This article introduces ddddocr, an open‑source deep‑learning OCR library for recognizing double‑digit numbers, explains its background, key features, installation steps, and provides detailed PHP examples for basic OCR, target detection, and slider detection functionalities.
The article details progressive front‑end watermark schemes—from a basic canvas overlay to mutation‑observer‑protected, hide‑ and cover‑resistant, and low‑opacity dark watermarks—and explains how adaptive tone handling, contrast tuning, region cropping, and a hybrid OCR pipeline (internal service with tesseract.js fallback) ensure robust, invisible data protection and accurate screenshot analysis.
This guide explains how to set up a Spring Boot project, add the Tess4J dependency, configure language data, implement an OCR service and REST controller, and test both local file uploads and remote image URLs for text recognition.
This tutorial explains how to create an automatic math‑grading tool in Python by generating synthetic digit images, training a small CNN on the data, segmenting handwritten equations with projection techniques, recognizing characters, evaluating the expressions, and overlaying the results back onto the original image.
MegaParse is an open‑source document parser that transforms PDFs, Word, PPT, Excel and CSV files into LLM‑friendly formats, preserving full information, boosting processing efficiency, and enabling deeper semantic analysis, with quick‑start installation steps and a roadmap for future features.
PDF‑Extract‑Kit is an open‑source toolkit that combines high‑accuracy layout detection, formula detection, formula recognition, and OCR for PDFs, and the article details its model comparisons, evaluation on academic and textbook datasets, and step‑by‑step instructions for running it on Windows or macOS, including Apple Silicon.
Meituan's tech team highlights seven CVPR 2024 papers—spanning OCR pre‑training, long‑tail semi‑supervised learning, visual AIGC, audio‑visual segmentation and synthetic‑data detection—provides detailed abstracts and experimental results, and announces an online author‑talk session on June 27.
This article walks through creating a server‑side license‑plate recognition system using Spring Boot 3.x, the open‑source Tesseract OCR library, and OpenCV for image preprocessing, covering project goals, Maven dependencies, core service implementations, special‑plate handling, and a REST API controller.
This tutorial walks through building a self‑trained OCR pipeline that generates synthetic digit images, trains a CNN model, segments handwritten math expressions, predicts each character, evaluates the arithmetic result, and overlays checkmarks, crosses or answers onto the original image.
This guide shows how to integrate the open‑source Tesseract OCR engine into a Spring Boot application using the Tess4J Java wrapper, covering Chinese language data setup, Maven dependency configuration, bean creation, service implementation, and a unit test to verify image text extraction.
This tutorial walks through setting up a Spring Boot backend, adding the Tess4J OCR library, creating a service and REST controller to recognize text from both local files and remote image URLs, and provides testing steps and deployment tips.
This guide demonstrates how to integrate Tess4J OCR into a Spring Boot application, covering environment setup, Maven dependencies, adding language data, creating an OCR service class, building REST endpoints for local and remote image processing, and testing the solution.
This guide walks through setting up a Spring Boot project, adding Tess4J dependencies, configuring language data, implementing an OCR service class, exposing REST endpoints for local and remote image recognition, and testing the OCR functionality end‑to‑end.
This guide explains step‑by‑step how to install required Python libraries, extract text and images from a PDF, perform OCR on the images, locate embedded MP3 data in the combined text, and save the audio file, providing complete sample code for each stage.
This guide walks through installing Anaconda, creating a Python 3.10 conda environment, adding PyTorch and ModelScope libraries, installing domain-specific dependencies, verifying NLP pipelines, and using PHPY to call ModelScope's OCR model from PHP, complete with code snippets and troubleshooting tips.
This tutorial demonstrates how to use Python's urllib to download captcha images, apply pytesseract OCR for text extraction, and integrate the result into Selenium scripts to automate the entry of image captchas during web testing.
An OCR‑based video review system using PaddleOCR’s DB detector and SVTR recognizer, combined with multi‑level frame deduplication, message‑queue task decoupling, Redis prioritization, and dynamic thread‑pool scheduling, was fine‑tuned on 5 000 samples to cut daily frames from 794 million to 3.6 million, achieving automated detection of over 230 abnormal videos per day and replacing three manual reviewers, with future plans for GPU acceleration and cross‑instance GRPC dispatch.
