Skip to content

Commit 5d08720

Browse files
Merge pull request #231718 from laujan/72618-classifier-classification
update terms
2 parents 81c45ae + 6daf12c commit 5d08720

File tree

9 files changed

+49
-49
lines changed

9 files changed

+49
-49
lines changed

articles/applied-ai-services/form-recognizer/concept-composed-models.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -42,7 +42,7 @@ With composed models, you can assign multiple custom models to a composed model
4242

4343
::: moniker range="form-recog-3.0.0"
4444

45-
With the introduction of [****custom classifier models****](./concept-custom-classifier.md), you can choose to use [**composed models**](./concept-composed-models.md) or the classifier model as an explicit step before analysis. For a deeper understanding of when to use a classifier or composed model, _see_ [**Custom classifier models**](concept-custom-classifier.md).
45+
With the introduction of [**custom classification models**](./concept-custom-classifier.md), you can choose to use a [**composed model**](./concept-composed-models.md) or [**classification model**](concept-custom-classifier.md) as an explicit step before analysis. For a deeper understanding of when to use a classification or composed model, _see_ [**Custom classification models**](concept-custom-classifier.md#compare-custom-classification-and-composed-models).
4646

4747
## Compose model limits
4848

articles/applied-ai-services/form-recognizer/concept-custom-classifier.md

Lines changed: 15 additions & 15 deletions
Original file line numberDiff line numberDiff line change
@@ -1,7 +1,7 @@
11
---
2-
title: Custom classifier model - Form Recognizer
2+
title: Custom classification model - Form Recognizer
33
titleSuffix: Azure Applied AI Services
4-
description: Use the custom classifier model to train a model to identify and split the documents you process within your application.
4+
description: Use the custom classification model to train a model to identify and split the documents you process within your application.
55
author: vkurpad
66
manager: nitinme
77
ms.service: applied-ai-services
@@ -14,47 +14,47 @@ monikerRange: 'form-recog-3.0.0'
1414
recommendations: false
1515
---
1616

17-
# Custom classifier model
17+
# Custom classification model
1818

1919
**This article applies to:** ![Form Recognizer v3.0 checkmark](media/yes-icon.png) **Form Recognizer v3.0**.
2020

21-
Custom classifier models are deep-learning-model types that combine layout and language features to accurately detect and identify documents you process within your application. Custom classifier models can classify each page in an input file to identify the document(s) within and can also identify multiple documents or multiple instances of a single document within an input file.
21+
Custom classification models are deep-learning-model types that combine layout and language features to accurately detect and identify documents you process within your application. Custom classification models can classify each page in an input file to identify the document(s) within and can also identify multiple documents or multiple instances of a single document within an input file.
2222

2323
## Model capabilities
2424

25-
Custom classifier models can analyze a single- or multi-file documents to identify if any of the trained document types are contained within an input file. Here are the currently supported scenarios:
25+
Custom classification models can analyze a single- or multi-file documents to identify if any of the trained document types are contained within an input file. Here are the currently supported scenarios:
2626

2727
* A single file containing one document. For instance, a loan application form.
2828

2929
* A single file containing multiple documents. For instance, a loan application package containing a loan application form, payslip, and bank statement.
3030

3131
* A single file containing multiple instances of the same document. For instance, a collection of scanned invoices.
3232

33-
Training a custom classifier model requires at least two distinct classes and a minimum of five samples per class.
33+
Training a custom classifier requires at least two distinct classes and a minimum of five samples per class.
3434

35-
### Compare custom classifier and composed models
35+
### Compare custom classification and composed models
3636

37-
A custom classifier model can replace [a composed model](concept-composed-models.md) in some scenarios but there are a few differences to be aware of:
37+
A custom classification model can replace [a composed model](concept-composed-models.md) in some scenarios but there are a few differences to be aware of:
3838

3939
| Capability | Custom classifier process | Composed model process |
4040
|--|--|--|
41-
|Analyze a single document of unknown type belonging to one of the types trained for extraction model processing.| &#9679; Requires multiple calls. </br> &#9679; Call the classifier models based on the document class. This step allows for a confidence-based check before invoking the extraction model analysis.</br> &#9679; Invoke the extraction model. | &#9679; Requires a single call to a composed model containing the model corresponding to the input document type. |
41+
|Analyze a single document of unknown type belonging to one of the types trained for extraction model processing.| &#9679; Requires multiple calls. </br> &#9679; Call the classification model based on the document class. This step allows for a confidence-based check before invoking the extraction model analysis.</br> &#9679; Invoke the extraction model. | &#9679; Requires a single call to a composed model containing the model corresponding to the input document type. |
4242
|Analyze a single document of unknown type belonging to several types trained for extraction model processing.| &#9679;Requires multiple calls.</br> &#9679; Make a call to the classifier that ignores documents not matching a designated type for extraction.</br> &#9679; Invoke the extraction model. | &#9679; Requires a single call to a composed model. The service selects a custom model within the composed model with the highest match.</br> &#9679; A composed model can't ignore documents.|
4343
|Analyze a file containing multiple documents of known or unknown type belonging to one of the types trained for extraction model processing.| &#9679; Requires multiple calls. </br> &#9679; Call the extraction model for each identified document in the input file.</br> &#9679; Invoke the extraction model. | &#9679; Requires a single call to a composed model.</br> &#9679; The composed model invokes the component model once on the first instance of the document. </br> &#9679;The remaining documents are ignored. |
4444

