Currently I am using a deep learing model which is called "Yolov2" for object detection, and I want to use it to extract text and use save it in disk, but i don't know how to do that, if anyone know more about that, please advice me
I use Tensorflow
Thanks
The word accuracy attained by the YOLO model was 88% and coupled with the Inference module TEYSuR attained a word accuracy of 96%. Hence, this system can be successfully used for extracting text from images with high efficiency.
The EAST deep learning text detector We call the algorithm “EAST” because it's an: Efficient and Accurate Scene Text detection pipeline. The EAST pipeline is capable of predicting words and lines of text at arbitrary orientations on 720p images, and furthermore, can run at 13 FPS, according to the authors.
YOLO is an algorithm that uses neural networks to provide real-time object detection. This algorithm is popular because of its speed and accuracy. It has been used in various applications to detect traffic signals, people, parking meters, and animals.
Optical character recognition (OCR) is a technology that extracts text from images. It scans GIF, JPG, PNG, and TIFF images. If you turn it on, the extracted text is then subject to any content compliance or objectionable content rules you set up for Gmail messages.
If you use the pretrained model, you would need to save those outputs and input the images into a character recognition network, if using neural net, or another approach.
What you are doing is "scene text recognition". You can check out the Reading Text in the Wild with Convolutional Neural Networks paper, here's a demo and homepage. Github user chongyangtao has a whole list of resources on the topic.
I have a similar question and I am making a digit detection model with svhn dataset. It is not a finished project yet, but it seems to work well. You can see the code at Yolo-digit-detector.
If you love us? You can donate to us via Paypal or buy me a coffee so we can maintain and grow! Thank you!
Donate Us With