結(jié)構(gòu)化的表單識(shí)別與處理工具,提供表單識(shí)別/注冊(cè)/移除,標(biāo)記識(shí)別(氣泡和復(fù)選框)等。
FormFix所推出的.NET以及ActiveX COM(組件對(duì)象模型)控件,能夠?yàn)楸韱翁幚響?yīng)用程序開(kāi)發(fā)人員提供基于模板的黑白表單鑒定、表單注冊(cè)、表單移除以及OMR(光學(xué)標(biāo)記識(shí)別)技術(shù)。本產(chǎn)品結(jié)構(gòu)高度靈活,基于速度優(yōu)化,出眾的表單識(shí)別以及表單注冊(cè)功能能顯著提高ICR(智能字符識(shí)別)、OCR(光學(xué)字符識(shí)別)以及OMR的精確度。本產(chǎn)品可以輕松地與識(shí)別引擎(請(qǐng)查看FormSuite)集成,也可以與任何支持內(nèi)存到內(nèi)存(memory-to-memory)方式數(shù)據(jù)傳輸?shù)淖R(shí)別引擎集成。具有圖像處理功能、高級(jí)圖像清除功能以及TWAIN掃描功能的ImagXpress控件和ScanFix Xpress控件也包含到了本產(chǎn)品中。
FormFix delivers both .NET and ActiveX COM components offering bitonal template-based form identification, form registration, form drop out, and OMR technology to developers of forms processing applications. Highly flexible and optimized for speed, FormFix’s superior form recognition and form registration improve ICR, OCR, and OMR accuracy. It easily interfaces with Pegasus recognition engines (see FormSuite), and with any recognition engine supporting memory-to-memory data transfers. ImagXpress and ScanFix Xpress are included with FormFix for image handling, advanced image cleanup, and TWAIN scanning. <br />
技術(shù)說(shuō)明:
- 編程環(huán)境:Win32可視化開(kāi)發(fā)環(huán)境。
- 本產(chǎn)品包含有適用于以下平臺(tái)的示例代碼:VB.NET、C#、VB、Delphi、VC++、HTML。
- 為 .NET用戶(hù)提供的面向?qū)ο螅∣bject-oriented)的應(yīng)用程序編程接口(API)。
- 本產(chǎn)品可以在.NET平臺(tái)下以一個(gè)托管控件的形式部署,并且能夠與.NET 1.0及以上版本完全兼容(請(qǐng)查看“構(gòu)建適用于微軟.NET平臺(tái)的健壯圖像組件”白皮書(shū))。
- 本產(chǎn)品可以在任何可以包容ActiveX COM(組件對(duì)象模型)控件的開(kāi)發(fā)環(huán)境下使用。
- 本產(chǎn)品可以在多線(xiàn)程的環(huán)境下使用。
- 本產(chǎn)品的專(zhuān)業(yè)版本(Professional edition)包含有8個(gè)控件,它們分別是:FormFix、FormDirector、ScanFix、ImagXpress、NotateXpress、ThumbnailXpress、TwainPRO以及PrintPRO。
- 支持用戶(hù)設(shè)定的調(diào)式日志記錄級(jí)別。
- 處理速度優(yōu)化,本產(chǎn)品能夠以毫秒級(jí)的速度提交匹配結(jié)果。
- 支持超過(guò)一萬(wàn)個(gè)的匹配候選表單模板。
- 具有客戶(hù)端/服務(wù)器模式的Web應(yīng)用開(kāi)發(fā)能力。
- 通過(guò)一個(gè)易用的多重圖像緩沖(multiple image buffering)機(jī)制,本產(chǎn)品的圖像處理速度大大提高。
- 具有兩種可選的處理速度(標(biāo)準(zhǔn)以及專(zhuān)業(yè)版本)。
- 用戶(hù)可以立即下載本產(chǎn)品功能完整的免費(fèi)試用版本。
表單設(shè)置:
- 本產(chǎn)品擁有可用于字段、表單模板以及表單模板集合設(shè)置的應(yīng)用程序編程接口(API)。
- 本產(chǎn)品具有靈活的體系結(jié)構(gòu),用戶(hù)可以在處理流程的任何一個(gè)步驟設(shè)定自定義操作。
- 用戶(hù)可以在每一個(gè)表單上定義OMR(定義光學(xué)標(biāo)記識(shí)別)字段、文本字段或者自定義字段。
- 對(duì)表單處理操作提供廣泛的支持。
表單鑒定:
- 將候選表單與預(yù)定義的未填充模板進(jìn)行匹配分析,并返回表單的匹配可信度數(shù)值。
- 為用戶(hù)提供不需要注冊(cè)標(biāo)記、識(shí)別符標(biāo)記或者定位點(diǎn)標(biāo)記的自動(dòng)鑒定。
- 能夠匹配那些由模板圖像旋轉(zhuǎn)90度、180度或者270度得到的表單。
- 能夠匹配尺寸被縮放為模板尺寸的90%到110%的表單。
- 能夠匹配那些掃描解析度只有模板解析度50%到150%的表單。
- 能夠匹配那些由本產(chǎn)品所含控件ScanFix預(yù)處理為傾斜20度的表單。
- 本產(chǎn)品可以鑒定數(shù)以千計(jì)的各種不同表單。
- 將某一識(shí)別操作的操作對(duì)象限定為可用模板的某一子集。
- 用戶(hù)可以設(shè)置完成表單匹配所付出的代價(jià)的級(jí)別。