4545
## Language support
4646

47-
Classifier models currently only support English language documents.
47+
Classification models currently only support English language documents.
4848

4949
## Best practices
5050

51-
Custom classifier models require a minimum of five samples per class to train. If the classes are similar, adding extra training samples improves model accuracy.
51+
Custom classification models require a minimum of five samples per class to train. If the classes are similar, adding extra training samples improves model accuracy.
5252

5353
## Training a model
5454

55-
Custom classifier models are only available in the [v3.0 API](v3-migration-guide.md) starting with API version ```2023-02-28-preview```. [Form Recognizer Studio](https://formrecognizer.appliedai.azure.com/studio) provides a no-code user interface to interactively train a custom classifier.
55+
Custom classification models are only available in the [v3.0 API](v3-migration-guide.md) starting with API version ```2023-02-28-preview```. [Form Recognizer Studio](https://formrecognizer.appliedai.azure.com/studio) provides a no-code user interface to interactively train a custom classifier.
5656

57-
When using the REST API, if you've organized your documents by folders, you can use the ```azureBlobSource``` property of the request to train a classifier model.
57+
When using the REST API, if you've organized your documents by folders, you can use the ```azureBlobSource``` property of the request to train a classification model.
5858

5959
```rest
6060
https://{endpoint}/formrecognizer/documentClassifiers:build?api-version=2023-02-28-preview
@@ -128,8 +128,8 @@ File list `car-maint.jsonl` contains the following files.
128128

129129
## Next steps
130130

131-
Learn to create custom classifier models:
131+
Learn to create custom classification models:
132132

133133
> [!div class="nextstepaction"]
134-
> [**Build a custom classifier model**](how-to-guides/build-a-custom-classifier.md)
134+
> [**Build a custom classification model**](how-to-guides/build-a-custom-classifier.md)
135135
> [**Custom models overview**](concept-custom.md)

articles/applied-ai-services/form-recognizer/concept-custom.md

Lines changed: 4 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -24,7 +24,7 @@ recommendations: false
2424

2525
Form Recognizer uses advanced machine learning technology to identify documents, detect and extract information from forms and documents, and return the extracted data in a structured JSON output. With Form Recognizer, you can use document analysis models, pre-built/pre-trained, or your trained standalone custom models.
2626

27-
Custom models now include [custom classifier models](./concept-custom-classifier.md) for scenarios where you need to identify the document type prior to invoking the extraction model. Classifier models are available starting with the ```2023-02-28-preview``` API. A classifier model can be paired with a custom extraction model to analyze and extract fields from forms and documents specific to your business to create a document processing solution. Standalone custom extraction models can be combined to create [composed models](concept-composed-models.md).
27+
Custom models now include [custom classification models](./concept-custom-classifier.md) for scenarios where you need to identify the document type prior to invoking the extraction model. Classifier models are available starting with the ```2023-02-28-preview``` API. A classification model can be paired with a custom extraction model to analyze and extract fields from forms and documents specific to your business to create a document processing solution. Standalone custom extraction models can be combined to create [composed models](concept-composed-models.md).
2828

2929
::: moniker range="form-recog-3.0.0"
3030

@@ -81,9 +81,9 @@ The following table compares custom template and custom neural features:
8181
|Document variations | Requires a model per each variation | Uses a single model for all variations |
8282
|Language support | Multiple [language support](language-support.md#read-layout-and-custom-form-template-model) | English, with preview support for Spanish, French, German, Italian and Dutch [language support](language-support.md#custom-neural-model) |
8383

84-
### Custom classifier model
84+
### Custom classification model
8585

86-
Document classification is a new scenario supported by Form Recognizer with the ```2023-02-28-preview``` API. Document classifier supports classification and splitting scenarios. Train a classifier model to identify the different types of documents your application supports. The input file for the classifier model can contain multiple documents and classifies each document within an associated page range. See [custom classification](concept-custom-classifier.md) models to learn more.
86+
Document classification is a new scenario supported by Form Recognizer with the ```2023-02-28-preview``` API. the document classifier API supports classification and splitting scenarios. Train a classification model to identify the different types of documents your application supports. The input file for the classification model can contain multiple documents and classifies each document within an associated page range. See [custom classification](concept-custom-classifier.md) models to learn more.
