Skip to content

How to use Google Lens OCR text tool on desktop (Full Guide)

How to use Google Lens OCR text tool on desktop

One of Google’s most impressive innovations is Google Lens. Although it may not be as popular as the former, nevertheless, it’s an advanced, interactive, and unique photographic search engine for easier and quicker integration of the world around us. 

In case you’re looking for different Artificial Intelligence (AI) applications excellently combined into one unique tool, Google Lens is the best illustration of this. This Search Engine can easily describe text, identify objects, do humanoid translation, and lots more.

Recently, Google released an update to Lens on the desktop or PC, integrating the OCR text tool. In this guide, we will discuss what this tool is, and its advantages to users.

On a quick note, this tool is a feature that enables your device or camera to recognize or identify text. Also, we will be discussing how you can use the newly released OCR text tool on Google Lens on your PC/desktop.


What is Google Lens?

Google Lens was initially released as an add-on for image search on Google, the most popular and most used search engine worldwide. As the years went by, developers continued integrating new features to enhance their functionalities.

Now, Google Lens has evolved into a standalone platform that offers its users many amazing services. For instance, the two most useful and appreciated tools on Google Lens include text and object recognition. 

Have you ever taken a good look at an object, while wondering what it’s called or what it does, and then tried to look it up on the internet? 

Google Lens makes this type of search easier. You can quickly scan an object, either inanimate or animate. Then Google will show you all the relevant information, similar products, and everything else you need to know about the object.

Text recognition on the other hand has lots of advantages as well. It’s especially useful for foreigners in other countries. With the help of Google Lens, it’s easy to translate any text form into the language you understand. 

You can use it on documents, billboards, road signs, shopping tags, and lots more. The Google Lens app on your mobile phone can save your contact information through business cards or take note of an event in your Calendar from an advert by marking it. Also, Google now allows you to use the Lens search on both mobile and PC/desktop.

You should also know that OCR

OCR stands for Optical Character Recognition. Maybe you’ve noticed this term when trying to convert a PDF document into Word or some other rich text format. 

This tech identifies text from images and then converts it into a format you can edit. This means any platform with OCR can easily convert photos into computer-readable text. The functionality of this tool is no doubt exceptional.

Usually, you’ll see OCR integrated into systems with a balanced combination of hardware and software. Google Lens is the exact illustration of such a system. 

You easily scan text in the real world around you and then transform it into a digital form. OCR can be enhanced with AI to help you understand the text better than using any other program.

Some examples of these applications include indexing printed documents, archiving information, automating data entry, and synchronous translation. Google Lens saves you a lot of time and effort that you can invest in other tasks.


How to use the OCR text tool on Google Lens to convert text

It’s important to note that OCR has been a part of the Google Lens app for some time now, except that it has been extended recently for use on desktops and computers. Also, there have been a couple of adjustments to the app interface.

Now, you can open a picture in Google Chrome with Google Lens on a side panel. This helps you to keep track of the main page at the same time.

In case the Google Lens option doesn’t appear on your Chrome, you should stick to this guide till the end as we’ve properly explained the process of enabling Google Lens using experimental flags. 

With that said, here’s how you can use the OCR text tool on Google Lens for converting texts.

Step 1: Launch Google Chrome on your device (computer) and navigate to the image you want to work on. You should know that this method works the same for different images displayed on your internet browser.

Step 2: Right-click on the chosen image. Select “Open image in new tab” from the options in the drop-down menu. This will display the picture in its best resolution.

Step 3: You need to Right-click on the image again. Select “Search image with Google Lens” from the options in the drop-down menu. This will open the Google Lens panel on the right side of your screen.

Step 4: You will see the image preview with three buttons under it. Select “Text.” This will prompt Google Lens to implement the OCR algorithm and identify every bit of text in that image.

Step 5: Tap the “Select all text” button at the bottom.

Step 6: Select the “Copy text” option to move all text to your device clipboard. For other options, you can do a Google search or listen to it. While scrolling down the panel, you’ll see other relevant search results displayed on the page. 

In case you don’t want to copy all the text, there is another method of making selections. Move your cursor to the image preview and select any word or sentence you’d like to copy.


How to use the OCR text tool on Google Lens for translation

Another important use of the OCR text tool is its real-time translation. You can easily translate from one language to any other supported language on Google. 

So, here’s how to perform a synchronous translation using Google Lens’ OCR text tool.

Step 1: Launch Google Chrome on your device (computer), then go to the image you’d like to work on. Note that this method works the same for different images displayed on your internet browser.

Step 2: Right-click on the selected image. Select “Open image in new tab” from the options in the drop-down menu. This will display that picture in its best quality.

Step 3: Right-click on the selected image again. Select the “Search image with Google Lens” option from the drop-down menu. This will open the Google Lens panel on the right side of your device screen.

Step 4: You will see the image preview with three buttons under it. Tap the “Translate” option and chose the language you’d like to translate to from the top.

Google will detect the language of the text inside the image automatically. However, if there are more languages in the picture, you need to select each one manually.

Step 5: After selecting the language, the text will be translated. Then, you can just copy the translated text, open it in Google Translate, or listen to it.

Also, the image preview will change its view and show the converted text instead. This will help you mark correspondences between the real text you translated and its translation.


How to force enable Google Lens on desktop?

Now, this is the part where we talk about those who can’t find the Google Lens feature on their Chrome browser. 

Usually, Google Lens may not appear on your browser if your browser isn’t up to date, or you’ve disabled Google Chrome updates. 

If this is the case, you can enable it back on Google Chrome via the Chrome experimental flags. Don’t be bothered by the word “experimental.” Using these flags to enable Google Lens is pretty easy. 

These flags are just settings that haven’t been released into the main versions of the Google Chrome browser. In other words, these settings are still being experimented on. 

These settings are developed under the Chromium project. Therefore, keep in mind that although you can use these flags, they haven’t been rolled out in regular browser settings. 

Some of the flags mentioned above can enable the Google Lens side panel. However, our focus here is the flag that enables Lens image and region search to understand the visual content you see on Google Chrome.

Step 1: Launch “Google Chrome” on your device (computer), then enter “chrome://flags” in your browser’s address bar. That will bring up the “Experiments” page.

Remember that all Chrome flags are features that are still being experimented on. Therefore, don’t start tweaking any settings unless you need to.

Step 2: Search for “Lens” on the “Experiments” page, then mark the button at the front of the “Enable Lens features in Chrome” flag. You will see that it is set to “Default.”

Step 3: Select it and click on the “Enabled with Side Panel” option from the drop-down menu.

Step 4: Whenever you change any default setting in the experimental flags, a “Relaunch” button will show up at the bottom right corner of your device’s screen. 

The new modification you made will only take effect after restarting the browser. So, click on the “Relaunch” button to restart Google Chrome.

After restarting your browser, carefully go through the outlined methods in the previous parts of this guide.


No doubt, Google Lens is an innovative and efficient tool for identifying objects, performing live translations, classifying images, and transforming text in images into a format you can edit. 

This is why you need to know how to use the OCR text tool on Google Lens on your desktop, as it serves you many purposes from translation to text conversion. 

If the option of opening images with Google Lens does appear on your desktop, enabling it via Chrome experimental flags is the best option you’ve got.