At ICDAR 2023, Tencent's OCR team leveraged self‑developed algorithms and large‑model backbones to clinch four official championship titles across the DSText and SVRD tracks, showcasing breakthroughs in dense video text detection, tracking, end‑to‑end recognition, and structured information extraction.
This article describes the design and implementation of a Document Analytics & Anti‑Fraud Support platform for Hong Kong virtual banking, detailing its OCR/NLP‑driven pipeline, dynamic rule engine, multi‑template PDF processing, model training, and the resulting improvements in fraud detection and operational efficiency.
The authors present a multimodal system that automatically extracts high‑energy video segments for dynamic covers by analyzing subtitles, audio, visual frames, and danmu, employing LLM prompt‑tuning, scene‑cut detection, and aesthetic scoring to reduce manual effort and boost click‑through rates.
This article provides a comprehensive overview of OCR technology, detailing the evolution from traditional hand‑crafted methods to modern deep‑learning approaches, describing image preprocessing, text detection and recognition pipelines, summarizing classic machine‑learning algorithms, and presenting a practical OpenCV implementation with Python code.
This article provides a comprehensive overview of Optical Character Recognition (OCR), covering its definition, historical development, classification, real‑world applications, technical pipeline, common challenges, mitigation strategies, popular datasets, model performance comparisons, and leading open‑source platforms.
This article explains how to build a text‑to‑image search system by first extracting text with OCR, then storing image paths and textual embeddings in a SQLite or Milvus vector database, and finally improving retrieval with Transformer‑based sentence embeddings and image‑captioning models.
This guide explains how to programmatically download arithmetic captcha images, use OCR to extract and compute the expression, and automatically click the correct image on a website by combining Python requests, pytesseract, and Selenium for web automation.
This article compares three popular Python OCR libraries—pyocr, pytesseract, and python‑tesseract—explaining their installation, basic usage, and how they can be applied in interface automation tasks to extract text from images, with code examples for each.
This tutorial demonstrates how to install the Tesseract OCR library via Composer, set up a PHP script to load an image, create a TesseractOCR instance, run the OCR process, and output the extracted text, providing complete sample code for each step.
This tutorial walks through creating a Chrome extension that captures images from web pages, sends them to a Python‑backed Tesseract OCR engine, and displays the recognized text, covering the plugin's file structure, manifest configuration, JavaScript code, HTML UI, CSS styling, and installation steps.
This article walks through solving Python web‑scraping captcha challenges by using Selenium to capture the image, applying OCR for recognition, and offering alternative request‑based methods, while also addressing common driver version mismatches.
The article presents the background, challenges, and objectives of Bilibili's AI services, introduces the self‑developed InferX inference framework with its quantization and sparsity optimizations, details OCR‑specific enhancements, and describes how integrating InferX with Nvidia Triton dramatically improves throughput, latency, and GPU utilization.
This tutorial presents seven Python3 utilities—including PDF‑to‑Word, image‑to‑PDF/Word, image compression, filtering, Excel conversion, and OCR—detailing required libraries, step‑by‑step procedures, and complete code examples to streamline everyday file‑format tasks.
This article presents Weibo's comprehensive multimedia content understanding pipeline, covering video summarization techniques, quality assessment models, OCR advancements, video embedding strategies, and the performance benefits of CV‑CUDA acceleration, while highlighting real‑world applications and engineering trade‑offs.
This article provides a detailed introduction to OCR technology, covering its fundamental concepts, major categories (document, scene, and handwritten OCR), typical processing pipelines, a suite of open‑source models on ModelScope—including detection, recognition, and table OCR—and recent multimodal pre‑training methods such as VLDoc and VLPT.
This article introduces the open‑source ddddocr SDK, demonstrates how to install it and use it in Python to automatically solve three common captcha types—slider, click‑based, and alphanumeric—providing code examples and result explanations for each.
MegaPortal is an easy‑to‑use AI model loader for Apple devices that lets users configure visual‑block Snippets for tasks such as face‑filtering, Genshin Impact gacha recommendation, and Stable Diffusion image generation, with step‑by‑step tutorials, system requirements, cache clearing, model downloads, and a call for iOS‑dev help.
