Convert characters contained in images to text dataOptical Character Recognition (OCR)Widely used as a method of digitizing printed materials such as invoices, receipts and business cards. Open source OCR systems “” have realized this kind of OCR with a deep learning framework.pp-ocrv2There is a demo version of “”paddleocr“Is.
PaddleOCR – A Hugging Face Space by Akhleeq
GitHub – PaddlePaddle/PaddleOCR: Awesome Multilingual OCR Toolkit based on PaddlePaddle (Practical Ultra Lightweight OCR System, Supports 80+ Language Recognition, Provides Data Annotation and Synthesis Tools, Training Between Server, Mobile, Embedded and IoT Devices and supports deployment
Paddle OCR and PP-OCR v2 are deep learning frameworks developed by Baidu.paddle paddlebuilt on the basis of PP-OCRv2, developed by technical researcher Yuning Du and others, recognizes 80 languages, including Chinese, English and Japanese, from deep learning and outputs them as text. It is said to be developed as open source with efficiency and speed.
Paddle OCR, which is a demo version of PP-OCR v2, has been released, so I’ll actually use it. First, Paddle OCRtop pageto use.
Click “Drop image here or click to upload” on the left side of the screen to open Explorer. Select the image you want to OCR and upload it.
When the upload is complete, select the language you want to analyze from “Language” and click “Submit”. This time, I’ll analyze it in Japanese.
After a while, the analysis is completed and the result is displayed as an image file on the right side of the screen. The analysis took 78.69 seconds. The analysis result is output as an image file, so you cannot copy the text.
Looking at the results of the analysis in detail, it seems so. The text information read from each paragraph and its accuracy are indicated by numbers. I’ve read words like “fruit mixed juice” and “raw material name”, but I can see roughness with little precision, like “/” being “no” and “ml” being “0”.
Next is the PS5 controller”double feelingI will try it with package.
When I analyzed this with Japanese settings, I found that “PlayStation” was read as “PIqy5LatI0n” and “Wireless Controller” was read as “WIrelesSContr0ler”. It took 1.91 seconds.
When I changed the analysis language to English and analyzed it again, it read with fairly high accuracy, so it’s good to change the language setting when reading the alphabet.
PaddleOCR can read in English with fairly high accuracy, but it seems that the accuracy in Japanese is not as good as it is a demo version. I started using it thinking that it could be used to “read the contents of a package of a product written in a foreign language that I don’t know well”, but since it doesn’t output as text So I can’t use it. , this is just a demo version which I was well aware of.
In addition, GitHub, Paddle OCR . Feathertoolkitis delivered.
Copy the title and URL of this article