# Detailed Usage ## Reading a Text The core class of **EasyDeepOCR** is the [`ETextReader`](../../../doxygen_cpp/classeVision_1_1EasyDeepOCR_1_1ETextReader.html) [.NET](../../../doxygen_cs/classeVision_1_1EasyDeepOCR_1_1ETextReader.html) [Python](../../../doxygen_python/classeVision_1_1EasyDeepOCR_1_1ETextReader.html). In order to read a text, create a new `ETextReader` instance and initialize it using [`ETextReader::Initialize()`](../../../doxygen_cpp/classeVision_1_1EasyDeepOCR_1_1ETextReader.html#a8aa4a233c236ab66c860b792fdd8fbc3) [.NET](../../../doxygen_cs/classeVision_1_1EasyDeepOCR_1_1ETextReader.html#a5ca732cfe514ac1ca50059551abba832) [Python](../../../doxygen_python/classeVision_1_1EasyDeepOCR_1_1ETextReader.html#a05a2381cf55e5a93bc140d58c3de4661). To read the texts in a loaded image, use [`ETextReader::Read()`](../../../doxygen_cpp/classeVision_1_1EasyDeepOCR_1_1ETextReader.html#a89af65e87d9b4bcb08c67ccb6144bef6) [.NET](../../../doxygen_cs/classeVision_1_1EasyDeepOCR_1_1ETextReader.html#ab4c5317f2a21715a57f29a5d7f28f4d1) [Python](../../../doxygen_python/classeVision_1_1EasyDeepOCR_1_1ETextReader.html#a74442f7cf99d92154de65b581cdc78a8). This method will return a vector of [`EasyDeepOCR::EText`](../../../doxygen_cpp/classeVision_1_1EasyDeepOCR_1_1EText.html) [.NET](../../../doxygen_cs/classeVision_1_1EasyDeepOCR_1_1EText.html) [Python](../../../doxygen_python/classeVision_1_1EasyDeepOCR_1_1EText.html). #### NOTE When the topology is not specified, the returned [`EText`](../../../doxygen_cpp/classeVision_1_1EasyDeepOCR_1_1EText.html) [.NET](../../../doxygen_cs/classeVision_1_1EasyDeepOCR_1_1EText.html) [Python](../../../doxygen_python/classeVision_1_1EasyDeepOCR_1_1EText.html) always contains a single [`ETextLine`](../../../doxygen_cpp/classeVision_1_1EasyDeepOCR_1_1ETextLine.html) [.NET](../../../doxygen_cs/classeVision_1_1EasyDeepOCR_1_1ETextLine.html) [Python](../../../doxygen_python/classeVision_1_1EasyDeepOCR_1_1ETextLine.html). #### NOTE The method [`ETextReader::Initialize`](../../../doxygen_cpp/classeVision_1_1EasyDeepOCR_1_1ETextReader.html#a8aa4a233c236ab66c860b792fdd8fbc3) [.NET](../../../doxygen_cs/classeVision_1_1EasyDeepOCR_1_1ETextReader.html#a5ca732cfe514ac1ca50059551abba832) [Python](../../../doxygen_python/classeVision_1_1EasyDeepOCR_1_1ETextReader.html#a05a2381cf55e5a93bc140d58c3de4661) is designed to pre-allocate memory and to load the necessary resources needed by the [`ETextReader`](../../../doxygen_cpp/classeVision_1_1EasyDeepOCR_1_1ETextReader.html) [.NET](../../../doxygen_cs/classeVision_1_1EasyDeepOCR_1_1ETextReader.html) [Python](../../../doxygen_python/classeVision_1_1EasyDeepOCR_1_1ETextReader.html). * This initialization can be time-consuming, but it must only be performed once after an instantiation, a loading from memory or a copy from another instance. * The duration of the process ranges from a few seconds to several minutes, depending on the execution settings and the computing platform. #### SEE ALSO [Code snippet](../../../resources/code_snippets/text_and_code_reading/easydeepocr/readingatext.html.md) ## Getting a Score Each [`ETextLine`](../../../doxygen_cpp/classeVision_1_1EasyDeepOCR_1_1ETextLine.html) [.NET](../../../doxygen_cs/classeVision_1_1EasyDeepOCR_1_1ETextLine.html) [Python](../../../doxygen_python/classeVision_1_1EasyDeepOCR_1_1ETextLine.html) and [`EText`](../../../doxygen_cpp/classeVision_1_1EasyDeepOCR_1_1EText.html) [.NET](../../../doxygen_cs/classeVision_1_1EasyDeepOCR_1_1EText.html) [Python](../../../doxygen_python/classeVision_1_1EasyDeepOCR_1_1EText.html) returned by the [`ETextReader`](../../../doxygen_cpp/classeVision_1_1EasyDeepOCR_1_1ETextReader.html) [.NET](../../../doxygen_cs/classeVision_1_1EasyDeepOCR_1_1ETextReader.html) [Python](../../../doxygen_python/classeVision_1_1EasyDeepOCR_1_1ETextReader.html) has a score attached to it. ### The score of an `ETextLine` The score of an [`ETextLine`](../../../doxygen_cpp/classeVision_1_1EasyDeepOCR_1_1ETextLine.html) [.NET](../../../doxygen_cs/classeVision_1_1EasyDeepOCR_1_1ETextLine.html) [Python](../../../doxygen_python/classeVision_1_1EasyDeepOCR_1_1ETextLine.html): * Is the arithmetic mean of the detection score and the recognition score. * Is in the interval `[0.0; 1.0]`. * You can use it to get an approximation of the reading quality of the underlying text. Use [`ETextLine::GetScore`](../../../doxygen_cpp/classeVision_1_1EasyDeepOCR_1_1ETextLine.html#a174f9f47b9383c454448bb278eedfd2a) [.NET](../../../doxygen_cs/classeVision_1_1EasyDeepOCR_1_1ETextLine.html#a2e6c59307ede3648487696bf34215944) [Python](../../../doxygen_python/classeVision_1_1EasyDeepOCR_1_1ETextLine.html#a8a9d5c721ded2d2ed8682a25de9b8a24) to get the score of an `ETextLine`. ### The score of an `EText` The score of an [`EText`](../../../doxygen_cpp/classeVision_1_1EasyDeepOCR_1_1EText.html) [.NET](../../../doxygen_cs/classeVision_1_1EasyDeepOCR_1_1EText.html) [Python](../../../doxygen_python/classeVision_1_1EasyDeepOCR_1_1EText.html) (that is composed of multiple [`ETextLine`](../../../doxygen_cpp/classeVision_1_1EasyDeepOCR_1_1ETextLine.html) [.NET](../../../doxygen_cs/classeVision_1_1EasyDeepOCR_1_1ETextLine.html) [Python](../../../doxygen_python/classeVision_1_1EasyDeepOCR_1_1ETextLine.html)): * Is the average of all line scores * Is in the interval `[0.0; 1.0]`. * You can use it to get an approximation of the reading quality of the underlying lines. Use [`EText::GetScore`](../../../doxygen_cpp/classeVision_1_1EasyDeepOCR_1_1EText.html#adadf2b57d7b31c55f4d4a46536622e36) [.NET](../../../doxygen_cs/classeVision_1_1EasyDeepOCR_1_1EText.html#aefc37fbf862806da1c04ef3d303c889c) [Python](../../../doxygen_python/classeVision_1_1EasyDeepOCR_1_1EText.html#aa7091855901fb5b51fe8cbe7ec0c3064) to get the score of an `EText`. #### SEE ALSO [Code snippet](../../../resources/code_snippets/text_and_code_reading/easydeepocr/getscore.html.md) ## Drawing an ETextLine or an EText * Use the methods `Draw` to graphically draw an [`ETextLine`](../../../doxygen_cpp/classeVision_1_1EasyDeepOCR_1_1ETextLine.html) [.NET](../../../doxygen_cs/classeVision_1_1EasyDeepOCR_1_1ETextLine.html) [Python](../../../doxygen_python/classeVision_1_1EasyDeepOCR_1_1ETextLine.html) or an [`EText`](../../../doxygen_cpp/classeVision_1_1EasyDeepOCR_1_1EText.html) [.NET](../../../doxygen_cs/classeVision_1_1EasyDeepOCR_1_1EText.html) [Python](../../../doxygen_python/classeVision_1_1EasyDeepOCR_1_1EText.html). * Use the class [`ETextDrawingParameters`](../../../doxygen_cpp/classeVision_1_1EasyDeepOCR_1_1ETextDrawingParameters.html) [.NET](../../../doxygen_cs/classeVision_1_1EasyDeepOCR_1_1ETextDrawingParameters.html) [Python](../../../doxygen_python/classeVision_1_1EasyDeepOCR_1_1ETextDrawingParameters.html) to set the drawing attributes and display: * The text box. * The text line box. * The text string. * The text direction, with a configurable arrow length. ![](assets/images/easydeepocr/drawing_an_etext.webp) #### SEE ALSO [Sample program](../../../resources/sample_programs/text_and_code_reading/easydeepocrread.html.md) ## Specifying a Topology A topology is a canvas that a given string can satisfy, or not. Specifying a topology improves the relevance of the outputs of [`ETextReader`](../../../doxygen_cpp/classeVision_1_1EasyDeepOCR_1_1ETextReader.html) [.NET](../../../doxygen_cs/classeVision_1_1EasyDeepOCR_1_1ETextReader.html) [Python](../../../doxygen_python/classeVision_1_1EasyDeepOCR_1_1ETextReader.html) because only the texts that fit into the canvas are returned. Before applying this filter, the [`ETextReader`](../../../doxygen_cpp/classeVision_1_1EasyDeepOCR_1_1ETextReader.html) [.NET](../../../doxygen_cs/classeVision_1_1EasyDeepOCR_1_1ETextReader.html) [Python](../../../doxygen_python/classeVision_1_1EasyDeepOCR_1_1ETextReader.html) tries to correct a few small mistakes in order to prevent excessive filtering. In addition, the topology triggers the grouping of lines into texts. In other words, an [`ETextReader`](../../../doxygen_cpp/classeVision_1_1EasyDeepOCR_1_1ETextReader.html) [.NET](../../../doxygen_cs/classeVision_1_1EasyDeepOCR_1_1ETextReader.html) [Python](../../../doxygen_python/classeVision_1_1EasyDeepOCR_1_1ETextReader.html) returns [`EText`](../../../doxygen_cpp/classeVision_1_1EasyDeepOCR_1_1EText.html) [.NET](../../../doxygen_cs/classeVision_1_1EasyDeepOCR_1_1EText.html) [Python](../../../doxygen_python/classeVision_1_1EasyDeepOCR_1_1EText.html) composed of several [`ETextLine`](../../../doxygen_cpp/classeVision_1_1EasyDeepOCR_1_1ETextLine.html) [.NET](../../../doxygen_cs/classeVision_1_1EasyDeepOCR_1_1ETextLine.html) [Python](../../../doxygen_python/classeVision_1_1EasyDeepOCR_1_1ETextLine.html) only when several lines are required by the topology. In practice, a topology is an instance of the class [`ETopology`](../../../doxygen_cpp/classeVision_1_1ETopology.html) [.NET](../../../doxygen_cs/classeVision_1_1ETopology.html) [Python](../../../doxygen_python/classeVision_1_1ETopology.html), which is basically a vector of [`ETopologyLine`](../../../doxygen_cpp/classeVision_1_1ETopologyLine.html) [.NET](../../../doxygen_cs/classeVision_1_1ETopologyLine.html) [Python](../../../doxygen_python/classeVision_1_1ETopologyLine.html), with the nth entry referring to the nth text line. As mentioned previously, a topology thus never matches a text whose number of lines is different from the size of the vector [`ETopologyLine`](../../../doxygen_cpp/classeVision_1_1ETopologyLine.html) [.NET](../../../doxygen_cs/classeVision_1_1ETopologyLine.html) [Python](../../../doxygen_python/classeVision_1_1ETopologyLine.html). The canvas mentioned in the first paragraph must be specified inside the class [`ETopologyLine`](../../../doxygen_cpp/classeVision_1_1ETopologyLine.html) [.NET](../../../doxygen_cs/classeVision_1_1ETopologyLine.html) [Python](../../../doxygen_python/classeVision_1_1ETopologyLine.html) and in particular, by setting its “format string”. This “format string” is a string that can be interpreted using: * The **eVision** simplified format * A standard regular expression format. #### SEE ALSO [Code snippet](../../../resources/code_snippets/text_and_code_reading/easydeepocr/specifyingatopology.html.md) ### The eVision Simplified Format * Each character from the “format string” represents a “character class”. * An [`ETextLine`](../../../doxygen_cpp/classeVision_1_1EasyDeepOCR_1_1ETextLine.html) [.NET](../../../doxygen_cs/classeVision_1_1EasyDeepOCR_1_1ETextLine.html) [Python](../../../doxygen_python/classeVision_1_1EasyDeepOCR_1_1ETextLine.html) satisfies the [`ETopologyLine`](../../../doxygen_cpp/classeVision_1_1ETopologyLine.html) [.NET](../../../doxygen_cs/classeVision_1_1ETopologyLine.html) [Python](../../../doxygen_python/classeVision_1_1ETopologyLine.html) if each of its characters belongs to the corresponding “character class” specified by the “format string”. * The **eVision** simplified format is composed of the following eight “character classes”: * `A`: an uppercase ASCII letter: `ABCDEFGHIJKLMNOPQRSTUVWXYZ` * `a`: a lowercase ASCII letter: `abcdefghijklmnopqrstuvwxyz` * `0`: a digit: `0123456789` * `P`: an ASCII punctuation character: `!"#$%&\'()*+,-./:;<=>?@[\]^_`{|}~` * `V`: a character belonging to either A or 0 * `X`: a character belonging to either A, a, 0 or P * ` `: a space * `S`: a character belonging to either X or a space ### “Literal Groups” * You can specify a “literal group”, that is a group of characters that should appear verbatim in the [`ETextLine`](../../../doxygen_cpp/classeVision_1_1EasyDeepOCR_1_1ETextLine.html) [.NET](../../../doxygen_cs/classeVision_1_1EasyDeepOCR_1_1ETextLine.html) [Python](../../../doxygen_python/classeVision_1_1EasyDeepOCR_1_1ETextLine.html). * These “literal groups” must be included inside square brackets `[]`. Note that square brackets themselves must not appear in a literal group. * For more flexibility, you can use a “range quantifier” or an “exact quantifier” just after a “character class”: * Add a “range quantifier” as `{m,n}` to specify that the preceding “character class” must be matched between `m` and `n` times. * Add an “exact quantifier” as `{n}` to specify that the preceding “character class” must be matched exactly `n` times. * Examples * The “format string” `[Lot:] 00[-]0{1,3}` matches all the following strings: * `Lot: 12-783` * `Lot: 74-1` * `Lot: 09-447` * `Lot: 85-75` * The “format string” `[Exp:] 00[/]00[/]0{4}` matches all the following strings: * `Exp: 06/07/2024` * `Exp: 01/03/1995` * `Exp: 75/42/0065` * `Exp: 01/22/1569` ### The Regular Expression Format * The “format string” is a regular expression written using the **ECMAScript regular expression grammar**. * To learn how to use the regular expression format, see the [Regex 101](https://regex101.com/) web application. * This grammar is described in the [ECMAScript Language Specification, ECMA-262, Chapter 15 part 10, RegExp (Regular Expression) Objects](https://web.archive.org/web/20260831102636/https://262.ecma-international.org/5.1/#sec-15.10). ## Setting