# Apple recognized text: connect a phone number or web address to the right action

US12001642B2 links recognized text, image coordinates, text types and user input to contextual menus and actions.

Source: https://www.iplexlaw.co.kr/en/blog/apple-recognized-text-contextual-actions

HOME / NEWS & INSIGHTS NEWS & INSIGHTS Apple recognized text: connect a phone number or web address to the right action US12001642B2 links recognized text, image coordinates, text types and user input to contextual menus and actions. Artificial Intelligence 2026.11.17 published IPLEX 7 min read Recognized text must remain associated with its location and type. Recognizing characters in a photograph is only the first step. Apple’s patent describes how a device associates text with its visible position and type, then offers an appropriate operation when the user selects it. 1. From poster pixels to usable text Imagine a photograph of an event poster containing a title, telephone number and web address. OCR produces text, but the interface still needs to determine which visible line the user means. Apple’s US12001642B2, granted on 4 June 2024, describes interactions with recognized text in images and camera previews. The focus here is the interface workflow, not a claim that it introduces a new OCR algorithm. The useful chain runs from recognition through location and text-type interpretation to user selection and an action. Each step can succeed or fail independently. 2. Keep text aligned with the image Figure 6C illustrates recognized regions and the visual prominence of text, including its size and position. These properties can affect which text is emphasized. Figure 6D addresses a changed view. As the image or preview changes, displayed text regions and the visible content must remain associated. Recognizing the correct string is insufficient if a tap selects the adjacent line. The interface needs a reliable relationship between coordinates and text. 3. Text type guides the available operations The patent describes data detectors that can use regular-expression patterns to identify types such as phone numbers or email addresses. Formats vary by region and context. In Figure 6C, indications such as underlining identify detected address or telephone content. Figures 6N and 6O connect telephone-related input with calling or a menu including calling, messaging, adding a contact and copying. Figure 6L also illustrates ordinary text operations such as copying or sharing. Type detection narrows relevant choices; it does not mean every numeric string should initiate a call. 4. Three choices on a hypothetical poster A user may press and hold the event name to copy it, select the number for calling or copying, and select the web address to open a browser. The illustration separates the selected region, interpreted type and available operation. Different lines in one photograph therefore lead to different choices. These actions follow user input. Reading a number from a camera image alone is not the same as automatically making a telephone call. 5. Read alongside Apple’s public documentation Apple’s iPhone guide describes selecting, copying, sharing and translating text in photos or paused video. A separate camera guide explains using the text-recognition control in a live view. A hypothetical poster shows copying, telephone choices and a web link as distinct interactions. The WWDC 2022 VisionKit presentation distinguishes image analysis from interaction and describes workflows such as mapping an address, dialing a number or opening a URL. These materials help explain the user-facing concepts. They do not, by themselves, establish which particular patent claims a specific product version implements. 6. Evaluate the entire interaction chain Assess OCR, coordinate alignment, type classification and the resulting operation separately. Correct text on the wrong line and an order number mistaken for a phone number are different errors. Test glare, partial obstruction, zoom and rotation, including whether selection remains aligned as the view changes. Information shown before an external action also matters to informed user choice. A technical disclosure should identify the data flow, state conditions, coordinate association and action selection. Controlled image comparisons can show which step improves the interaction rather than treating all outcomes as OCR accuracy. The original figure labels and forms are preserved; the text explains the source material. The event poster is hypothetical. Public product documentation explains related functions without establishing implementation of particular patent claims. USPTO patent US12001642B2 Apple guide: text in photos and videos Apple guide: Live Text in Camera WWDC 2022: Live Text interaction with VisionKit Naver’s image-translation patent: keeping translated text aligned with a moving camera Google’s document-understanding patent: reading the layout of headings, text and images together Explore IPLEX’s AI projects and consultation materials for document recognition and interfaces that connect perception to action. Explore our AI and patent practice Original Tistory article Read the Korean source This article reflects the information available when it was published. Contact us to discuss your circumstances. Discuss this topic ↗ All articles ON THIS PAGE 1. From poster pixels to usable text 2. Keep text aligned with the image 3. Text type guides the available operations 4. Three choices on a hypothetical poster 5. Read alongside Apple’s public documentation 6. Evaluate the entire interaction chain TALK TO IPLEX Discuss your IP questions We consider your technology and business needs together. ↗ Contact us Newer Trademark filing in Hungary: procedure, opposition and renewal ↗ Older Customer photographs and Korea’s design disclosure exception ↗ Related insights Artificial Intelligence 2026.11.19 Matryoshka embeddings for image retrieval: shortlist with a prefix, rerank with the full vector A practical reading of Matryoshka Representation Learning, its nested training objective and the ImageNet-1K retrieval results reported at NeurIPS 2022. ↗ Read article Artificial Intelligence 2026.11.18 ByteDance’s captioning patent: transcribing separate tracks and resolving overlapping display times How US11837234B2 processes selected audio tracks and adjusts caption timing, with a practical distinction between patent disclosure and CapCut’s public guidance. ↗ Read article Artificial Intelligence 2026.11.16 Hyundai Mobis: infer passenger activity before adjusting the cabin US12233843B2 combines cropped image features to recognize passenger states and control lighting, seats and variable-tint glazing. ↗ Read article

