Read Tool

Adjust the Character Size search box. The search box cannot be rotated. Place the character size around a character.

When using User Trained mode, or the Pre-Trained v1 Standard training mode, place the search box tightly around a character. This model works best with monospace fonts.

When using one of the Pre-Trained v2 training modes, place the search box loosely around an average-sized character. The V2 models can recognize variable width fonts. For example, if the text you want to process contains a W that is significantly wider than other characters, the search box can be smaller than the W, but needs to be bigger than a V.

If you are using the Pre-Trained v2 Complete model, which also supports lowercase characters, you can set the height of the character size box between the height of uppercase characters and the height of lowercase characters.

Defines the minimum confidence threshold for classifying a candidate as a character. The final scores combines the likelihood of being a character and matching a specific character class. As a result, low-scoring characters can still appear as possible characters.

You can set the threshold between 0 and 100, the default value is 50.

Use the slider, or type in a number to set the value.

You can set the tool to accept only certain characters or patterns under Fielding. There are two main settings, Variable number of characters and Fixed number of characters.

1. Variable number of characters

   The tool reads all the characters in the image.

   

   Acceptable Characters: Specify what type of characters the Read tool recognizes.

   • Any character: The tool searches for letters, numbers, and symbols (for example <, $, ?).

   • Numerical character only: The tool searches for numbers only.

   • Alphabetical characters only: The tool searches for letters only.

   • Alphanumerical characters only: The tool searches for numbers and letters.

   Number of lines: Tick the box next to Specify number of lines if the characters in your image are arranged in multiple rows. Enter the number of rows in the Number of lines input field.

2. Fixed number of characters

   The tool reads a character pattern or character patterns on the image. The tool recognizes characters that does not fit the provided pattern, but returns an error.

   

   The pattern uses a simple regular expression style composed of constant characters (alphanumerical and special characters) and metacharacters.

   You can use the following metacharacters:

   • "\d": matches any numerical character [0-9].

   • "\l": matches any alphabetical character [a-z, A-Z].

   • "\w": matches any alphanumerical character [a-z, A-Z, 0-9].

   Examples of valid patterns:

   • "\d\d\d\d": matches a number composed of four digits.

   • "\l\l\l": matches a word composed of three letters.

   • "\d\d:\d\d:\d\d": matches a time in the HH:MM:SS format.

   • "N\d\d\d\l\l\l": can be used to read a serial number starting with 'N', followed by 3 digits and 3 letters.

   You can apply multiple patterns for one Read tool configuration by clicking the Add Pattern button. If you provide multiple patterns the tool returns the name of the matching pattern during reading.

   Formula used: 1C4RJH\w\w\w\w\d\d\d\d\d\d\d	Formula used: Z1\w06456\d\d\d\d\d

3. Flexible Fielding

   Flexible fielding allows you to capture specific texts and filter out false detections. The flexible fielding is defined using a series of fixed anchoring patterns (for example, “BEST BY” or “SERIAL”) and flexible Regex A regular expression (shortened as regex or regexp), sometimes referred to as rational expression, is a sequence of characters that specifies a match pattern in text. patterns (for example, to match digits, upper case letters, a specific range of characters, and so on). The anchoring and Regex patterns determine the allowed character classes in the text. Flexible fielding filters out candidates for different characters based on these patterns, finding the combination that best matches the specified patterns, effectively “coercing” the classification. For example, if the user is only looking for digits at a certain position, this can turn a ‘I’ into a ‘1’.

   Specific portions of the flexible fielding can be captured. The detected characters that match a capture group is reported in the string output. The other detected characters are not reported in the string output. The non-captured groups can be used to align the text or to filter out false, or flaky detections (for example, using wildcards).

   Flexible fielding computes a fielding score from the individual scores of the fielded characters. Both capturing and non-capturing groups are used to compute the fielding score, except for non-capturing wildcards. The fielding score can be used as a metric to measure how well the fielded text matches the target fielding.

   Make sure that all expected characters are read correctly before applying the flexible fielding expression. If needed, adjust the character size and/or the character find threshold.

   Key Regex-like components:

   • ".": Any single character including newlines

   • "\d": Digit [0-9]

   • "\l": Lowercase letter [a-z]

   • "\u": Uppercase letter [A-Z]

   • "\w": Alphanumeric [a-zA-Z0-9]

   • "[...]": Character set, for example [0-9A-F] matches digits or uppercase A-Z

   • "*, +, ?": Zero or more, one or more, zero or one of the preceding character

   • "{n}, {n,}, {n,m}": Exact, minimum, or range of repetitions

   • "()": Captures part of the matched pattern

   Using capture groups: Always use parenthesis to capture specific parts of the result. The fielding succeeds if there are captures and/or mandatory characters. It only fails if there are only optional, non-captured characters, for example ".*".