This article explains intelligent document processing (IDP) by describing its core components—OCR, document parsing, and information extraction—detailing various OCR and text‑detection algorithms, discussing document layout reconstruction, table parsing, domain‑specific model adaptation, system optimization, and productization challenges, and outlining future research directions.
This article explains how a unified AI platform enables rapid, data‑driven creation, training, deployment, and evaluation of OCR models for visually distinct text regions such as seals, meter readings, license plates, and VIN codes, while minimizing hardware and annotation costs.
Tencent Cloud’s OCR team cut average response time from 1.8 seconds to under one second and boosted throughput by over 50 % by redesigning the model with self‑attention, accelerating inference with a Tensor‑Network accelerator, shrinking RPC payloads, enabling asynchronous logging, and optimizing multi‑region GPU memory utilization.
The article describes Laiye's shift to a data‑driven deep‑learning workflow and presents the design, macro‑ and micro‑analysis features, visual diff tools, distributed tracing, and code examples of their OCR testing system that accelerate model evaluation and iterative optimization.
ShopeeVideo OCR is a multi‑language text‑recognition system for Southeast Asian e‑commerce videos that unifies detection, Transformer‑based recognition, layout analysis, and large‑scale synthetic data generation to handle Indonesian, Filipino, English, Vietnamese, Thai and Chinese scripts, delivering industry‑leading accuracy and winning thirteen ICDAR first‑place awards.
This article reviews the 40‑year evolution of Optical Character Recognition, discusses its integration with Intelligent Document Processing, outlines recent research hotspots such as scene text recognition and domain‑specific symbol detection, and shares practical engineering experiences and future directions from Datagrand.
This article describes how OCR technology is used in a game marketplace to automatically extract skin parameters from user‑uploaded images, outlines methods for separating owned skin regions from background using color analysis, and presents a tolerant matching solution based on Rabin‑Karp hashing to handle OCR errors.
The article explains OCR fundamentals and details how Baidu’s open‑source PaddleOCR suite can be converted and run in browsers via the @paddlejs‑models/ocr SDK, describing model initialization, detection and CRNN‑based recognition pipelines, and presenting benchmark results that show the newer ch_PP‑OCRv2 model achieving higher accuracy and faster inference than the mobile variant.
This tutorial walks through OCR fundamentals using pytesseract and chineseocr_lite, demonstrates how to push notifications via Server酱, provides reusable Python image‑processing utilities, and shows how to dump and parse Android UI XML for automated interactions.
This article introduces the Transformer architecture, explains its attention mechanism, details its adaptations for natural language processing, computer vision, and OCR tasks, and presents experimental results of various models such as BERT, ELECTRA, Swin Transformer, and CRNN-BCN on large-scale medical data from Haodf.com.
This article reviews recent progress in applying self‑supervised learning to OCR text recognition, covering mainstream model architectures, key considerations for self‑supervised tasks on text images, and detailed analyses of representative papers such as SeqCLR, SimAN, and DiG, highlighting their designs, experiments, and results.
This article reviews the evolution of automated testing toward intelligent solutions, explaining self‑healing mechanisms, machine‑learning‑driven object recognition, computer‑vision and OCR approaches, industry tools such as Healenium and Airtest, and future prospects for zero‑code AI‑powered test automation.
This article walks through a Python OCR solution for a blank image output problem, demonstrates a working ddddocr code snippet, and suggests an alternative OpenCV preprocessing step, providing clear screenshots and concise explanations for effective image text extraction.
This article reviews recent self‑supervised learning approaches for optical character recognition, covering mainstream OCR model architectures, key factors for applying contrastive and masked image modeling methods to text images, and detailed analyses of representative works such as SeqCLR, SimAN, and DiG, including their designs and experimental results.
This article presents JD.com's end‑to‑end intelligent creative system, covering the background of content‑driven e‑commerce, a multi‑stage content understanding pipeline, AI‑powered video, image and copy generation, multimodal creative selection and distribution, and real‑world business impact.
This tutorial explains how to generate synthetic digit images, train a CNN model to recognize handwritten numbers and operators, segment scanned math worksheets using projection techniques, evaluate each expression with Python's eval, and overlay the results on the original image to provide automatic grading feedback.
