Can we use Yolo to detect and recognize text in a image

tensorflow deep-learning text-recognition
Kamel BOUYACOUB picture Kamel BOUYACOUB · Mar 24, 2017 · Viewed 21.8k times · Source

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

Answer

vega picture vega · Mar 27, 2017

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.

Related questions

TensorFlow - Text recognition in image

I am new to TensorFlow and to Deep Learning. I am trying to recognize text in naturel scene images. I used to work with an OCR but I would like to use Deep Learning. The text has always the same …

Read More
What is the difference between 'SAME' and 'VALID' padding in tf.nn.max_pool of tensorflow?

What is the difference between 'SAME' and 'VALID' padding in tf.nn.max_pool of tensorflow? In my opinion, 'VALID' means there will be no zero padding outside the edges when we do max pool. According to A guide to …

Read More
Keras, How to get the output of each layer?

I have trained a binary classification model with CNN, and here is my code model = Sequential() model.add(Convolution2D(nb_filters, kernel_size[0], kernel_size[1], border_mode='valid', input_shape=input_shape)) model.add(Activation('relu')) model.add(Convolution2…

Read More