   Examples:

   • .*SERIAL(\d{5}): can be used to read a serial number starting with "SERIAL" followed by five digits, capturing the digits and ignoring preceding text.

   • .* (LOT[A-F]\d{3,4}): can be used to read a lot number starting with a letter between A and F, followed by 3 to 4 digits, capturing both the LOT prefix and the actual lot number, ignoring preceding text.

   • .*BEST.*BEFORE.*(\d{2}).*(\u{3}).*(\d{4}): can be used to read an expiry date such as BEST BY 12 JAN 2025, capturing only the date and ignoring false detections in-between these character groups using wildcards.

   • .*USEBY:?(\d{8}): can be used to read an expiry date such as USE BY 12 01 2025, capturing only the date, ignoring preceding text as well as any flaky detection of the colon (":") character in-between BY and the date.

   • LOT(.*)BATCH: can be used to read a string starting with LOT, capturing any text between the words LOT and BATCH, and ignoring both LOT and BATCH.

   Sample Image	Expected Read String	Flexible Fielding Expression	ViDiELRead Result
   	The identifier can contain any digits and can vary in length.	(\d+)	1005404508
   	The identifier starts with JJ, followed by exactly six digits.	.*(JJ\d{6})	JJ200076
   	The identifier starts with TT, followed by exactly seven digits.	.*(TT\d{7})	TT4195768
   	The identifier begins with the fixed prefix CS, after that there are exactly five numeric digits. After the digits, there is the fixed letter D. Finally, the text ends with exactly six numeric digits.	.*(CS\d{5}D\d{6})	CS22116D640441
   	The identifier starts with EMB, followed by exactly five digits, a hyphen, and then exactly seven digits	.*(EMB\d{5}-\d{7})	EMB59139-1113598
   	The text contains any lower and upper case characters. Note: You can curve the region by using the ScaleImage() function Functions are tools that are available in Spreadsheet for processing and analyzing acquisitions or other results. You can add functions to your Spreadsheet job to create tool chains and produce results for specific applications..	([a-zA-Z&]+)	Holdtabdown&turn
   	The lot number consists of alphanumeric characters (letters and digits) following the LOT: label. The expiration date is in the format MM-YYYY, following the EXP: label, with the month and year separated by a hyphen.	.*LOT:(\w+).*EXP:(\d{2}-\d{4})	9241A81N 01-2025
   	The manufacturing date follows the MFG: label and is in the format MM/DD/YYYY. The expiration date follows the EXP: label and is also in the format MM/DD/YYYY.	.*MFG:(\d{2}/\d{2}/\d{4}).*EXP:(\d{2}/\d{2}/\d{4})	6/14/2024 6/13/2027
   	The first part is an alphanumeric identifier (letters, numbers, and hyphens) that can vary in length. In the second line, there is a timestamp in the format DD/MM/YYYY HH:MM, where the date is separated by slashes and the time by a colon.	([A-Z0-9-]+)\n(\d{2}/\d{2}/\d{4})(\d{2}:\d{2})	L141E18-FG 13/08/202510:55

Train letters, numbers, and symbols to the tool.

1. Load your images by selecting the folder icon in the bottom-left corner. You cannot open individual pictures, only folders, so it is recommended to put all your images under one directory.

2. Type in the corresponding characters for the selected letters and numbers. Label and train all expected characters (A-Z, 0-9) for your application before deploying the tool. To use the Read tool you need to train at least 3 images. The more images and characters you train the higher the quality of your output will be. Also, fixturing with the pattern tool often leads to improved speed and tool performance.

   

   By default, the tool identifies possible characters in the image by placing a green bounding box around them. You can move the bounding boxes freely, but the size can only be modified under the Character Size setting. To add more bounding boxes, click one of the boxes and select the Add button. To remove a box, select it and click Remove. To remove all your boxes, select the Clear All option. To accept your settings, click Accept All.

   Note: Every character needs to be labeled in the search region. Removing labels from valid characters trains the tool to ignore them.

Shows the number of trained characters and source images, and the confidence level of the tool in a given character. The lower the percentage is, the less likely that a result is correct.

You can see the percentage by hovering over the colored line under the character. The color also shows the confidence level:

• Green: high certainty.

• Yellow: medium certainty.

• Red: low certainty.

You can sort the trained data either by character or image:

You can jump to retraining a certain character by left-clicking its image under By Character view, or you can retrain all characters on one image by clicking the edit icon next to the appropriate row in By Image view.

You can also search for a specific character by typing it in the search bar under both views. The tool differentiates between upper-case and lower-case letters.

You can also delete samples by checking the box next to the appropriate row and clicking Delete Samples.