A middle‑aged Android developer recounts breaking his child's "Niu Ting Ting" device, then details how he recreated its functionality by integrating OpenCV‑based paper detection, OCR, and TTS into a mobile app, complete with code snippets and performance results.
This article explains how intelligent document processing uses deep‑learning‑based seal detection and OCR techniques—enhanced YOLOv5, multi‑label loss, combined NMS, and end‑to‑end models such as Mask‑TextSpotter, ABCNet, PGNet, and TrOCR—to overcome diverse stamp styles, background interference, and image quality issues, presenting experimental results that surpass commercial OCR vendors.
This guide shows how to use Python to scrape high‑quality chat screenshots, apply OCR, generate silent chat videos, batch‑download matching audio from short‑video platforms, and combine them into thousands of unique WeChat Video Channel clips, leveraging volume to outsmart recommendation algorithms and boost traffic.
This article documents a Python parking lot management application, detailing its project directory layout, describing each module such as button handling, OCR, and time utilities, and presenting key pygame-based code that renders parking statistics and vehicle information from an Excel file.
This article introduces the open‑source Python library ddddocr, explains its evolution from version 1.2.0 to 1.4.3—including OCR, target detection, and slider recognition features—and shows how it leverages deep‑learning and OpenCV to simplify captcha solving for developers.
This article presents a technical overview of the Youdao Dictionary Pen, describing its hardware design, real‑time scanning and point‑query image processing, on‑device offline translation with model compression techniques, and the high‑performance Edge ML Library (EMLL) that enables efficient AI inference on constrained edge hardware.
This article documents the author’s step‑by‑step journey of building an OCR system for recognizing Chinese characters in a card‑game UI, covering game selection, technical background, data generation, deep‑learning model training with CRNN, real‑image data collection, optimization attempts, and final performance evaluation.
This article describes Laiye's OCR error‑correction system, detailing the background challenges of Chinese character recognition, the analysis of three possible solutions, the chosen post‑processing approach, model architecture, training data, loss design, online inference, and experimental results showing a measurable performance boost.
This article presents a series of concise Python examples—each under ten lines—demonstrating how to generate QR codes, create word clouds, perform image segmentation, conduct sentiment analysis, detect masks, automate message sending, extract text with OCR, and build a basic number‑guessing game, showcasing the versatility of Python for quick prototyping across AI and utility tasks.
This article explores how optical character recognition (OCR) technology can address the financing pain points of micro‑enterprises by automating document verification, enhancing risk assessment, and enabling an end‑to‑end intelligent OCR platform built on deep‑learning models, data pipelines, and deployment automation.
The Yiche OCR system combines a DBNet‑based text detector and a CRNN recognizer, enhances performance on natural‑scene texts through data expansion, multi‑branch dictionaries, distribution‑aware weighting, and accelerates training via IPEX and parallel processing on CPU servers.
This article reviews the challenges of extracting structured table data from images, compares two‑stage and end‑to‑end OCR approaches, evaluates four state‑of‑the‑art table‑recognition models (SPLERGE, CascadeTabNet, TableMASTER, UnetTable), and presents a practical deployment workflow with performance metrics.
This tutorial shows how to use Python, ADB, and OpenCV to automate the mobile game Princess Connect, covering environment setup, device communication, screen capture, image matching, OCR, and script snippets for clicking, typing, and switching accounts.
This article explains how to handle custom web fonts whose glyph order or shapes are randomized by extracting glyph metadata with FontTools, creating binary signatures for reliable matching, and applying image‑recognition OCR to decode characters when glyph contours also change, complete with code examples and step‑by‑step instructions.
Paddle.js OCR SDK brings Baidu’s lightweight PaddleOCR models to web browsers, offering init() and recognize() APIs that load the ch_PP-OCRv2 detection (DB) and recognition (CRNN with bidirectional LSTM) models in parallel, achieving 258 ms detection, 60 ms recognition, 0.52 F‑score, and a combined size under 12 MB.
This article demonstrates step‑by‑step how to overcome a website’s anti‑scraping defenses using Selenium with stealth options, retrieve CSS‑based price images, reconstruct the digits, and apply Tesseract OCR to accurately extract numeric data, providing complete Python code snippets throughout.
