![]() 開發商:ABBYY 原廠網址:http://www.abbyy.com/ocr_sdk_linux/overview/ 更新日期:2011/05/29 採購正式版、大量授權報價、技術支援、軟體諮詢、委託採購、詢問報價請來電 02-29299388 分機16 , 來信service@orderble.com,或點我 ----------------------------------------------------------------------------- 圖像導入OCR SDK的從各種管道獲得的圖像:圖像文件,幾乎任何格式,並直接從內存中。 圖像文件格式包括BMP,DCX,GIF和應用於 JBIG2,對 JPEG,JPEG 2000,PCX,PNG,PDF,TIFF格式,多頁 TIFF和PDF格式。 記憶的圖像格式包括原材料,位圖(HBITMAP)DIB。 影像處理該文件承認 SDK的前處理儀器包括了很多有用的前處理技術,以改善接收圖像質量:自動傾斜校正,分裂雙頁,清理圖像,紋理過濾,文本和背景顏色調整,自動檢測的頁面方向,許多其他人。 文獻分析該引擎的API提供了智能識別文檔的佈局結構,包括autodection文字,圖像,條形碼和圖片,文字方向檢測。 它也支持特殊文件分析設計,用於分類和捕獲應用,包括發票處理,表格分析和垂直文本檢測。 佈局重構ABBYY FineReader還為Linux 9.0發動機介紹 自適應文檔識別技術(ADRT), 一套核心文件的複製合成算法一般的邏輯結構的文件。 它會自動生成一個邏輯模型的文檔結構,並確定其成分。 ADRT定義:
語言支持世界領導人在文檔識別,光學字符識別的ABBYY提供高度精確的技術,超過 195種語言。 該組包括拉丁和西里爾為基礎的語言,亞洲象形文字的語言(中文,日文和韓文),希伯來語,泰語,越南語和西部老哥特式字體。 條碼類型該引擎識別 20多個一維條碼和一個數字的最廣泛使用的二維條碼:PDF417碼,阿茲特克,QR碼和DataMatrix。 PDF轉換ABBYY FineReader還為 Linux提供9.0引擎開發的PDF輸入和處理,以及文件轉換為多種類型的可搜索PDF格式,包括PDF / A和壓縮 MRC分PDF格式。 先進的開發工具ABBYY FineReader還引擎9.0的Linux提供了有用的工具,提高開發人員的能力,互動與認同的SDK和API的識別過程管理的核心層。 選項輸出出口到所有流行的文件格式,包括RTF格式,文檔,xls,幻燈片,XML格式,PDF格式,文本文件。 擋土牆的詳細資料,整個結構的認可文件。 mage ImportThe OCR SDK receives images from various sources: image files of virtually any format, and directly from memory. Image file formats include BMP, DCX, GIF, JBIG2, JPEG, JPEG 2000, PCX, PNG, PDF, TIFF, multi-page TIFF, and PDF. Memory image format include Raw, Bitmap (HBITMAP), DIB. Image ProcessingThe document recognition SDK pre-processing instruments include a lot of useful pre-processing technologies to improve incoming image quality: automated deskewing, splitting dual pages, image clean up, texture filtering, text and background color adjustment, autodetection of page orientation, and many others. Document AnalysisThe Engine’s API delivers intelligent structural recognition of document layout, including autodection of text, images, barcodes and pictures, text orientation detection. It also supports special document analysis designed to be used in classification and capture applications, including invoice processing, tables analysis and vertical text detection. Layout ReconstructionABBYY FineReader Engine 9.0 for Linux introduces Adaptive Document Recognition Technology (ADRT), a core set of document synthesis algorithms which reproduces general logical structure of document. It automatically builds a logical model of the document structure and identifies its elements. ADRT defines:
Language SupportA world leader in document recognition, ABBYY offers highly accurate OCR technologies with more than 195 languages. The set includes Latin- and Cyrillic-based languages, Asian hieroglyphic languages (Chinese, Japanese and Korean), Hebrew, Thai, Vietnamese and Western old gothic fonts. Barcode TypesThe engine recognizes more than 20 1D barcodes and a number of most widely used 2D barcodes: PDF417, Aztec, QR Code and DataMatrix. PDF ConversionABBYY FineReader Engine 9.0 for Linux provides developers with PDF input and processing, and document conversion to multiple types of searchable PDF, including PDF/A and compressed MRC PDF. Advanced Development ToolsABBYY FineReader Engine 9.0 for Linux offers useful tools that enhance developer's ability to interact with the recognition API of the SDK and manage the recognition process on the core level. Output OptionsExport to all popular document formats, including RTF, DOC, XLS, PPT, XML formats, PDF, text files. Retaining detailed information on the whole structure of the recognized document. |