optical character recognition

Winsage
August 11, 2026
Microsoft PowerToys has introduced on-device support for Phi Silica, a small language model, in its latest preview version, enhancing the Advanced Paste feature for clipboard management. Advanced Paste can format clipboard content in various formats, extract text from images using OCR, and transcode audio and video files. It now supports multiple AI models, including local options like Foundry Local and Ollama. The latest version, PowerToys v0.101.2211.0, includes improvements such as enhanced AI customization for Advanced Paste, better dialog handling in the Command Palette, and improved window management features. Mouse Jump has transitioned to the newer WinUI app architecture, and new settings have been added for update channel selection and bug reporting.
AppWizard
July 31, 2026
Bitsight's investigation revealed that inexpensive Android TV boxes are being shipped with applications that can change their hardware identity, allowing them to impersonate popular smartphone brands like Samsung and Huawei. This operation, named Fuyao, is linked to Zhejiang Fengwo IoT Technology Co., Ltd., a Chinese company established in 2019. The H96MAXV11 model was frequently reported among the affected devices. In one day, the operation received 65,957 reports from about 38,000 unique MAC addresses, with many devices misidentified as phones due to spoofed identifiers. Fengwo has also promoted over 120,000 "AI digital humans," though details on this marketing term are vague. The command-and-control server for Fuyao sends phone profiles to devices, masking their actual hardware specifications. The operation uses machine vision technology and a YOLOv8s object-detection model to identify advertisements. Bitsight documented 40 fraud tasks, 21 unique campaigns, and 166 modules across four devices. The operation's payout structure involves 144 operator-owned domains, with an estimated gross return of .25 per device daily, potentially leading to annual revenues in the millions. Attribution to Fengwo is supported by shared TLS certificate data and public patent records, although the patents do not directly address advertising. There is uncertainty about how the fraudulent apps were installed and at what point in the supply chain they were introduced. Device owners are advised to verify Play Protect certification and disconnect suspicious devices.
Winsage
June 25, 2026
Raycast for Windows, a productivity app, was initially a valuable tool for launching applications and executing actions quickly. However, the introduction of the Command Palette in Microsoft PowerToys provided similar functionality, leading to Raycast being less essential for the user's needs. The user found that the Command Palette effectively served as a fast app launcher, integrating well with other PowerToys features. The user also transitioned from GlazeWM, a tiling window manager, to FancyZones in PowerToys for better window management, as FancyZones offered more tailored window layout options. Additionally, Text Extractor in PowerToys streamlined the user's optical character recognition (OCR) tasks by allowing easy text extraction from images. Overall, PowerToys consolidated several utilities into one suite, enhancing the user's productivity while reducing the need for multiple separate applications.
AppWizard
June 17, 2026
Adobe Acrobat Reader has been integrated into Android Auto with the v26.5.0.45958 update. Full access to its features requires a subscription, but non-subscribers can use limited free features, including accessing scanned PDFs in Liquid Mode, annotating documents, signing PDFs, and connecting to Google Drive. Visual functions are disabled on the car's screen for safety, but a "Read Aloud" text-to-speech engine is available for free users. Paid subscribers can access high-quality voices, Adobe's AI assistant for file management, a complete mobile editing suite, optical character recognition (OCR), and additional tools, although advanced features are currently not accessible through the dashboard.
Winsage
April 6, 2026
AI PCs with Neural Processing Units (NPUs) are becoming common in technology, enabling innovative applications that utilize on-device AI. Microsoft's Windows AI APIs facilitate easy integration of AI into applications, requiring only a Copilot+ PC with a capable NPU. Lance McCarthy, a Microsoft MVP, highlights tools available for developers, including Phi Silica for local language modeling, AI Text Recognition for OCR, and AI Imaging tools for image processing. McCarthy's Xkcd Viewer app exemplifies these tools, featuring AI-powered image descriptions for visually impaired users, which enhance the experience beyond simple text readouts. The modification of the app took ten minutes and significantly improved user accessibility.
Winsage
March 20, 2026
Microsoft PowerToys is a utility that enhances the Windows experience with additional features. It was first introduced with Windows 95, revived in 2019 as an open-source tool, and is available for free download from the Microsoft Store or GitHub. Key features of PowerToys include: - Pin important windows on top: Users can pin active windows above others using the shortcut Win+Ctrl+T, allowing for better focus on key tasks. - Resize images: The Image Resizer tool allows users to resize images to specific dimensions through right-click options, with presets for Fill, Fit, or Stretch. - Extract text from the screen: The Text Extractor uses Optical Character Recognition (OCR) to copy text directly from anywhere on the screen by selecting the area with Win+T. - Control multiple computers: The Mouse Without Borders feature enables users to control up to four computers with a single set of peripherals and share clipboard and files. - Customize shortcuts: The Keyboard Manager allows users to remap keys and shortcuts, though some keys are reserved for system functions. - Batch rename files: PowerRename enables users to rename multiple files at once through a right-click option, with a preview of changes. - Thumbnail and preview pane previews: PowerToys enhances file previews in File Explorer for additional file types and adds thumbnail support for files that Windows Explorer does not natively generate thumbnails for. - Crop and Lock: This feature allows users to crop application windows to focus on specific content, with two modes: Thumbnail mode for static previews and Reparent mode for functional cropped windows. PowerToys continues to be a valuable tool for enhancing productivity on Windows.
Search