Zia can recognize and classify images of living and non-living objects and alert whenever an invalid image is uploaded to CRM. Images of automobiles, stationary items, sports personnels, mobile phones etc. can be uploaded to train Zia in identifying objects of various kinds. You can use pre-trained object classifiers provided by Zoho CRM or images of your own for training purpose.
For example, a real estate agent can use image validation to validate property images before adding them to the CRM system. The agent can send the images or the entire record to the senior agents for approval in case of invalidity. By validating images before adding them to the property listings they can prevent invalid entries.
Enabling permission to configure image validation rule and review images
CRM administrators who have the permission to manage configuration or review images enabled in their profile will be able to create image validation rule and review images respectively. You can give the manage configuration permission to selected users who will only create the rule and not be responsible for reviewing the images and similarly the reviewers can be restricted from viewing or creating the configuration.
Under Profiles > Zia > Image Validation, there are two permissions which allow the user to do the following:
- Manage configuration: Users with this permission can only create, edit, view, enable, disable or delete a rule. They cannot review the images.
- Manage action: Users with this permission can review the images and approve or reject them. These users will not be allowed to view or create a rule.
Remember that when you toggle on Image validation for a profile, manage action will be automatically enabled. However, you have to select manage configuration manually.
To give profile permission
- Go to Setup > Users and Control > Security Control and choose a profile.
Only admin profiles or its equivalent clone can be selected.
- In Profile, go to Setup Permissions and click Zia.
- Under Zia, toggle on Image Validation.
Manage action will be enabled automatically. Click to disable.
- Select Manage Configuration or/and Manage Action.
Setting up image validation rule
Record images that are uploaded manually or enter through CRM portals or API may sometimes be incorrect or illegible. Zia can identify these images and help the reps take action to remove or replace them.
Setting up the image validation rule involves the following steps:
- Records that need to undergo image validation: You can set an image validation rule for both standard and custom modules. You can define the criteria for records to undergo image validation. This can be helpful if you have a variety of record images in a single module, like both houses and villas in a Properties module or both cars and motorbikes in the Vehicles module, and only want the images of villas or motorbikes to be validated.
- Field that contains the image: You can select record images or images uploaded to the image upload field for validation. The image upload field will be available during configuration only if it has one image uploaded in it.
Actions to be performed if the image is invalid: Zia will indicate that an image is invalid if it fails to comply with the expected set of images for that module. For example, if the Properties module only contains images of villas or individual houses and an image of an apartment is uploaded, Zia will identify the mismatch and return an error. You can ask Zia to perform a range of actions when an image cannot be validated:
Do not create or update a record: The record will not be created or updated. It will be considered rejected, you may edit and resubmit for validation. Only the submitter can see a notification in the record detail page that states the image validation has failed and the record can be edited and re-submitted. These failed records can be viewed under the custom view called Records that entered Image Validation.
- Send image for approval: Only the record image will be sent for the CRM admin's approval.
- Send record for approval: The records sent for approval can be viewed under the My Jobs or record detail page by the approvers. If the record fails image validation, it will be automatically locked for approval. The users (who are not record approvers) can view the records awaiting image validation or approval, and records that are rejected or under processing in the list view under Records [module name] under image validation.
- Create record by removing image: A new record will be created in CRM without the record image.
Uploading training data for Zia: You can upload either pre-trained images or your own images as training data to enable object identification. Zia requires a minimum of 5 images of an object to classify it appropriately and find other objects that don't match. The training data is classified into two types:
The pre-trained images are classified into following categories, e.g.: food, cars, motorbikes, and bicycles. You can upload images of one set at a time.
You can only upload images of one object type at a time. This applies to all three (desired, undesired, pre-trained) image types.
Best practices for uploading images
Take a look at the below cases that highlight the possible problems and the ways to troubleshoot them:
Case 1. A stationary supplier wants to validate images of pens and pencils received through bulk orders from the vendors. They upload the images of these objects as classifiers. However, when bulk orders are received most images of biros (ballpoint pens) are marked invalid.
