# US 2020/0401783 A1 · Fake finger detection using ridge features > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2020/0401783 A1 - Document ID: US20200401783A1 - Status: Published application - Kind: A1 - Application number: 16/909,917 - Filed: 2020-06-23 - Published: 2020-12-24 - Earliest claimed: 2019-06-24 - Assignees: InvenSense, Inc. - Applicants: InvenSense, Inc. - Inventors: Sina AKHBARI; Lingtao WANG; Mei-Lin CHAN; Nikhil APTE - Web page: https://patentgrep.com/patent/US20200401783A1 ## CPC - G06V 40/1394: {using acquisition arrangements} - G06V 40/1306: {non-optical, e.g. ultrasonic or capacitive sensing} - G06V 40/1359: {Extracting features related to ridge properties; Determining the fingerprint type, e.g. whorl or loop} - G06V 40/1382: {Detecting the live character of the finger, i.e. distinguishing from a fake or cadaver finger} - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## Abstract In a method for determining whether a finger is a real finger at an ultrasonic fingerprint sensor, a first image of a fingerprint pattern is captured at an ultrasonic fingerprint sensor, wherein the first image is based on ultrasonic signals corresponding to a first time of flight range. A second image of the fingerprint pattern is captured at the ultrasonic fingerprint sensor, wherein the second image is based on ultrasonic signals corresponding to a second time of flight range, the second time of flight range being delayed compared to the first time of flight range. A difference in a width of ridges of the fingerprint pattern in the first image compared to the width of ridges of the fingerprint pattern in the second image is quantified. Based on the quantification of the difference, a probability whether the finger is a real finger is determined. ## Claims ### Claim 1 A method for determining whether a finger is a real finger at a fingerprint sensor, the method comprising: capturing a first image of a fingerprint pattern at an ultrasonic fingerprint sensor, wherein the first image is based on ultrasonic signals corresponding to a first time of flight range; capturing a second image of the fingerprint pattern at the ultrasonic fingerprint sensor, wherein the second image is based on ultrasonic signals corresponding to a second time of flight range, the second time of flight range being delayed compared to the first time of flight range; quantifying a difference in a width of ridges of the fingerprint pattern in the first image compared to the width of ridges of the fingerprint pattern in the second image; and based on the quantification of the difference, determining a probability whether the finger is a real finger. ### Claim 2 (depends on 1) The method of claim 1, wherein the quantifying the difference in the width of the ridges of the fingerprint pattern in the first image compared to the width of ridges of the fingerprint pattern in the second image comprises: determining a difference between the first image and the second image; determining a first signal strength at a first spatial frequency range of at least one of the first image and the second image; determining a second signal strength at a second spatial frequency range of the difference between the first image and the second image; and comparing the first signal strength to the second signal strength; and determining, based on the comparing, the probability that the finger is a real finger. ### Claim 3 (depends on 2) The method of claim 2, wherein the comparing the first signal strength to the second signal strength comprises: determining a ratio of the second signal strength to the first signal strength; and provided the ratio satisfies a ratio range threshold, determining that the finger is a real finger. ### Claim 4 (depends on 2) The method of claim 2, wherein the probability that the finger is a real finger is based on the ratio of the second signal strength to the first signal strength, wherein the probability that the finger is a real finger increases as the ratio of the second signal strength to the first signal strength increases. ### Claim 5 (depends on 3) The method of claim 3, wherein the ratio range threshold is above 0.8. ### Claim 6 (depends on 2) The method of claim 2, wherein the second spatial frequency range is distributed around a frequency substantially double a main frequency contribution of the first spatial frequency range. ### Claim 7 (depends on 2) The method of claim 2, wherein the first spatial frequency range corresponds to a spatial ridge frequency range of the fingerprint pattern. ### Claim 8 (depends on 2) The method of claim 2, wherein the first signal strength corresponds to a maximum in signal strength of the first spatial frequency range and wherein the second signal strength corresponds to a maximum in signal strength of the second spatial frequency range. ### Claim 9 (depends on 2) The method of claim 2, wherein the determining the difference between the first image and the second image: generating a difference image by subtracting the second image from the first image. ### Claim 10 (depends on 9) The method of claim 9, wherein the