the Text Angle The text angle is an optional parameter of [`ETextReader`](../../../doxygen_cpp/classeVision_1_1EasyDeepOCR_1_1ETextReader.html) [.NET](../../../doxygen_cs/classeVision_1_1EasyDeepOCR_1_1ETextReader.html) [Python](../../../doxygen_python/classeVision_1_1EasyDeepOCR_1_1ETextReader.html) that controls the reading direction of the texts that are returned. * Use [`ETextReader::SetTextAngle`](../../../doxygen_cpp/classeVision_1_1EasyDeepOCR_1_1ETextReader.html#a2c9a6af1bab6ba83699abaa446c10ca6) [.NET](../../../doxygen_cs/classeVision_1_1EasyDeepOCR_1_1ETextReader.html#af26d63afb6c8877206937bf7c6dafbea) [Python](../../../doxygen_python/classeVision_1_1EasyDeepOCR_1_1ETextReader.html#a031915c49655f185aaad366962c1b3e1) to set an angle and [`ETextReader::GetHasTextAngle`](../../../doxygen_cpp/classeVision_1_1EasyDeepOCR_1_1ETextReader.html#a465890926bad485e99bfedd0887bf76c) [.NET](../../../doxygen_cs/classeVision_1_1EasyDeepOCR_1_1ETextReader.html#a2bad996f04b4c5cd4a4cd31c4d4bed9b) [Python](../../../doxygen_python/classeVision_1_1EasyDeepOCR_1_1ETextReader.html#a6e4113d0cfe79cbb076ba2296e33f38d) to check if an angle is specified. * When the text angle is set, [`ETextReader`](../../../doxygen_cpp/classeVision_1_1EasyDeepOCR_1_1ETextReader.html) [.NET](../../../doxygen_cs/classeVision_1_1EasyDeepOCR_1_1ETextReader.html) [Python](../../../doxygen_python/classeVision_1_1EasyDeepOCR_1_1ETextReader.html) determines the direction of the texts by selecting the orientation that is closest to the specified angle among the four cardinal directions. #### HINT This is particularly useful when the approximate orientation of the texts is known. | Text angle | 10° | 80° | -120° | -35° | |-------------------|--------------------------------------------------|--------------------------------------------------|--------------------------------------------------|--------------------------------------------------| | Reading direction | ![](assets/images/easydeepocr/text_angle_1.webp) | ![](assets/images/easydeepocr/text_angle_2.webp) | ![](assets/images/easydeepocr/text_angle_3.webp) | ![](assets/images/easydeepocr/text_angle_4.webp) | * Use [`ETextReader::UnsetTextAngle`](../../../doxygen_cpp/classeVision_1_1EasyDeepOCR_1_1ETextReader.html#a2cb9394e27668cf71c9efee0b2f0b211) [.NET](../../../doxygen_cs/classeVision_1_1EasyDeepOCR_1_1ETextReader.html#abb88bdab625b742144fd516059c6067f) [Python](../../../doxygen_python/classeVision_1_1EasyDeepOCR_1_1ETextReader.html#ad54a20cf375e9f5e403d2aa33ae6740f) to delete any set angle. * When the text angle is not set, [`ETextReader`](../../../doxygen_cpp/classeVision_1_1EasyDeepOCR_1_1ETextReader.html) [.NET](../../../doxygen_cs/classeVision_1_1EasyDeepOCR_1_1ETextReader.html) [Python](../../../doxygen_python/classeVision_1_1EasyDeepOCR_1_1ETextReader.html) automatically chooses the reading direction among the four cardinal directions based on its internal heuristics. ## Performing an Optimization You can optimize the [`ETextReader`](../../../doxygen_cpp/classeVision_1_1EasyDeepOCR_1_1ETextReader.html) [.NET](../../../doxygen_cs/classeVision_1_1EasyDeepOCR_1_1ETextReader.html) [Python](../../../doxygen_python/classeVision_1_1EasyDeepOCR_1_1ETextReader.html) for your