Summary: Image processing is a rapidly evolving field with immense significance in science and engineering. One of the latest applications of Image processing is in Intelligent Character Recognition (ICR). Intelligent Character Recognition is the computer translation of handwritten text into machine-readable and machine-editable characters. It is an advanced version of Optical Character Recognition system that allows fonts and different styles of handwriting to be recognized during processing with high accuracy and speed. ICR, in combination with OCR and OMR (Optical Mark Recognition), is used in forms processing.
This abstract explores an RNN-based approach to online handwritten recognition problem. Our method uses data from an accelerometer and a gyroscope mounted on a handheld pen-like device to train and run a character pre-diction model. We have built a dataset of timestamped gyroscope and accelerometer data gathered during the manual process of handwriting Latin characters, labeled with the character being written; in total, the dataset con-sists of 1500 gyroscope and accelerometer data sequenc-es for 8 characters of the Latin alphabet from 6 different people, and 20 characters, each 1500 samples from Georgian alphabet from 5 different people. with each sequence containing the gyroscope and accelerometer data captured during the writing of a particular character sampled once every 10ms. We train an RNN-based neural network architecture on this dataset to predict the character being written. The model is optimized with categorical cross-entropy loss and RMSprop optimizer and achieves high accuracy on test data.
The stroke sequence of characters is significant for the character recognition task. In this paper, we propose a stroke-based character recognition (SCR) method. We train a stroke inference module under deep reinforcement learning (DRL) framework. This module extracts the sequence of strokes from characters, which can be integrated with character recognizers to improve their robustness to noise. Our experiments show that the module can handle complicated noise and reconstruct the characters. Meanwhile, it can also help achieve great ability in defending adversarial attacks of character recognizers.
Convolution Neural Networks (CNN) have recently achieved state-of-the art performance on handwritten Chinese character recognition (HCCR). However, most of CNN models employ the SoftMax activation function and minimize cross entropy loss, which may cause loss of inter-class information. To cope with this problem, we propose to combine cross entropy with similarity ranking function and use it as loss function. The experiments results show that the combination loss functions produce higher accuracy in HCCR. This report briefly reviews cross entropy loss function, a typical similarity ranking function: Euclidean distance, and also propose a new similarity ranking function: Average variance similarity. Experiments are done to compare the performances of a CNN model with three different loss functions. In the end, SoftMax cross entropy with Average variance similarity produce the highest accuracy on handwritten Chinese characters recognition.
There are two problems that must be solved. Character segmentation is used to locate individual characters and find their correct order according to position of individual strings in the image and position of character in the string. Determination of location consists of determination of translation and determination of rotation and this must be done irrespective to all other objects in the image. Character recognition is used to determine the relation between images of individual characters and symbols they represent (characters). There is a lot of different methods for character recognition, but thy are not all suitable for industiral applications.