- 本產(chǎn)品將返回用來(lái)指示表單匹配可信度的鑒定確定度(Identification Certainty)。
- 用戶(hù)可以設(shè)定一個(gè)用于決定表單是否為匹配表單的最小確定度級(jí)別。
- 本產(chǎn)品最多可以返回100個(gè)低確定度的可選表單匹配。
- 即使是使用了大量的模板表單集合,本產(chǎn)品仍然能夠快速鑒定表單。
表單注冊(cè):
- 本產(chǎn)品可以基于圖像內(nèi)容來(lái)將某個(gè)已填充表單自動(dòng)對(duì)齊到其主模板。
- 分析主模板表單內(nèi)容,并決定自動(dòng)確定定位點(diǎn)(anchor points)。
- 在一個(gè)移除區(qū)域內(nèi)調(diào)整對(duì)齊,以便能彌補(bǔ)表單之間的微小差異。
- 通過(guò)在每一個(gè)角使用一個(gè)定位點(diǎn)標(biāo)記,本產(chǎn)品支持一個(gè)可選的注冊(cè)過(guò)程。
- 本產(chǎn)品能夠注冊(cè)即使是有如下特點(diǎn)的表單:
- 傾斜(最大傾斜度為20度)。
- 圖像大小比模板大或者小(最多10%)
- 使用與模板解析度不同的解析度(最多比模板解析度高50%或者低50%)掃描的表單。
- 旋轉(zhuǎn)(將模板旋轉(zhuǎn)90度、180度或者270度得到的表單)。
表單移除:
- 本產(chǎn)品能夠以毫秒級(jí)的速度來(lái)移除模板表單。
- 提供一個(gè)可信度來(lái)突出有問(wèn)題的圖像。
- 調(diào)整由打印、復(fù)制或者掃描引起的失真。
- 精確移除線(xiàn)條、斷線(xiàn)、陰影、噪聲、向?qū)谋疽约捌渌?/li>
- 自動(dòng)修復(fù)與線(xiàn)條或者定義表單的向?qū)谋窘诲e(cuò)的文本,這些文本在模板移除的過(guò)程中已被破壞(包含中斷字符)。
- 在表單已移除的圖像中跨區(qū)域應(yīng)用“字符修復(fù)”功能。
- 應(yīng)用“字符平滑”功能來(lái)平滑字符的邊緣,以便能夠提高OCR(光學(xué)字符識(shí)別)精確度。
- 支持指定字段范圍內(nèi)的表單移除或者整個(gè)圖像內(nèi)的表單移除。
- 用戶(hù)可以使用像素精度的剪切來(lái)從源圖像(字段集)中創(chuàng)建新的圖像
OMR(光學(xué)標(biāo)記識(shí)別以及標(biāo)記感應(yīng)):
- 檢測(cè)標(biāo)記或者字符是否存在或者丟失(例如:用于驗(yàn)證簽名是否存在)。
- 支持氣泡形狀的編程規(guī)范。
- 支持0度、90度、180度以及270度方向的OMR(光學(xué)標(biāo)記識(shí)別)識(shí)別。
- 將字段設(shè)定為表格(行列式)或者單一氣泡的形式。
- 支持單一標(biāo)記識(shí)別以及多標(biāo)記識(shí)別。
- 識(shí)別復(fù)選標(biāo)記的選擇框。
- 對(duì)字段數(shù)量沒(méi)有任何限制。
- 支持正標(biāo)記閾值的編程規(guī)范。
- 返回可用于OMR(光學(xué)標(biāo)記識(shí)別)精確度檢察的可信度。
表單疊加
- 允許使用dropout來(lái)存取已填充數(shù)據(jù)以及變量數(shù)據(jù)。
- 支持將已歸檔的“純數(shù)據(jù)”(“data only”)文件疊加到表單模板來(lái)顯示或者打印。
- 本處理功能能大大減少存儲(chǔ)需求。
- 提高傳輸速度。
圖像輸入、圖像輸出以及圖像處理:
- 本產(chǎn)品的專(zhuān)業(yè)版本包含有ImagXpress Document控件(閱讀完整的ImagXpress Document v8產(chǎn)品描述),用戶(hù)可以使用它來(lái)完成圖片瀏覽、TWAIN掃描、注釋添加、打印以及其它各種功能。本產(chǎn)品的標(biāo)準(zhǔn)版本包含有ImagXpress Standard控件(閱讀完整的ImagXpress Standard v8產(chǎn)品描述),用戶(hù)可以使用它來(lái)基本的圖像轉(zhuǎn)換、圖像處理以及TWAIN掃描。
黑白圖像清除:
- 本產(chǎn)品專(zhuān)業(yè)版本包含有ScanFix Xpress控件(閱讀完整的ScanFix Xpress v5產(chǎn)品描述),此控件能夠提供各種高級(jí)雙重圖像清楚技術(shù)支持,例如:點(diǎn)狀陰影移除、線(xiàn)條移除、字符平滑、文本反轉(zhuǎn)校正、孔洞移除、偏斜校正(deskew)、斑點(diǎn)移除(despeckle)、旋轉(zhuǎn)、鏡像(mirror)、翻轉(zhuǎn)(flip)等等各種功能。
- 本產(chǎn)品專(zhuān)業(yè)版本包含有ScanFix Xpress Lite控件(查看ScanFix Xpress Lite v5的特征功能),此控件能夠提供各種高級(jí)雙重圖像清楚技術(shù)支持,例如:偏斜校正(deskew)、斑點(diǎn)移除(despeckle)、旋轉(zhuǎn)鏡像(mirror)、翻轉(zhuǎn)(flip)等等各種功能。
圖像以及數(shù)據(jù)傳輸工具:
- 本產(chǎn)品包含有FormDirector組件,此組件可以與多個(gè)Pegasu圖像處理組件(包括 FormFix、SmartZone以及ScanFix Xpress)通訊,幫助用戶(hù)組織、存儲(chǔ)以及獲取在表單處理中需要的各種描述以及控件參數(shù)。
- 支持閱讀、修訂以及編寫(xiě)表單模板集合文件。
- 支持閱讀、修訂以及編寫(xiě)表單模板定義文件。
- 可以處理超過(guò)一萬(wàn)個(gè)的不同表單模板。
- 支持黑白文件(在將來(lái)的版本中將支持灰度以及彩色)。
- 支持Unicode(統(tǒng)一字符編碼標(biāo)準(zhǔn))字符。
- 支持自定義,包括用戶(hù)自定義的字段類(lèi)型以及附加到表單集合、表單和字段之上的私有用戶(hù)數(shù)據(jù)。