determining second signal strength at the second spatial frequency range of the difference between the first image and the second image comprises: determining the second signal strength at the second spatial frequency of the of the difference image. ### Claim 11 (depends on 1) The method of claim 1, wherein the quantifying the difference in the width of the ridges of the fingerprint pattern in the first image compared to the width of ridges of the fingerprint pattern in the second image comprises: determining a first average width of ridges of the fingerprint pattern of the first image; determining a second average width of ridges of the fingerprint pattern of the second image; and quantifying a difference between the first average width and the second average width. ### Claim 12 (depends on 11) The method of claim 11, wherein the quantifying the difference between the first average width and the second average width comprises: determining a ratio of the first average width to the second average width. ### Claim 13 (depends on 12) The method of claim 12, wherein the determining the probability whether the finger is a real finger comprises: comparing of the ratio of the first average width and the second average width to a width range threshold. ### Claim 14 An ultrasonic fingerprint sensor device comprising: a two-dimensional array of ultrasonic transducers; and a processor, wherein the processor is configured to: capture a first image of a fingerprint pattern at an ultrasonic fingerprint sensor, wherein the first image is based on ultrasonic signals corresponding to a first time of flight range; capture a second image of the fingerprint pattern at the ultrasonic fingerprint sensor, wherein the second image is based on ultrasonic signals corresponding to a second time of flight range, the second time of flight range being delayed compared to the first time of flight range; quantify a difference in a width of ridges of the fingerprint pattern in the first image compared to the width of ridges of the fingerprint pattern in the second image; and based on the quantification of the difference, determine a probability whether the finger is a real finger. ### Claim 15 (depends on 14) The ultrasonic fingerprint sensor device of claim 14, wherein the processor is further configured to: determine a difference between the first image and the second image; determine a first signal strength at a first spatial frequency range of at least one of the first image and the second image; determine a second signal strength at a second spatial frequency range of the difference between the first image and the second image; and compare the first signal strength to the second signal strength; and determine, based on the compare, the probability that the finger is a real finger. ### Claim 16 (depends on 15) The ultrasonic fingerprint sensor device of claim 15, wherein the processor is further configured to: determine a ratio of the second signal strength to the first signal strength; and provided the ratio satisfies a ratio range threshold, determine that the finger is a real finger. ### Claim 17 (depends on 15) The ultrasonic fingerprint sensor device of claim 15, wherein the probability that the finger is a real finger is based on the ratio of the second signal strength to the first signal strength, wherein the probability that the finger is a real finger increases as the ratio of the second signal strength to the first signal strength increases. ### Claim 18 (depends on 15) The ultrasonic fingerprint sensor device of claim 15, wherein the second frequency range is distributed around a frequency substantially double a main frequency contribution of the first frequency range. ### Claim 19 (depends on 14) The ultrasonic fingerprint sensor device of claim 14, wherein the processor is further configured to: determine a first average width of ridges of the fingerprint pattern of the first image; determine a second average width of ridges of the fingerprint pattern of the second image; and quantify a difference between the first average width and the second average width. ### Claim 20 A non-transitory computer readable storage medium having computer readable program code stored thereon for causing a computer system to perform a method for determining whether a finger is a real finger at a fingerprint sensor, the method comprising: capturing a first image of a fingerprint pattern at an ultrasonic fingerprint sensor, wherein the first image is based on ultrasonic signals corresponding to a first time of flight range; capturing a second image of the fingerprint pattern at the ultrasonic fingerprint sensor, wherein the second image is based on ultrasonic signals corresponding to a second time of flight range, the second time of flight range being delayed compared to the first time of flight range; quantifying a difference in a width of ridges of the fingerprint pattern in the first image compared to the width of ridges of the fingerprint pattern in the second image; and based on the quantification of the difference, determining a probability whether the finger is a real finger.