This article provides a comprehensive overview of Optical Character Recognition, covering its traditional applications, the evolution to deep learning methods, key datasets, popular tools, and practical strategies for tackling diverse OCR challenges in real-world scenarios.
This article reviews self‑supervised learning techniques, common computer‑vision pretext tasks, contrastive loss functions, popular frameworks such as SimCLR, MoCo and SimSiam, and demonstrates their application to OCR captcha recognition with detailed implementation and experimental results.
This article surveys self‑supervised learning techniques for computer‑vision tasks, explains common pretext tasks and contrastive loss designs, reviews representative models such as SimCLR, MoCo, SmAV and SimSiam, and demonstrates their practical impact on a captcha‑OCR system with measurable accuracy gains.
This article explains how OCR-based text recognition is applied to content safety, detailing common risk categories, a step‑by‑step detection and recognition pipeline, mainstream detection and recognition algorithms such as regression‑based and segmentation‑based methods, and practical deployment and performance optimization strategies.
The article provides a comprehensive technical overview of PaddleOCR's PP‑OCRv2, detailing its five major algorithmic enhancements, performance improvements over previous versions, historical milestones, core capabilities, and links to the open‑source repositories for developers interested in state‑of‑the‑art OCR solutions.
This article introduces the ddddocr Python library for fast, code‑light captcha recognition, compares it with pillow + pytesseract and Baidu API, provides installation steps, usage examples, performance tips, and discusses its accuracy limits.
This article presents a method for precisely measuring mobile app response latency by extracting video frames, detecting start and end frames through image markers and OCR, and calculating the time difference, offering a high‑precision, customizable solution for performance evaluation across diverse app scenarios.
This article walks through creating a Python desktop demo that uses Youdao's OCR translation API to batch‑process cosmetic product label images, covering API credential setup, request parameters, signature generation, core code snippets, and a summary of the translation results.
This article demonstrates how to automatically convert PDF slide decks into editable markdown text by first converting each page to images, then applying a deep‑learning OCR pipeline (CTPN for detection and CRNN for recognition) with Python code examples, achieving high transcription accuracy.
This article reviews two end‑to‑end deep‑learning approaches—DocUNet (CVPR 2018) and DewarpNet (ICCV 2019)—for correcting warped document images, detailing their network architectures, synthetic data generation, loss functions, experimental results, and the remaining challenges in document dewarping.
This article presents a step‑by‑step Python demo that uses Youdao's OCR translation API to batch‑process cosmetic product images, covering API key setup, request parameters, signature generation, GUI implementation with Tkinter, and code snippets for file selection, result storage, and API invocation.
This article reviews modern text‑recognition systems, detailing how encoders such as CNN, CNN‑BiLSTM, and Transformer‑based models extract visual features, and how decoders like Position Attention, Transformer decoders, and RNN Seq2Seq align variable‑length text, while also discussing CTC loss and practical design choices.
This article traces the origins, unique difficulties, method classifications, and current advancements of scene text detection, highlighting how AI has enabled computers to read images and the ongoing research to improve accuracy, speed, and multilingual support.
This article explains the main captcha varieties—input, sliding, grid, and click‑based—and provides step‑by‑step Python solutions using OCR libraries, image preprocessing, and Selenium automation to bypass them effectively.
The article explains that Flutter Driver and Integration Test struggle to locate elements in hybrid native‑Flutter apps, then describes Xianyu’s approach of extending native UI automation with OCR, image‑matching, and a layered page‑object architecture, achieving over 98% success across 500+ runs.
Automatic homework grading leverages AI to transform captured images into graded results through preprocessing, layout analysis, OCR, answer matching, and strategy modules, while addressing three question categories—logical, text‑rich, and graphic—each presenting distinct technical challenges and future research directions.
iQIYI’s OCR journey, explained by researcher Harlon, covers the evolution from separate detection and recognition pipelines to end‑to‑end models, key algorithms like CTPN, DB and CRNN, large‑scale simulated training, diverse video‑text applications, and future goals such as mobile deployment and tighter NLP integration.
