classes according to said at least one feature, wherein each class is associated with touchscreens having or not having imperfections. ### Claim 6 (depends on 1) The method of claim 1, wherein the object comprises a test object, and the method further comprises swiping the test object along at least a portion of the touchscreen, wherein the swiping represents the object's contact with the touchscreen. ### Claim 7 (depends on 1) The method of claim 1, wherein said analyzing comprises analyzing by the processor of the electric signal, indicative of the test object's contact with the touchscreen, to detect a circumference of the test object's contact area with the touchscreen. ### Claim 8 (depends on 7) The method of claim 7, further comprising: defining at least one requirement for the circumference of the test object's contact area with the touchscreen; and when the requirement is not met, prompting a user to apply changes to the test object to meet the defined requirement. ### Claim 9 (depends on 1) The method of claim 1, analysis of the acoustic signal further comprises: forming an initial group of labeled touchscreens, comprising at least one touchscreen with at least one known imperfection, and at least one touchscreen without imperfections; extracting, by a processor, at least one feature from the acoustic signal relating to each touchscreen of the initial group of labeled touchscreens; classifying each touchscreen of the labeled group of touchscreens to classes according to said at least one feature, wherein each class is associated with touchscreens having or not having imperfections; receiving an additional acoustic signal, from an additional unlabeled touchscreen; extracting the at least one feature from the additional acoustic signal of the additional unlabeled touchscreen; and associating the additional touchscreen with a class of touchscreens having or not having imperfections. ### Claim 10 (depends on 9) The method of claim 9, wherein the at least one feature includes at least one of: frequencies, amplitudes, Fast Fourier Transform (FFT) coefficients, Discrete Fourier Transform (DPT) coefficients, Discrete Cosine Transform (DCT) coefficients, Discrete Wavelet Transform (DWT) coefficients, and Mel-Frequency Cepstral Coefficients (MFCC). ### Claim 11 (depends on 1) The method of claim 1, wherein the object comprises a test object, and the method further comprises swiping the test object along at least a portion of the touchscreen, wherein the swiping represents the object's contact with the touchscreen. ### Claim 12 A method comprising: constructing device that is configured to detect imperfections on a surface of a touchscreen of an electrical device in accordance with a process comprising: producing, by the touchscreen, an electric signal indicative of an object's contact with the touchscreen; receiving an acoustic signal by an acoustic sensor, during the contact of the object with the touchscreen; analyzing, by a processor, at least one of the electric signal and received acoustic signal, wherein the analyzing includes: referencing an initial group of labeled touchscreens, comprising at least one touchscreen with at least one known imperfection, and at least one touchscreen without imperfections, wherein: at least one feature has been extracted from an electric signal relating to each touchscreen of the initial group of labeled touchscreens; each touchscreen of the labeled group of touchscreens has been classified to classes according to said at least one feature; each class is associated with touchscreens having or not having imperfections; producing an additional electric signal, from an additional unlabeled touchscreen; extracting, by a processor, the at least one feature from the additional electric signal of the additional unlabeled touchscreen; and associating, by a processor, the additional touchscreen with a class of touchscreens having or not having imperfections; and determining an existence of imperfections on the touchscreen's surface based on the analysis. ### Claim 13 (depends on 12) The method of claim 12, further comprising: presenting a pattern on the touchscreen and prompting a user to swipe a test object along the presented pattern; analyzing, by a processor, the electric signal, indicative of the test object's contact with the touchscreen; verifying follow of the test object's swipe along the presented pattern, based on the analysis; and prompting the user to repeat the swipe along at least a portion of the presented pattern, when the verification has failed. ### Claim 14 (depends on 12) The method of claim 12, further comprising: detecting whether a screen cover is applied to the touchscreen, based on analysis of data received from the acoustic sensor; and prompting a user to remove the cover and repeat the swipe when a screen cover has been detected. ### Claim 15 (depends on 12) The method of claim 12, wherein determining the existence of imperfections based on the analysis further comprises: extracting, by a processor, values of at least one parameter of the acoustic signal; and determining existence of imperfections when the extracted values are within at least one predetermined range. ### Claim 16 (depends on 12) The method of claim 12, wherein analysis of the electric signal further comprises: forming the initial group of labeled touchscreens, comprising at least one touchscreen with at least one known imperfection, and at least one touchscreen without imperfections; extracting, by a processor, the at least one feature from the electric signal relating to each touchscreen of the initial group of labeled touchscreens; and classifying each touchscreen of the labeled group of touchscreens to classes according to said at least one feature, wherein each class is associated with touchscreens having or not having imperfections. ### Claim 17 (depends on 12) The method of claim 12, wherein said analyzing comprises analyzing by the processor of the electric signal, indicative of the test object's contact with the touchscreen, to detect a circumference of the test object's contact area with the touchscreen. ### Claim 18 (depends on 17) The method of claim 17, further comprising: defining at least one requirement for the circumference of the test object's contact area with the touchscreen; and when the requirement is not met, prompting a user to apply changes to the test object to meet the defined requirement. ### Claim 19 (depends on 12) The method of claim 12, analysis of the acoustic signal further comprises: forming an initial group of labeled touchscreens, comprising at least one touchscreen with at least one known imperfection, and at least one touchscreen without imperfections; extracting, by a processor, at least one feature from the acoustic signal relating to each touchscreen of the initial group of labeled touchscreens; classifying each touchscreen of the labeled group of touchscreens to classes according to said at least one feature, wherein each class is associated with touchscreens having or not having imperfections; receiving an additional acoustic signal, from an additional unlabeled touchscreen; extracting the at least one feature from the additional acoustic signal of the additional unlabeled touchscreen; and associating the additional touchscreen with a class of touchscreens having or not having imperfections. ### Claim 20 (depends on 19) The method of claim 19, wherein the at least one feature includes at least one of: frequencies, amplitudes, Fast Fourier Transform (FFT) coefficients, Discrete Fourier Transform (DPT) coefficients, Discrete Cosine Transform (DCT) coefficients, Discrete Wavelet Transform (DWT) coefficients, and Mel-Frequency Cepstral Coefficients (MFCC).