- 取代SmartScan Xpress ICR/OCR/OMR(表單定義文件)、FormFix(表格文件)以及Prizm Color IP(表單定義文件以及表單簇文件)中的表單定義以及表單移除特征功能。
版本描述:
- 本產(chǎn)品的專(zhuān)業(yè)版本是專(zhuān)門(mén)為各種商業(yè)級(jí)表單處理應(yīng)用程序開(kāi)發(fā)人員設(shè)計(jì)的。專(zhuān)業(yè)版本能夠提供本產(chǎn)品的完整功能以及最快的處理速度,不僅包含有能夠提供多頁(yè)文檔處理以及注釋功能支持的ImagXpress Document控件(請(qǐng)查看ImagXpress對(duì)照頁(yè)),還包含有可以完成黑白圖像清除的ScanFix Xpress控件。
- 本產(chǎn)品的標(biāo)準(zhǔn)版本是專(zhuān)門(mén)為部署小容量的表單處理解決方案的開(kāi)發(fā)人員設(shè)計(jì)的,這些小容量的表單處理解決方案一般只使用單頁(yè)的表單,而且也不需要高級(jí)的圖像清除功能。標(biāo)準(zhǔn)版本處理表單的速度每一頁(yè)面大概比專(zhuān)業(yè)版本慢5秒,不僅包含ImagXpress Standard控件(請(qǐng)查看ImagXpress對(duì)照頁(yè)),還包含有具有標(biāo)準(zhǔn)偏斜校正(deskew)、斑點(diǎn)去除(despeckle)、旋轉(zhuǎn)、鏡像(mirror)、翻轉(zhuǎn)(flip)、線(xiàn)條移除等等各種功能的ScanFix Xpress Lite控件。
Technical Notes
- Programming environments: Win32 visual development environments
- Sample code is included for: VB.NET, C#, VB, Delphi, VC++, HTML
- Object-oriented API for .NET users
- Deploys within .NET as a managed control and is fully compliant with .NET 1.0 and above (see "Building Robust Imaging Components for the Microsoft .NET Platform" white paper)
- Can also be used in any development environment that hosts ActiveX COM controls
- Can be used in a multi-threaded environment
- Professional edition includes 8 controls: FormFix, FormDirector, ScanFix, ImagXpress, NotateXpress, ThumbnailXpress, TwainPRO and PrintPRO
- Support user-specified debug logging levels
- Optimized for speed, delivers matching results at sub-second speeds
- Supports over 10,000 unique form templates as candidates for matching
- Client/server Web development capabilities
- Increased image processing speed available via an easy to use multiple image buffering mechanism
- Two processing speeds are available (Standard and Professional editions)
- Free full-featured trial version available for immediate download
Form Setup
- API support for setting up fields, form templates, and sets of form templates
- Flexible architecture for defining custom operations at any stage of processing
- Define OMR, text, image, or custom fields on each form
- Extensive support for form processing operations
Form Identification
- Match forms against previously defined unfilled templates and return confidence values Provide automatic identification without the need for registration marks, ID marks, or anchor marks
- Match forms that are rotated 90, 180, or 270 degrees from template image
- Match forms that have been scaled from 90% to 110% of the template size
- Match forms scanned with resolution of 50% to 150% of the template resolution
- Match forms that are skewed up to 20 degrees by pre-processing with the included ScanFix
- Identify thousands of different forms
- Limit a recognition operation to a subset of the available templates