Solution: The training data consists of images of all kinds of pens such as fountain pens, gel pens, marker pens, and pencils except ballpoint pens. Therefore, though Zia can identify a variety of pens it cannot identify a ballpoint pen and shows it as an invalid image. Hence, in order to get accurate result it is important to upload all images of all the objects that you want to be classified.
Case 2. A mobile phone dealer wants to validate images of smart phones. He uploads pictures of all the brands of smartphones he sells, but still some images of mobile phones are shown as invalid.
Solution: The dealer uploads front images of all brands of smartphones. However, some images that are taken from other angles are difficult to identify and draw similarity between objects. Therefore, it is essential to upload images of objects from various angles for ease of identification and accuracy of results.
Case 3. A distributor of toys and puzzles is confused because images of geometric or shape puzzles are identified as invalid objects though the same type of images have been used as classifiers.
Solution: A geometric shape appears similar from every angle thus uploading image of an object from either angles would always give accurate results. However, there must be enough images to draw similarity between objects. Hence, while uploading images of objects that may appear similar from all angles it is necessary to have at least 5 to 6 images (minimum requirement for Zia's image validation) of the object. We recommend to repeat one image 5 times for the system to draw correlation.
Points to remember
- If you want to upload images from your desktop, you must follow these guidelines to achieve the best results from Zia:
- The images must be in these format: JPG, JPEG, PNG, GIF, BMP, and TIFF.
- The training data should be as close as possible to the data to be validated.
- In general, you should try to provide multiple angles, resolutions, and backgrounds in your training images.
- Vision models generally cannot recognize patterns that humans cannot. So if a human cannot recognize a pattern by looking at the image for around half to one second, the model probably cannot be trained to do it either.
- You can upload as many images as you want for a better accuracy, but minimum 5 images of a particular category must be uploaded for Zia to validate images.
- Do not combine images from different categories. Use images that best depict your category.
- The training accuracy score will be impacted if these guidelines are not followed.
- We recommend you to select record or image approval as the action until you are sure of the results shown by Zia.
- We calculate the accuracy of the image validation rule by evaluating the points outlined in the guidelines. Only if a rule has a training accuracy above 80% the system will allow you apply it.
- In case multiple rules are configured, a record will enter the rule that based on the configuration rules that it matches.
To create an image validation rule
- Go to Setup > Zia > Vision > Get Started.
If you have created rules before, click New Image Validation Rule.
- In Create Image Validation Rule page, enter the Rule name (e.g. Image validation for Houses and Villas).
In Which record(s) do you want to consider?:
- Select the module from the drop-down list (e.g.: Properties).
- Set the criteria, either All records or Selected records (e.g.Property type is individual house or villa].
In What action should Zia perform upon failure?, select an option:
- Do not create or update record
- Send image for approval
- Send record for approval
- Create record by removing image
- In Upload Training Data upload your Desired or Undesired images.
You can either choose from the gallery or upload your own images.
- Click Save.
Testing the model
With the Test the model feature, the admin can assess the pattern Zia has created based on the training data. It can instantly provide results whether the give input matches with the model Zia has created and show if it is a success or failure. Based on these results the admin can make changes to the model.
To test a model,
- Go to Setup > Zia > Vision.
- Select the rule for which you want to test the model.
- Click Test the model.
- Upload the image that needs to be validated by Zia.
- Zia will validate the image and deliver the result.
Record and Image approvals from My Jobs
The records or images can be approved from the My Jobs tab. The admin must approve the record only then can the image be approved. If the record is rejected the image is automatically disqualified.
Delete or deactivate a rule
You can delete or deactivate a rule if required. If you chose to approve the records that enter the rule, then upon deleting the rule you will be notified about the records that are awaiting an approval. Similarly, upon deactivating a rule the existing records that are awaiting an approval will be retained as is, however new records will not be allowed to enter the rule.