8787

8888
## Custom model tools
8989

@@ -184,7 +184,7 @@ Extract data from your specific or unique documents using custom models. You nee
184184

185185
1. Review and create your project.
186186

187-
1. Label your documents to build and test your custom classifier model.
187+
1. Label your documents to build and test your custom classification model.
188188

189189
> [!div class="nextstepaction"]
190190
> [Try Form Recognizer Studio](https://formrecognizer.appliedai.azure.com/studio/document-classifier/projects)

articles/applied-ai-services/form-recognizer/concept-model-overview.md

Lines changed: 16 additions & 16 deletions
Original file line numberDiff line numberDiff line change
@@ -50,12 +50,12 @@ recommendations: false
5050
|**Custom models**||
5151
| [Custom model (overview)](#custom-models) | Extract data from forms and documents specific to your business. Custom models are trained for your distinct data and use cases. |
5252
| [Custom extraction models](#custom-extraction)| &#9679; **Custom template models** use layout cues to extract values from documents and are suitable to extract fields from highly structured documents with defined visual templates.</br>&#9679; **Custom neural models** are trained on various document types to extract fields from structured, semi-structured and unstructured documents.|
53-
| [Custom classifier model](#custom-classifier)| The **Custom classifier model** can classify each page in an input file to identify the document(s) within and can also identify multiple documents or multiple instances of a single document within an input file.
53+
| [Custom classification model](#custom-classifier)| The **Custom classification model** can classify each page in an input file to identify the document(s) within and can also identify multiple documents or multiple instances of a single document within an input file.
5454
| [Composed models](#composed-models) | Combine several custom models into a single model to automate processing of diverse document types with a single composed model.
5555

5656
### Read OCR
5757

58-
[:::image type="icon" source="media/studio/read-card.png" :::](https://formrecognizer.appliedai.azure.com/studio/read)
58+
:::image type="icon" source="media/studio/read-card.png" :::
5959

6060
The Read API analyzes and extracts lines, words, their locations, detected languages, and handwritten style if detected.
6161

@@ -68,7 +68,7 @@ The Read API analyzes and extracts lines, words, their locations, detected langu
6868
6969
### Layout analysis
7070

71-
[:::image type="icon" source="media/studio/layout.png":::](https://formrecognizer.appliedai.azure.com/studio/layout)
71+
:::image type="icon" source="media/studio/layout.png":::
7272

7373
The Layout analysis model analyzes and extracts text, tables, selection marks, and other structure elements like titles, section headings, page headers, page footers, and more.
7474

@@ -82,9 +82,9 @@ The Layout analysis model analyzes and extracts text, tables, selection marks, a
8282
8383
### General document
8484

85-
[:::image type="icon" source="media/studio/general-document.png":::](https://formrecognizer.appliedai.azure.com/studio/document)
85+
:::image type="icon" source="media/studio/general-document.png":::
8686

87-
The general document model is ideal for extracting common key-value pairs from forms and documents. It's a pre-trained model and can be directly invoked via the REST API and the SDKs. You can use the general document model as an alternative to training a custom model.
87+
The general document model is ideal for extracting common key-value pairs from forms and documents. It's a pretrained model and can be directly invoked via the REST API and the SDKs. You can use the general document model as an alternative to training a custom model.
8888

8989
***Sample document processed using the [Form Recognizer Studio](https://formrecognizer.appliedai.azure.com/studio/document)***:
9090

@@ -95,7 +95,7 @@ The general document model is ideal for extracting common key-value pairs from f
9595
9696
### Health insurance card
9797

98-
:::image type="content" source="media/studio/health-insurance-logo.png" alt-text="Screenshot of insurance card analysis in Form Recognizer Studio.":::
98+
:::image type="icon" source="media/studio/health-insurance-logo.png":::
9999

100100
The health insurance card model combines powerful Optical Character Recognition (OCR) capabilities with deep learning models to analyze and extract key information from US health insurance cards.
101101

@@ -108,7 +108,7 @@ The health insurance card model combines powerful Optical Character Recognition
108108
109109
### W-2
110110

111-
[:::image type="icon" source="media/studio/w2.png":::](https://formrecognizer.appliedai.azure.com/studio/prebuilt?formType=tax.us.w2)
111+
:::image type="icon" source="media/studio/w2.png":::
112112