- Set the level of effort expended in completing form matching
- Return Identification Certainty indicating confidence of form matching
- Accept a Minimum Certainty level for acceptance as a matched form
- Return up to 100 alternative form matches of lower certainty
- Quickly identify forms, even when using very large sets of template forms
Form Registration
- Automatically align a filled form to its master template based on image contents, to within one or two pixels of the blank template without requiring registration marks
- Analyze the master template form content and determine anchor points automatically
- Adjust alignment within a drop out zone to compensate for small differences between forms
- Support an alternate registration process using anchor marks in each corner
- Register forms even when the forms exhibit these characteristics:
- Skew (up to 20 degrees)
- Smaller or larger image size than the template (up to 10%)
- Forms scanned at different resolutions (up to 50% greater and lesser) than the template resolution
- Rotation (at 90, 180, and 270 degrees from the template)
Form Drop Out
- Remove template forms at sub-second speeds
- Provide confidence values to highlight problem images
- Adjust for distortion caused by printing, copying or scanning
- Precisely remove lines, broken lines, shading, noise, guide text, and more
- Automatically repair text that intersects with lines or guide text defining the form, that was damaged during template removal (fills broken characters)
- Apply “character repair” across areas of the image where the form was removed
- Apply “character smoothing” to smooth the edges of characters for increased OCR accuracy
- Support for form drop out only within specified fields or the entire image
- Create new images using pixels cropped from a source image (field clips)
OMR (Optical Mark Recognition and Mark Sense)
- Detect the presence or absence of marks or characters (for verification of signature presence for example)
- Support programmatic specification for bubble shape
- Support OMR recognition at 0, 90, 180, and 270 degree orientation
- Specify fields as grids (rows by columns) or single bubbles
- Support single and multiple mark recognition
- Recognize check-marked check boxes
- Set custom recognition parameters on a per-field basis
- Allow an unlimited number of fields
- Support programmatic specification for threshold for positive marks
- Return confidence values to check accuracy of OMR
Form Overlay
- Enables the use of dropout to access the filled, variable data
- Overlay archived “data only” file over form template for display or print
- This process dramatically reduces storage requirements