This tutorial walks through a project‑based OpenCV workflow that reads a digit template, preprocesses both template and credit‑card images, extracts individual numbers, matches them against the template, and finally overlays the recognized digits onto the original image, illustrating core computer‑vision techniques.
Amap’s visual‑technology pipeline automatically generates and updates POI names by crowdsourcing street‑level images, applying deep‑learning scene‑text recognition, dual‑branch classification of text attributes, and a BERT‑plus‑graph‑attention model that selects and orders recognized text, achieving about 95 % naming accuracy.
This article presents the practical deployment of OCR technology within 58’s information‑security workflows, focusing on layout‑analysis techniques for document and credential recognition, detailing rule‑based, template‑matching, object‑detection, and image‑segmentation methods, their implementation steps, experimental results, advantages, limitations, and future directions.
This article describes how a team at Longquan Temple leverages deep‑learning, NLP, and OCR technologies to automatically punctuate, recognize, and translate the massive Buddhist canon, achieving near‑human accuracy and dramatically accelerating scholarly work on ancient texts.
This article describes a Java-based ID card number recognition project that integrates Tess4j with JavaCPP to leverage OpenCV functionality without requiring a separate OpenCV installation, outlines required software, troubleshooting steps, recent updates, and provides the project repository link.
WeChat’s 8.0 update introduced an OCR pipeline that first quickly detects text in images, classifies the image type, applies a lightweight multi‑language detection network and a MobileNetV3‑based DBNet recognizer with a multi‑task CTC/Attention model, then merges results via a rule‑based layout analyzer to deliver accurate, well‑formatted extracted text across diverse languages and document types.
This article presents Meitu Community's AI‑driven multimedia content analysis pipeline, covering short‑video classification, video fingerprinting, and OCR, detailing model choices, experimental results, and future directions for improving content audit, quality, tagging, and feature engineering.
This article introduces ImageDT's PlugNet, which combines deep‑learning OCR and super‑resolution techniques to improve low‑quality text recognition in natural scenes, detailing the company's background, OCR challenges, deep‑learning approaches, super‑resolution methods, the PlugNet architecture, experimental results, and future research directions.
This article explains how to extract RGB values from a CAPTCHA image with PHP, convert the pixel data into binary patterns, map those patterns to digits using a predefined dictionary, and achieve 100% recognition accuracy, illustrating a practical backend security technique.
This article describes how a Chinese online medical platform tackled the large‑scale extraction and structuring of hospital report images by combining OCR, deep‑learning text‑region detection, fast text classification, and advanced NER techniques, detailing challenges, algorithm choices, performance results, and remaining issues.
This article explains what OCR is, introduces the EasyOCR Python library, shows how to install it, walks through step‑by‑step usage with code examples, and summarizes the underlying deep‑learning techniques powering the library.
TextShot, a newly released open‑source Python utility by GitHub user ianzhao05, lets you capture any screen region and instantly convert the image to editable text using Tesseract OCR, with multilingual support, hotkey integration, and step‑by‑step installation guidance for Windows and Linux.
Learn step‑by‑step how to use Baidu’s OCR service to extract text from images and employ the Pillow library to convert image formats in Python, including code snippets, API parameter details, and practical tips for handling local and online files.
This article introduces a Java OCR project for ID cards that integrates OpenCV, JavaCPP, and Tess4J to perform image preprocessing, region cropping, and character recognition without requiring OpenCV installation, and details its features, encountered issues, system requirements, updates, and source repository.
This article presents a deep‑learning Seq2Seq model that converts images of mathematical formulas—including matrices, equations, fractions, and radicals—into LaTeX sequences with over 95% accuracy, detailing data preparation, LaTeX normalization, model architecture, training, inference, and post‑processing techniques.
This article introduces a Java-based ID card number recognition project that integrates OpenCV, Tess4J, and JavaCPP to perform OCR without prior training, outlines the encountered library linking issue, lists required software, and details recent updates such as chunked uploads and OpenCV version upgrade.
PaddleOCR, the 2020 breakthrough in open‑source OCR, offers ultra‑light 3.5 MB multilingual models, high F1‑score performance across diverse scenarios, easy installation via pip, comprehensive documentation, custom training support, and deployment options for both server and mobile platforms, all backed by detailed benchmarks and code examples.