own specific use case. After this optimization: * The reader only returns the texts that belong to the same “customer use case” as the one used for the optimization. * The processing speed may increase. * **EasyDeepOCR** may find challenging texts that were not detected before the optimization. This optimization is based on the method [`ETextReader::Optimize`](../../../doxygen_cpp/classeVision_1_1EasyDeepOCR_1_1ETextReader.html#a22f3b11b24552c6f07defbc033203741) [.NET](../../../doxygen_cs/classeVision_1_1EasyDeepOCR_1_1ETextReader.html#a9dd2fd7f7ac49b8235bb383662c80960) [Python](../../../doxygen_python/classeVision_1_1EasyDeepOCR_1_1ETextReader.html#acd534b7cd06317be0bb6c3130673403b) that requires an instance of the class [`ESampleList`](../../../doxygen_cpp/classeVision_1_1EasyDeepOCR_1_1ESampleList.html) [.NET](../../../doxygen_cs/classeVision_1_1EasyDeepOCR_1_1ESampleList.html) [Python](../../../doxygen_python/classeVision_1_1EasyDeepOCR_1_1ESampleList.html). * The class [`ESampleList`](../../../doxygen_cpp/classeVision_1_1EasyDeepOCR_1_1ESampleList.html) [.NET](../../../doxygen_cs/classeVision_1_1EasyDeepOCR_1_1ESampleList.html) [Python](../../../doxygen_python/classeVision_1_1EasyDeepOCR_1_1ESampleList.html) is a container that gathers all the information about the “customer use case”. #### NOTE See section [Building a Sample List](setting_the_parameters.html.md#edo-building-sample-list). Considering that the [`ESampleList`](../../../doxygen_cpp/classeVision_1_1EasyDeepOCR_1_1ESampleList.html) [.NET](../../../doxygen_cs/classeVision_1_1EasyDeepOCR_1_1ESampleList.html) [Python](../../../doxygen_python/classeVision_1_1EasyDeepOCR_1_1ESampleList.html) is filled, the optimization only requires a few lines of code, as illustrated below. ### C++ ```cpp #include ``` ```cpp using namespace eVision; namespace EDO = eVision::EasyDeepOCR; // Create an ESample vector std::vector samples; // Fill the vector // ... // Create an ESampleList instance EDO::ESampleList sampleList; // Set the samples sampleList.SetSamples(samples); // Create an ETextReader instance EDO::ETextReader reader; // Initialize the ETextReader reader.Initialize(); // Optimize the ETextReader EDO::EOptimizationReport report = reader.Optimize(sampleList); // ... ``` ### C# ```cs using eVision; using EDO = eVision.EasyDeepOCR; ``` ```cs // Create an ESample vector EDO.ESample[] samples = new EDO.ESample[] { } ; // Fill the vector // ... // Create an ESampleList instance EDO.ESampleList sampleList = new EDO.ESampleList(); // Set the samples sampleList.Samples = samples; // Create an ETextReader instance EDO.ETextReader reader = new EDO.ETextReader(); // Initialize the ETextReader reader.Initialize(); // Optimize the ETextReader EDO.EOptimizationReport report = reader.Optimize(sampleList); // ... ``` ### Python ```py import eVision from eVision import EasyDeepOCR as EDO # Create an ESample vector samples = [] # Fill the vector # ... # Create an ESampleList instance sampleList = EDO.ESampleList() # Set the samples sampleList.Samples = samples # Create an ETextReader instance reader = EDO.ETextReader() # Initialize the ETextReader reader.Initialize() # Optimize the ETextReader report = reader.Optimize(sampleList); # ... ``` ## Splitting the Pipeline #### HINT While the function [`ETextReader::Read`](../../../doxygen_cpp/classeVision_1_1EasyDeepOCR_1_1ETextReader.html#a89af65e87d9b4bcb08c67ccb6144bef6) [.NET](../../../doxygen_cs/classeVision_1_1EasyDeepOCR_1_1ETextReader.html#ab4c5317f2a21715a57f29a5d7f28f4d1) [Python](../../../doxygen_python/classeVision_1_1EasyDeepOCR_1_1ETextReader.html#a74442f7cf99d92154de65b581cdc78a8) is suitable for straightforward OCR tasks, the split pipeline becomes beneficial when you require a custom processing for a specific use case. * The pipeline [`ETextReader::Read`](../../../doxygen_cpp/classeVision_1_1EasyDeepOCR_1_1ETextReader.html#a89af65e87d9b4bcb08c67ccb6144bef6) [.NET](../../../doxygen_cs/classeVision_1_1EasyDeepOCR_1_1ETextReader.html#ab4c5317f2a21715a57f29a5d7f28f4d1) [Python](../../../doxygen_python/classeVision_1_1EasyDeepOCR_1_1ETextReader.html#a74442f7cf99d92154de65b581cdc78a8) consists of 3 distinct functions that are invoked sequentially: * [`ETextReader::Localize`](../../../doxygen_cpp/classeVision_1_1EasyDeepOCR_1_1ETextReader.html#a245b6f00ef57348eeffd81aa0cd7f9cf) [.NET](../../../doxygen_cs/classeVision_1_1EasyDeepOCR_1_1ETextReader.html#af8851fdaeaca57e83e7e0e64afd23c74) [Python](../../../doxygen_python/classeVision_1_1EasyDeepOCR_1_1ETextReader.html#ac9b41c16d32f8ed43e4ab1efc9803975) detects the text areas. * [`ETextReader::Recognize`](../../../doxygen_cpp/classeVision_1_1EasyDeepOCR_1_1ETextReader.html#a24c134563a6fcdc0b13ce92170b4eab9) [.NET](../../../doxygen_cs/classeVision_1_1EasyDeepOCR_1_1ETextReader.html#ac09f3e7b3d5497c0200a59b022387238) [Python](../../../doxygen_python/classeVision_1_1EasyDeepOCR_1_1ETextReader.html#a4901ea3a07c9085d16924e375d5fcdd5) converts the detected areas to strings. * [`ETextReader::Merge`](../../../doxygen_cpp/classeVision_1_1EasyDeepOCR_1_1ETextReader.html#a21e26045505e85a374d18500a6b83c54) [.NET](../../../doxygen_cs/classeVision_1_1EasyDeepOCR_1_1ETextReader.html#acbad3ca833948f87937fdae817b45fbe) [Python](../../../doxygen_python/classeVision_1_1EasyDeepOCR_1_1ETextReader.html#a82990a87ac8245e283f36f6688ca7cce) combines the text lines based on a topology, if specified. * These 3 functions provide an enhanced control through capabilities such as: * Inserting custom processing between steps. * Skipping unnecessary steps. * Accessing intermediate results. * Applying different parameters for specific regions. #### SEE ALSO [Code snippet](../../../resources/code_snippets/text_and_code_reading/easydeepocr/splittingthepipeline.html.md) ### Using `ETextReader::Localize` The method [`ETextReader::Localize`](../../../doxygen_cpp/classeVision_1_1EasyDeepOCR_1_1ETextReader.html#a245b6f00ef57348eeffd81aa0cd7f9cf) [.NET](../../../doxygen_cs/classeVision_1_1EasyDeepOCR_1_1ETextReader.html#af8851fdaeaca57e83e7e0e64afd23c74) [Python](../../../doxygen_python/classeVision_1_1EasyDeepOCR_1_1ETextReader.html#ac9b41c16d32f8ed43e4ab1efc9803975) identifies regions in an image that contain text lines and returns them as rectangles. * This method is appropriate for identifying the locations of text lines in an image without reading their contents. * This approach is particularly useful in scenarios where certain regions might need filtering based on size, position or other geometric