- https://www.iplexlaw.co.kr/en
- https://www.iplexlaw.co.kr/en/blog/category/ai
- https://image-ppubs.uspto.gov/dirsearch-public/print/downloadPdf/12001642
- https://support.apple.com/en-gb/guide/iphone/iph37fdd714b/ios
- https://support.apple.com/guide/iphone/use-live-text-iphcf0b71b0e/ios
- https://developer.apple.com/videos/play/wwdc2022/10026/
- https://www.iplexlaw.co.kr/en/blog/naver-papago-ar-image-translation
- https://www.iplexlaw.co.kr/en/blog/google-layout-aware-document-understanding
- https://www.iplexlaw.co.kr/en/ai-patents
- https://iplexlaw.tistory.com/29
- https://www.iplexlaw.co.kr/ko/blog/apple-recognized-text-contextual-actions
- https://www.iplexlaw.co.kr/en/contact
- https://www.iplexlaw.co.kr/en/blog
- https://www.iplexlaw.co.kr/en/blog/apple-recognized-text-contextual-actions#article-29-en-0
- https://www.iplexlaw.co.kr/en/blog/apple-recognized-text-contextual-actions#article-29-en-1
- https://www.iplexlaw.co.kr/en/blog/apple-recognized-text-contextual-actions#article-29-en-2
- https://www.iplexlaw.co.kr/en/blog/apple-recognized-text-contextual-actions#article-29-en-3
- https://www.iplexlaw.co.kr/en/blog/apple-recognized-text-contextual-actions#article-29-en-4
- https://www.iplexlaw.co.kr/en/blog/apple-recognized-text-contextual-actions#article-29-en-5
- https://www.iplexlaw.co.kr/en/contact
- https://www.iplexlaw.co.kr/en/blog/hungary-trademark-filing-guide
- https://www.iplexlaw.co.kr/en/blog/brunch-case-1969
- https://www.iplexlaw.co.kr/en/blog/matryoshka-prefix-vector-image-retrieval
- https://www.iplexlaw.co.kr/en/blog/matryoshka-prefix-vector-image-retrieval
- https://www.iplexlaw.co.kr/en/blog/bytedance-track-based-caption-timing
- https://www.iplexlaw.co.kr/en/blog/bytedance-track-based-caption-timing
- https://www.iplexlaw.co.kr/en/blog/hyundai-mobis-occupant-state-cabin-control
- https://www.iplexlaw.co.kr/en/blog/hyundai-mobis-occupant-state-cabin-control
