diff options
Diffstat (limited to 'google/cloud/vision/v1p3beta1/text_annotation.proto')
| -rw-r--r-- | google/cloud/vision/v1p3beta1/text_annotation.proto | 259 |
1 files changed, 259 insertions, 0 deletions
diff --git a/google/cloud/vision/v1p3beta1/text_annotation.proto b/google/cloud/vision/v1p3beta1/text_annotation.proto new file mode 100644 index 000000000..3c256c577 --- /dev/null +++ b/google/cloud/vision/v1p3beta1/text_annotation.proto @@ -0,0 +1,259 @@ +// Copyright 2018 Google Inc. +// +// Licensed under the Apache License, Version 2.0 (the "License"); +// you may not use this file except in compliance with the License. +// You may obtain a copy of the License at +// +// http://www.apache.org/licenses/LICENSE-2.0 +// +// Unless required by applicable law or agreed to in writing, software +// distributed under the License is distributed on an "AS IS" BASIS, +// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +// See the License for the specific language governing permissions and +// limitations under the License. + +syntax = "proto3"; + +package google.cloud.vision.v1p3beta1; + +import "google/api/annotations.proto"; +import "google/cloud/vision/v1p3beta1/geometry.proto"; + +option cc_enable_arenas = true; +option go_package = "google.golang.org/genproto/googleapis/cloud/vision/v1p3beta1;vision"; +option java_multiple_files = true; +option java_outer_classname = "TextAnnotationProto"; +option java_package = "com.google.cloud.vision.v1p3beta1"; + +// TextAnnotation contains a structured representation of OCR extracted text. +// The hierarchy of an OCR extracted text structure is like this: +// TextAnnotation -> Page -> Block -> Paragraph -> Word -> Symbol +// Each structural component, starting from Page, may further have their own +// properties. Properties describe detected languages, breaks etc.. Please refer +// to the +// [TextAnnotation.TextProperty][google.cloud.vision.v1p3beta1.TextAnnotation.TextProperty] +// message definition below for more detail. +message TextAnnotation { + // Detected language for a structural component. + message DetectedLanguage { + // The BCP-47 language code, such as "en-US" or "sr-Latn". For more + // information, see + // http://www.unicode.org/reports/tr35/#Unicode_locale_identifier. + string language_code = 1; + + // Confidence of detected language. Range [0, 1]. + float confidence = 2; + } + + // Detected start or end of a structural component. + message DetectedBreak { + // Enum to denote the type of break found. New line, space etc. + enum BreakType { + // Unknown break label type. + UNKNOWN = 0; + + // Regular space. + SPACE = 1; + + // Sure space (very wide). + SURE_SPACE = 2; + + // Line-wrapping break. + EOL_SURE_SPACE = 3; + + // End-line hyphen that is not present in text; does not co-occur with + // `SPACE`, `LEADER_SPACE`, or `LINE_BREAK`. + HYPHEN = 4; + + // Line break that ends a paragraph. + LINE_BREAK = 5; + } + + // Detected break type. + BreakType type = 1; + + // True if break prepends the element. + bool is_prefix = 2; + } + + // Additional information detected on the structural component. + message TextProperty { + // A list of detected languages together with confidence. + repeated DetectedLanguage detected_languages = 1; + + // Detected start or end of a text segment. + DetectedBreak detected_break = 2; + } + + // List of pages detected by OCR. + repeated Page pages = 1; + + // UTF-8 text detected on the pages. + string text = 2; +} + +// Detected page from OCR. +message Page { + // Additional information detected on the page. + TextAnnotation.TextProperty property = 1; + + // Page width. For PDFs the unit is points. For images (including + // TIFFs) the unit is pixels. + int32 width = 2; + + // Page height. For PDFs the unit is points. For images (including + // TIFFs) the unit is pixels. + int32 height = 3; + + // List of blocks of text, images etc on this page. + repeated Block blocks = 4; + + // Confidence of the OCR results on the page. Range [0, 1]. + float confidence = 5; +} + +// Logical element on the page. +message Block { + // Type of a block (text, image etc) as identified by OCR. + enum BlockType { + // Unknown block type. + UNKNOWN = 0; + + // Regular text block. + TEXT = 1; + + // Table block. + TABLE = 2; + + // Image block. + PICTURE = 3; + + // Horizontal/vertical line box. + RULER = 4; + + // Barcode block. + BARCODE = 5; + } + + // Additional information detected for the block. + TextAnnotation.TextProperty property = 1; + + // The bounding box for the block. + // The vertices are in the order of top-left, top-right, bottom-right, + // bottom-left. When a rotation of the bounding box is detected the rotation + // is represented as around the top-left corner as defined when the text is + // read in the 'natural' orientation. + // For example: + // + // * when the text is horizontal it might look like: + // + // 0----1 + // | | + // 3----2 + // + // * when it's rotated 180 degrees around the top-left corner it becomes: + // + // 2----3 + // | | + // 1----0 + // + // and the vertice order will still be (0, 1, 2, 3). + BoundingPoly bounding_box = 2; + + // List of paragraphs in this block (if this blocks is of type text). + repeated Paragraph paragraphs = 3; + + // Detected block type (text, image etc) for this block. + BlockType block_type = 4; + + // Confidence of the OCR results on the block. Range [0, 1]. + float confidence = 5; +} + +// Structural unit of text representing a number of words in certain order. +message Paragraph { + // Additional information detected for the paragraph. + TextAnnotation.TextProperty property = 1; + + // The bounding box for the paragraph. + // The vertices are in the order of top-left, top-right, bottom-right, + // bottom-left. When a rotation of the bounding box is detected the rotation + // is represented as around the top-left corner as defined when the text is + // read in the 'natural' orientation. + // For example: + // * when the text is horizontal it might look like: + // 0----1 + // | | + // 3----2 + // * when it's rotated 180 degrees around the top-left corner it becomes: + // 2----3 + // | | + // 1----0 + // and the vertice order will still be (0, 1, 2, 3). + BoundingPoly bounding_box = 2; + + // List of words in this paragraph. + repeated Word words = 3; + + // Confidence of the OCR results for the paragraph. Range [0, 1]. + float confidence = 4; +} + +// A word representation. +message Word { + // Additional information detected for the word. + TextAnnotation.TextProperty property = 1; + + // The bounding box for the word. + // The vertices are in the order of top-left, top-right, bottom-right, + // bottom-left. When a rotation of the bounding box is detected the rotation + // is represented as around the top-left corner as defined when the text is + // read in the 'natural' orientation. + // For example: + // * when the text is horizontal it might look like: + // 0----1 + // | | + // 3----2 + // * when it's rotated 180 degrees around the top-left corner it becomes: + // 2----3 + // | | + // 1----0 + // and the vertice order will still be (0, 1, 2, 3). + BoundingPoly bounding_box = 2; + + // List of symbols in the word. + // The order of the symbols follows the natural reading order. + repeated Symbol symbols = 3; + + // Confidence of the OCR results for the word. Range [0, 1]. + float confidence = 4; +} + +// A single symbol representation. +message Symbol { + // Additional information detected for the symbol. + TextAnnotation.TextProperty property = 1; + + // The bounding box for the symbol. + // The vertices are in the order of top-left, top-right, bottom-right, + // bottom-left. When a rotation of the bounding box is detected the rotation + // is represented as around the top-left corner as defined when the text is + // read in the 'natural' orientation. + // For example: + // * when the text is horizontal it might look like: + // 0----1 + // | | + // 3----2 + // * when it's rotated 180 degrees around the top-left corner it becomes: + // 2----3 + // | | + // 1----0 + // and the vertice order will still be (0, 1, 2, 3). + BoundingPoly bounding_box = 2; + + // The actual UTF-8 representation of the symbol. + string text = 3; + + // Confidence of the OCR results for the symbol. Range [0, 1]. + float confidence = 4; +} |