properties before proceeding with the recognition. * It also serves as an excellent first step when building a custom OCR pipeline that requires specialized handling of different text regions. ### Using `ETextReader::Recognize` The method [`ETextReader::Recognize`](../../../doxygen_cpp/classeVision_1_1EasyDeepOCR_1_1ETextReader.html#a24c134563a6fcdc0b13ce92170b4eab9) [.NET](../../../doxygen_cs/classeVision_1_1EasyDeepOCR_1_1ETextReader.html#ac09f3e7b3d5497c0200a59b022387238) [Python](../../../doxygen_python/classeVision_1_1EasyDeepOCR_1_1ETextReader.html#a4901ea3a07c9085d16924e375d5fcdd5) accepts an [`ERegion`](../../../doxygen_cpp/classeVision_1_1ERegion.html) [.NET](../../../doxygen_cs/classeVision_1_1ERegion.html) [Python](../../../doxygen_python/classeVision_1_1ERegion.html) or an [`ERectangle`](../../../doxygen_cpp/classeVision_1_1ERectangle.html) [.NET](../../../doxygen_cs/classeVision_1_1ERectangle.html) [Python](../../../doxygen_python/classeVision_1_1ERectangle.html) as input and outputs a [`ETextLine`](../../../doxygen_cpp/classeVision_1_1EasyDeepOCR_1_1ETextLine.html) [.NET](../../../doxygen_cs/classeVision_1_1EasyDeepOCR_1_1ETextLine.html) [Python](../../../doxygen_python/classeVision_1_1EasyDeepOCR_1_1ETextLine.html). * It can work with either a miniature image containing only text or a region within a larger image. * This method is particularly valuable when working with images that contain text in specific areas requiring different processing parameters, such as different topology constraints. ### Using `ETextReader::Merge` The method [`ETextReader::Merge`](../../../doxygen_cpp/classeVision_1_1EasyDeepOCR_1_1ETextReader.html#a21e26045505e85a374d18500a6b83c54) [.NET](../../../doxygen_cs/classeVision_1_1EasyDeepOCR_1_1ETextReader.html#acbad3ca833948f87937fdae817b45fbe) [Python](../../../doxygen_python/classeVision_1_1EasyDeepOCR_1_1ETextReader.html#a82990a87ac8245e283f36f6688ca7cce) combines recognized multiple [`ETextLine`](../../../doxygen_cpp/classeVision_1_1EasyDeepOCR_1_1ETextLine.html) [.NET](../../../doxygen_cs/classeVision_1_1EasyDeepOCR_1_1ETextLine.html) [Python](../../../doxygen_python/classeVision_1_1EasyDeepOCR_1_1ETextLine.html) into structured objects [`EText`](../../../doxygen_cpp/classeVision_1_1EasyDeepOCR_1_1EText.html) [.NET](../../../doxygen_cs/classeVision_1_1EasyDeepOCR_1_1EText.html) [Python](../../../doxygen_python/classeVision_1_1EasyDeepOCR_1_1EText.html) based on the defined [`ETopology`](../../../doxygen_cpp/classeVision_1_1ETopology.html) [.NET](../../../doxygen_cs/classeVision_1_1ETopology.html) [Python](../../../doxygen_python/classeVision_1_1ETopology.html). * This method becomes valuable when working with images where the relationship between the text lines carries a semantic meaning. * By organizing the text according to the topology, the method [`ETextReader::Merge`](../../../doxygen_cpp/classeVision_1_1EasyDeepOCR_1_1ETextReader.html#a21e26045505e85a374d18500a6b83c54) [.NET](../../../doxygen_cs/classeVision_1_1EasyDeepOCR_1_1ETextReader.html#acbad3ca833948f87937fdae817b45fbe) [Python](../../../doxygen_python/classeVision_1_1EasyDeepOCR_1_1ETextReader.html#a82990a87ac8245e283f36f6688ca7cce) preserves the logical relationships between the different text elements.