# US 2019/0171907 A1 · Method, device and computer program product for generating image tag > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2019/0171907 A1 - Document ID: US20190171907A1 - Status: Published application - Kind: A1 - Application number: 16/172,158 - Filed: 2018-10-26 - Published: 2019-06-06 - Earliest claimed: 2017-10-27 - Assignees: EMC IP Holding Company LLC - Applicants: EMC IP Holding Company LLC - Inventors: Sanping Li; Junping Zhao - Web page: https://patentgrep.com/patent/US20190171907A1 ## CPC - G06F 16/583: using metadata automatically derived from the content - G06F 16/51: Indexing; Data structures therefor; Storage structures - G06F 16/5866: {using information manually generated, e.g. tags, keywords, comments, manually generated location and time information} - G06F 18/22: Matching criteria, e.g. proximity measures - G06V 10/751: {Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching} - G06V 10/761: {Proximity, similarity or dissimilarity measures} - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## Abstract Embodiments of the present disclosure relate to a method, a device and a computer readable medium for generating an image tag. According to the embodiments of the present disclosure, an index value of an image is determined based on contents of the image, similarities between a plurality of images is determined based on index values of the plurality of images, and thereby tags are generated for images. According to the embodiments of the present disclosure, images is further grouped depending on similarities between them. ## Claims ### Claim 1 A method for generating an image tag, comprising: determining, based on a first image, a first group of index values, each index value in the first group of index values indicating a content of each layer of a plurality of layers of the first image; determining, based on a second image, a second group of index values, each index value in the second group of index values indicating a content of each layer of a plurality of layers of the second image; determining a similarity between the first image and the second image based on the first group of index values and the second group of index values; and generating, based on the similarity, a tag associated with at least one of the first image and the second image. ### Claim 2 (depends on 1) The method of claim 1, wherein determining the first group of index values comprises: obtaining the content of each layer of the first image; and determining one index value for the content of each layer. ### Claim 3 (depends on 1) The method of claim 1, wherein determining a similarity between the first image and the second image comprises: obtaining a group of similarities by comparing at least one value in the first group of values with a group of candidate values in the second group, respectively; and determining the similarity between the first image and the second image based on the group of similarities. ### Claim 4 (depends on 1) The method of claim 1, wherein determining a similarity between the first image and the second image comprises: determining the similarity between the first image and the second image based on at least one of: a Hamming distance; an edit distance; an Euclidean distance; and an included angle cosine value. ### Claim 5 (depends on 1) The method of claim 1, wherein generating a tag associated with at least one of the first image and the second image comprises: in response to the similarity between the first image and the second image exceeding a first similarity threshold, assigning a first tag to the first image and the second image, respectively; and storing the first image and the second image in a same group. ### Claim 6 (depends on 5) The method of claim 5, further comprising: determining the number of images with the first tag in the group; and in response to the number of images with the first tag exceeding a threshold number, assigning the first tag to all images in the group. ### Claim 7 (depends on 1) The method of claim 1, wherein generating a tag associated with at least one of the first image and the second image comprises: in response to a content of the first image being known, determining a second tag indicating a content of the first image; and in response to a similarity between a content of the second image and the content of the first image exceeding a second similarity threshold, assigning the second tag to the second image. ### Claim 8 A device for generating an image tag, comprising: at least one processor; and a memory coupled to the at least one processor, the memory having instructions stored thereon, the instructions, when executed by the at least one processor, causing the device to perform acts including: determining, based on a first image, a first group of index values, each index value in the first group of index values indicating a content of each layer of a plurality of layers of the first image; determining, based on a second image, a second group of index values, each index value in the second group of index values indicating a content of each layer of a plurality of layers of the second image; determining a similarity between the first image and the second image based on the first group of index values and the second group of index values; and generating, based on the similarity, a tag associated with at least one of the first image and the second image. ### Claim 9 (depends on 8) The device of claim 8, wherein determining the first group of index values comprises: obtaining the content of each layer of the first image; and determining one index value for the content of the each layer. ### Claim 10 (depends on 8) The device of claim 8, wherein determining a similarity between the first image and the second image comprises: obtaining a group of similarities by comparing at least one value in the first group of values with a group of candidate values in the second group respectively; and determining the similarity between the first image and the second image based on the group of similarities. ### Claim 11 (depends on 8) The device of claim 8, wherein determining a similarity between the first image and the second image comprises: determining the similarity between the first image and the second image based on at least one of: a Hamming distance; an edit distance; an Euclidean distance; and an included angle cosine value. ### Claim 12 (depends on 8) The device of claim 8, wherein generating a tag associated with at least one of the first image and the second image comprises: in response to the similarity between the first image and the second image exceeding a first similarity threshold, assigning a first tag to the first image and the second image respectively; and storing the first image and the second image in a same group. ### Claim 13 (depends on 12) The device of claim 12, wherein the acts further comprise: determining the number of images with the first tag in the group; and in response to the number of images with the first tag exceeding a threshold number, assigning the first tag to all images in the group. ### Claim 14 (depends on 8) The device of claim 8, wherein generating a tag associated with at least one of the first image and the second image comprises: in response to a content of the first image being known, determining a second tag indicating the content of the first image; and in response to a similarity between a content of the second image and the content of the first image exceeding a second similarity threshold, assigning the second tag to the second image. ### Claim 15 A computer program product for generating an image tag, the computer program product comprising: a non-transitory computer readable medium encoded with computer-executable program code, the code configured to enable the execution of: determining, based on a first image, a first group of index values, each index value in the first group of index values indicating a content of each layer of a plurality of layers of the first image; determining, based on a second image, a second group of index values, each index value in the second group of index values indicating a content of each layer of a plurality of layers of the second image; determining a similarity between the first image and the second image based on the first group of index values and the second group of index values; and generating, based on the similarity, a tag associated with at least one of the first image and the second image. ### Claim 16 (depends on 15) The computer program product of claim 15, wherein determining the first group of index values comprises: obtaining the content of each layer of the first image; and determining one index value for the content of each layer. ### Claim 17 (depends on 15) The computer program product of claim 15, wherein determining a similarity between the first image and the second image comprises: obtaining a group of similarities by comparing at least one value in the first group of values with a group of candidate values in the second group, respectively; and determining the similarity between the first image and the second image based on the group of similarities. ### Claim 18 (depends on 15) The computer program product of claim 15, wherein determining a similarity between the first image and the second image comprises: determining the similarity between the first image and the second image based on at least one of: a Hamming distance; an edit distance; an Euclidean distance; and an included angle cosine value. ### Claim 19 (depends on 15) The computer program product of claim 15, wherein generating a tag associated with at least one of the first image and the second image comprises: in response to the similarity between the first image and the second image exceeding a first similarity threshold, assigning a first tag to the first image and the second image, respectively; and storing the first image and the second image in a same group. ### Claim 20 (depends on 19) The compute program product of claim 19, wherein the code is further configured to enable the execution of: determining the number of images with the first tag in the group; and in response to the number of images with the first tag exceeding a threshold number, assigning the first tag to all images in the group.