Subject your printed texts into your processes
Intelligent character recognition is a cutting-edge technology that can recognize and capture characters in printed texts and transform them as digital data.
Why do you need ICR in CRM?
From business cards to product tags, registration forms to invoices, ID proofs to shipping labels, your operations rely on data printed across a variety of physical assets. Yet, in today's fast-paced business environment, your agents are spending valuable time and effort manually converting these printed texts into usable data—just to get started.
Say, you are a busy sales representative. You met with a few high-value prospects at the customer conference and exchanged business cards. Coming back to the office, you create a record, fill in their details like name, phone number, website, address, and such for each card you have obtained.
For another example, imagine a post-production workflow, where the warehouse manager records information like product name, SKU number, date of manufacture, and so on from the product label attached to the packed product into Zoho CRM.
In both these scenarios, the actual process of lead nurturing and stock management starts only after the data is uploaded in the system, but the agents had to spend most of their time taking these data into the system.
Thus, to help simplify record creation and augment business productivity, Zia Vision is optimized with the ICR function.
Here's a glimpse of how a record can be created from an image:
Getting started with ICR
You can employ ICR to create records:
- If your data is available as non-editable image
- If your data source has a standard format
- You have a volume of data to be added one at a time
Training Zia
Like any AI model, Zia Vision requires preliminary training on formats and orientation of sample images.
To train
- Go to Setup> Zia > Vision > Intelligent Character Recognition.
- In the Intelligent Character Recognition page, click Create New Rule to create a training set for a module.
- In the Create New Rule page, do the following:
- Provide a rule name
- Choose the desired module
- Choose the desired layout
- Click Proceed.

- In the image upload page, click Upload Image(s).

- In the ensuing image upload for extraction screen, add your image either by dragging and dropping them or by browsing from the file.
- To browse from file, click the Browse button on the screen and click Extract.

- You will be landing on the training studio. Zia would have recognized the characters and marked all the valid characters as the region of interest using the bounding box.
- Every word in the image is recognized by Zia. This includes the field name and the intended field values.
- If what Zia recognized is accurate, you can click on the box and associate it with the field name from the layout.
- If not, you can also drag the margins to cover the characters and associate them as one field's value.
- After you have associated the localized characters with fields, Click Train.
- Click Save to save the rule.
Note:
- You need to create ICR rules (image configuration) to start creating records.
- You can create up to three rules for an organization.
- You can upload up to two images per layout of a module.
- At any point in time, you can edit, update, or delete the rule.
- For accurate association, we recommend you tag the character area covering the length and breadth of the characters without cutting the corners, overlapping on the neighbouring characters.
- You can zoom the image in and out for legibility in association.
- Kindly ensure the image you upload adheres to the guidelines.

Limitations:
- As part of ICR, Zia can recognize texts and human face. Other objects will not be recognized.
- The scope of recognition is limited only to the card-type orientation. The ability to extract printed texts and handwritten scripts from tables, forms, brochures, pamphlets, and more is under development.
- The values extracted from the images can be associated only with the fields of a layout. Associating with values in subform is not possible.
Accuracy:
Accuracy in text-to-digital transformation is based on training and consistent usage of the model. In addition to the training set you upload, Zia trains itself from the images you upload to create records.
To ensure acceptance and accuracy, kindly ensure the following prerequisites:
- You have created ICR rules under Zia Vision
- The uploading image should have the same layout as the sample.
- The image should be of card-based orientation.
If your image comply with these pre-requisites and ICR guidelines (mentioned above), then Zia will be able to give you a perfect match.
Creating records
To create a record from an image
- Go to the desired module and click on the drop-down available next to Create record. Remember, you should have configured the ICR rule to enable this option.
- In the Create Record from Image page, drag and drop the image for extraction. You can also click on Browse to source the image from your file.
- Click Proceed. Zia will start extracting the data.
- Once the extraction is done, Zia would have associated the field values from the image.

- Based on the accuracy of the extraction, you can choose to keep the value associations done by Zia. Remember, Zia will extract all characters in an image. This includes data that is not a value in your layout. You can unselect them if you don't need them.
- Click Proceed.
- If this image is not satisfactory, you can try a new image.
Updating existing records
In addition to creating records from images, you can also enrich your existing records using the image uploaded in your records.
To enrich existing records
- Go to the record you want to enrich and click on the image you'd like to refer to for enrichment.
- Click on the Enrich from Image button in the top-right of the preview.
- Zia would have localized characters in the image. Validate the enriched and existing data, and click Proceed.
- After associating, you will be navigated to the Edit record page with enriched fields highlighted for quick reference.
- Click Save to record the new changes.
Note:
The record will be enriched with standard view only. Enriching a record in Canvas view is not supported.
Business scenarios
One-click insurance
Insurance is among the long and time-consuming processes ever to exist. To transform this, Coverly—the techsavvy insurance provider, have come up with one-click insurance requests—where customers submit a Government-authorized ID proofs to create instant policies. Using ICR, the insurance agents working on these requests can use the image to create new records in simple steps.
Completing vendor BGV
Zylker is an online education platform that allows domain experts register and conduct courses on their platform. For enhanced UX, the platform onboards the creators via webforms with only few basic details like name, email, and ID proof. Just with these information, the business cannot authorize the creator; however, using the ID proof, Zylker can extract their data and enrich their records with required information.
Reaching out to the tradeshow prospects
One of the goals of conducting tradeshows is to attract new leads, and a quicker way of getting acquainted is by exchanging business cards. Using ICR, the reps can quickly create lead records and start qualifying and nurturing them without spending time in creating records manually.
In conclusion, ICR in Zoho CRM
- Saves your time and effort
- Improves agility and productivity
- Takes care of the operational logistics, so the agents can take care of the processes
- Alleviates fatigue caused by constant gaze shifting between the source and the screen