- Increase data transmission speed
Image Input, Image Output, and Image Handling
- FormFix Professional includes ImagXpress Document (read the full ImagXpress Document v8 product description) for image viewing, compression, conversion, thumbnail image support, document image processing and editing, TWAIN scanning, annotation, printing, and more
- FormFix Standard includes ImagXpress Standard (read the full ImagXpress Standard v8 product description) for basic image conversion, image processing, and TWAIN scanning
Bitonal Image Cleanup
- FormFix Professional includes ScanFix Xpress (read the full ScanFix Xpress v5 product description) for advanced bitonal image cleanup technology such as dot shading removal, line removal, character smoothing, inverse text correction, hole punch removal, deskew, despeckle, rotate, mirror, flip and more
- FormFix Standard includes ScanFix Xpress Lite (see ScanFix Xpress Lite v5 features) for bitonal image cleanup technology such as deskew, despeckle, rotate, mirror, flip and more
Image and Data Transfer Tool
- Included with FormFix is the FormDirector component, providing communication among multiple Pegasus Imaging components (including FormFix, SmartZone, and ScanFix Xpress)
- Assists in organizing, storing, and retrieving the descriptions and control parameters you will use while processing forms
- Supports reading, revising and writing form template set files
- Supports reading, revising and writing form template definition files
- Handles over 10,000 unique form templates
- For bitonal files (grayscale and color will be supported in a future edition)
- Supports Unicode characters
- Supports customization, including customer-defined field types and private customer data attached to form sets, forms, and fields
- Replaces the form definition and form drop out features of SmartScan Xpress ICR/OCR/OMR (form definition files), FormFix (table files), and Prizm Color IP (form definition and form suite files)
Edition Descriptions
- FormFix Professional is designed for commercial forms processing application developers. It provides the full speed and power of FormFix, includes ImagXpress Document for multi-page document and annotation support (see ImagXpress comparison page), and includes ScanFix Xpress for powerful bitonal image cleanup.
- FormFix Standard is designed for developers deploying a low volume forms processing solution using single-page forms and not requiring advanced image cleanup. FormFix Standard is delayed to processing forms at a speed of approximately 5 seconds per page. It includes ImagXpress Standard (see ImagXpress comparison page) and includes ScanFix Xpress Lite for standard deskew, despeckle, rotate, mirror, flip, line removal, and more.