113113
The W-2 form model extracts key information reported in each box on a W-2 form. The model supports standard and customized forms from 2018 to the present, including single and multiple forms on one page.
114114

@@ -121,7 +121,7 @@ The W-2 form model extracts key information reported in each box on a W-2 form.
121121
122122
### Invoice
123123

124-
[:::image type="icon" source="media/studio/invoice.png":::](https://formrecognizer.appliedai.azure.com/studio/prebuilt?formType=invoice)
124+
:::image type="icon" source="media/studio/invoice.png":::
125125

126126
The invoice model automates processing of invoices to extracts customer name, billing address, due date, and amount due, line items and other key data. Currently, the model supports English, Spanish, German, French, Italian, Portuguese, and Dutch invoices.
127127

@@ -134,7 +134,7 @@ The invoice model automates processing of invoices to extracts customer name, bi
134134
135135
### Receipt
136136

137-
[:::image type="icon" source="media/studio/receipt.png":::](https://formrecognizer.appliedai.azure.com/studio/prebuilt?formType=receipt)
137+
:::image type="icon" source="media/studio/receipt.png":::
138138

139139
Use the receipt model to scan sales receipts for merchant name, dates, line items, quantities, and totals from printed and handwritten receipts. The version v3.0 also supports single-page hotel receipt processing.
140140

@@ -147,7 +147,7 @@ Use the receipt model to scan sales receipts for merchant name, dates, line item
147147
148148
### Identity document (ID)
149149

150-
[:::image type="icon" source="media/studio/id-document.png":::](https://formrecognizer.appliedai.azure.com/studio/prebuilt?formType=idDocument)
150+
:::image type="icon" source="media/studio/id-document.png":::
151151

152152
Use the Identity document (ID) model to process U.S. Driver's Licenses (all 50 states and District of Columbia) and biographical pages from international passports (excluding visa and other travel documents) to extract key fields.
153153

@@ -160,7 +160,7 @@ Use the Identity document (ID) model to process U.S. Driver's Licenses (all 50 s
160160
161161
### Business card
162162

163-
[:::image type="icon" source="media/studio/business-card.png":::](https://formrecognizer.appliedai.azure.com/studio/prebuilt?formType=businessCard)
163+
:::image type="icon" source="media/studio/business-card.png":::
164164

165165
Use the business card model to scan and extract key information from business card images.
166166

@@ -173,7 +173,7 @@ Use the business card model to scan and extract key information from business ca
173173
174174
### Custom models
175175

176-
[:::image type="icon" source="media/studio/custom.png":::](https://formrecognizer.appliedai.azure.com/studio/custommodel/projects)
176+
:::image type="icon" source="media/studio/custom.png":::
177177

178178
Custom document models analyze and extract data from forms and documents specific to your business. They're trained to recognize form fields within your distinct content and extract key-value pairs and table data. You only need five examples of the same form type to get started.
179179

@@ -188,7 +188,7 @@ Version v3.0 custom model supports signature detection in custom forms (template
188188
189189
#### Custom extraction
190190

191-
[:::image type="icon" source="media/studio/custom-extraction.png":::](https://formrecognizer.appliedai.azure.com/studio/custommodel/projects)
191+
:::image type="icon" source="media/studio/custom-extraction.png":::
192192

193193
Custom extraction model can be one of two types, **custom template** or **custom neural**. To create a custom extraction model, label a dataset of documents with the values you want extracted and train the model on the labeled dataset. You only need five examples of the same form or document type to get started.
194194

@@ -204,12 +204,12 @@ Custom extraction model can be one of two types, **custom template** or **custom
204204
205205
#### Custom classifier
206206

207-
[:::image type="icon" source="media/studio/custom-classifier.png":::](https://formrecognizer.appliedai.azure.com/studio/custommodel/projects)
207+
:::image type="icon" source="media/studio/custom-classifier.png":::
208208

209-
The custom classifier model enables you to identify the document type prior to invoking the extraction model. The classifier model is available starting with the 2023-02-28-preview. Training a custom classifier model requires at least two distinct classes and a minimum of five samples per class.
209+
The custom classification model enables you to identify the document type prior to invoking the extraction model. The classification model is available starting with the 2023-02-28-preview. Training a custom classification model requires at least two distinct classes and a minimum of five samples per class.
210210

211211
> [!div class="nextstepaction"]
212-
> [Learn more: custom classifier model](concept-custom-classifier.md)
212+
> [Learn more: custom classification model](concept-custom-classifier.md)
213213
214214
#### Composed models
215215

0 commit comments

Comments
 (0)